feat: initial project setup
This commit is contained in:
Vendored
+25
@@ -0,0 +1,25 @@
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2024 lldacing
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
|
||||
---
|
||||
|
||||
The code and models of BiRefNet are released under the MIT License.
|
||||
+203
@@ -0,0 +1,203 @@
|
||||
import os
|
||||
import math
|
||||
|
||||
import folder_paths
|
||||
|
||||
|
||||
class Config:
|
||||
def __init__(self, bb_index: int = 6) -> None:
|
||||
# PATH settings
|
||||
# Make up your file system as: SYS_HOME_DIR/codes/dis/BiRefNet, SYS_HOME_DIR/datasets/dis/xx, SYS_HOME_DIR/weights/xx
|
||||
# self.sys_home_dir = [os.path.expanduser('~'), '/mnt/data'][0] # Default, custom
|
||||
# self.data_root_dir = os.path.join(self.sys_home_dir, 'datasets/dis')
|
||||
|
||||
# TASK settings
|
||||
self.task = ['DIS5K', 'COD', 'HRSOD', 'General', 'General-2K', 'Matting'][0]
|
||||
self.testsets = {
|
||||
# Benchmarks
|
||||
'DIS5K': ','.join(['DIS-VD', 'DIS-TE1', 'DIS-TE2', 'DIS-TE3', 'DIS-TE4']),
|
||||
'COD': ','.join(['CHAMELEON', 'NC4K', 'TE-CAMO', 'TE-COD10K']),
|
||||
'HRSOD': ','.join(['DAVIS-S', 'TE-HRSOD', 'TE-UHRSD', 'DUT-OMRON', 'TE-DUTS']),
|
||||
# Practical use
|
||||
'General': ','.join(['DIS-VD', 'TE-P3M-500-NP']),
|
||||
'General-2K': ','.join(['DIS-VD', 'TE-P3M-500-NP']),
|
||||
'Matting': ','.join(['TE-P3M-500-NP', 'TE-AM-2k']),
|
||||
}[self.task]
|
||||
# datasets_all = '+'.join([ds for ds in (os.listdir(os.path.join(self.data_root_dir, self.task)) if os.path.isdir(os.path.join(self.data_root_dir, self.task)) else []) if ds not in self.testsets.split(',')])
|
||||
self.training_set = {
|
||||
'DIS5K': ['DIS-TR', 'DIS-TR+DIS-TE1+DIS-TE2+DIS-TE3+DIS-TE4'][0],
|
||||
'COD': 'TR-COD10K+TR-CAMO',
|
||||
'HRSOD': ['TR-DUTS', 'TR-HRSOD', 'TR-UHRSD', 'TR-DUTS+TR-HRSOD', 'TR-DUTS+TR-UHRSD', 'TR-HRSOD+TR-UHRSD', 'TR-DUTS+TR-HRSOD+TR-UHRSD'][5],
|
||||
'General': 'DIS-TE1+DIS-TE2+DIS-TE3+DIS-TE4+DIS-TR+TR-HRSOD+TE-HRSOD+TR-HRS10K+TE-HRS10K+TR-UHRSD+TE-UHRSD+TR-P3M-10k+TE-P3M-500-P+TR-humans+DIS-VD-ori', # datasets_all
|
||||
'General-2K': 'DIS-TE1+DIS-TE2+DIS-TE3+DIS-TE4+DIS-TR+TR-HRSOD+TE-HRSOD+TR-HRS10K+TE-HRS10K+TR-UHRSD+TE-UHRSD+TR-P3M-10k+TE-P3M-500-P+TR-humans+DIS-VD-ori', # datasets_all
|
||||
'Matting': 'TR-P3M-10k+TE-P3M-500-NP+TR-humans+TR-Distrinctions-646', # datasets_all
|
||||
}[self.task]
|
||||
|
||||
# Data settings
|
||||
self.size = (1024, 1024) if self.task not in ['General-2K'] else (2560, 1440) # wid, hei. Can be overwritten by dynamic_size in training.
|
||||
self.dynamic_size = [None, ((512-256, 2048+256), (512-256, 2048+256))][0] # wid, hei. It might cause errors in using compile.
|
||||
self.background_color_synthesis = False # whether to use pure bg color to replace the original backgrounds.
|
||||
|
||||
# Faster-Training settings
|
||||
self.load_all = False and self.dynamic_size is None # Turn it on/off by your case. It may consume a lot of CPU memory. And for multi-GPU (N), it would cost N times the CPU memory to load the data.
|
||||
self.compile = True # 1. Trigger CPU memory leak in some extend, which is an inherent problem of PyTorch.
|
||||
# Machines with > 70GB CPU memory can run the whole training on DIS5K with default setting.
|
||||
# 2. Higher PyTorch version may fix it: https://github.com/pytorch/pytorch/issues/119607.
|
||||
# 3. But compile in 2.0.1 < Pytorch < 2.5.0 seems to bring no acceleration for training.
|
||||
self.precisionHigh = True
|
||||
|
||||
# MODEL settings
|
||||
self.ms_supervision = True
|
||||
self.out_ref = self.ms_supervision and True
|
||||
self.dec_ipt = True
|
||||
self.dec_ipt_split = True
|
||||
self.cxt_num = [0, 3][1] # multi-scale skip connections from encoder
|
||||
self.mul_scl_ipt = ['', 'add', 'cat'][2]
|
||||
self.dec_att = ['', 'ASPP', 'ASPPDeformable'][2]
|
||||
self.squeeze_block = ['', 'BasicDecBlk_x1', 'ResBlk_x4', 'ASPP_x3', 'ASPPDeformable_x3'][1]
|
||||
self.dec_blk = ['BasicDecBlk', 'ResBlk'][0]
|
||||
|
||||
# TRAINING settings
|
||||
self.batch_size = 4
|
||||
self.finetune_last_epochs = [
|
||||
0,
|
||||
{
|
||||
'DIS5K': -40,
|
||||
'COD': -20,
|
||||
'HRSOD': -20,
|
||||
'General': -20,
|
||||
'General-2K': -20,
|
||||
'Matting': -20,
|
||||
}[self.task]
|
||||
][1] # choose 0 to skip
|
||||
self.lr = (1e-4 if 'DIS5K' in self.task else 1e-5) * math.sqrt(self.batch_size / 4) # DIS needs high lr to converge faster. Adapt the lr linearly
|
||||
self.num_workers = max(4, self.batch_size) # will be decrease to min(it, batch_size) at the initialization of the data_loader
|
||||
|
||||
# Backbone settings
|
||||
self.bb = [
|
||||
'vgg16', 'vgg16bn', 'resnet50', # 0, 1, 2
|
||||
'swin_v1_t', 'swin_v1_s', # 3, 4
|
||||
'swin_v1_b', 'swin_v1_l', # 5-bs9, 6-bs4
|
||||
'pvt_v2_b0', 'pvt_v2_b1', # 7, 8
|
||||
'pvt_v2_b2', 'pvt_v2_b5', # 9-bs10, 10-bs5
|
||||
][bb_index]
|
||||
self.lateral_channels_in_collection = {
|
||||
'vgg16': [512, 256, 128, 64], 'vgg16bn': [512, 256, 128, 64], 'resnet50': [1024, 512, 256, 64],
|
||||
'pvt_v2_b2': [512, 320, 128, 64], 'pvt_v2_b5': [512, 320, 128, 64],
|
||||
'swin_v1_b': [1024, 512, 256, 128], 'swin_v1_l': [1536, 768, 384, 192],
|
||||
'swin_v1_t': [768, 384, 192, 96], 'swin_v1_s': [768, 384, 192, 96],
|
||||
'pvt_v2_b0': [256, 160, 64, 32], 'pvt_v2_b1': [512, 320, 128, 64],
|
||||
}[self.bb]
|
||||
if self.mul_scl_ipt == 'cat':
|
||||
self.lateral_channels_in_collection = [channel * 2 for channel in self.lateral_channels_in_collection]
|
||||
self.cxt = self.lateral_channels_in_collection[1:][::-1][-self.cxt_num:] if self.cxt_num else []
|
||||
|
||||
# MODEL settings - inactive
|
||||
self.lat_blk = ['BasicLatBlk'][0]
|
||||
self.dec_channels_inter = ['fixed', 'adap'][0]
|
||||
self.refine = ['', 'itself', 'RefUNet', 'Refiner', 'RefinerPVTInChannels4'][0]
|
||||
self.progressive_ref = self.refine and True
|
||||
self.ender = self.progressive_ref and False
|
||||
self.scale = self.progressive_ref and 2
|
||||
self.auxiliary_classification = False # Only for DIS5K, where class labels are saved in `dataset.py`.
|
||||
self.refine_iteration = 1
|
||||
self.freeze_bb = False
|
||||
self.model = [
|
||||
'BiRefNet',
|
||||
'BiRefNetC2F',
|
||||
][0]
|
||||
|
||||
# TRAINING settings - inactive
|
||||
self.preproc_methods = ['flip', 'enhance', 'rotate', 'pepper', 'crop'][:4 if not self.background_color_synthesis else 1]
|
||||
self.optimizer = ['Adam', 'AdamW'][1]
|
||||
self.lr_decay_epochs = [1e5] # Set to negative N to decay the lr in the last N-th epoch.
|
||||
self.lr_decay_rate = 0.5
|
||||
# Loss
|
||||
if self.task in ['Matting']:
|
||||
self.lambdas_pix_last = {
|
||||
'bce': 30 * 1,
|
||||
'iou': 0.5 * 0,
|
||||
'iou_patch': 0.5 * 0,
|
||||
'mae': 100 * 1,
|
||||
'mse': 30 * 0,
|
||||
'triplet': 3 * 0,
|
||||
'reg': 100 * 0,
|
||||
'ssim': 10 * 1,
|
||||
'cnt': 5 * 0,
|
||||
'structure': 5 * 0,
|
||||
}
|
||||
elif self.task in ['General', 'General-2K']:
|
||||
self.lambdas_pix_last = {
|
||||
'bce': 30 * 1,
|
||||
'iou': 0.5 * 1,
|
||||
'iou_patch': 0.5 * 0,
|
||||
'mae': 100 * 1,
|
||||
'mse': 30 * 0,
|
||||
'triplet': 3 * 0,
|
||||
'reg': 100 * 0,
|
||||
'ssim': 10 * 1,
|
||||
'cnt': 5 * 0,
|
||||
'structure': 5 * 0,
|
||||
}
|
||||
else:
|
||||
self.lambdas_pix_last = {
|
||||
# not 0 means opening this loss
|
||||
# original rate -- 1 : 30 : 1.5 : 0.2, bce x 30
|
||||
'bce': 30 * 1, # high performance
|
||||
'iou': 0.5 * 1, # 0 / 255
|
||||
'iou_patch': 0.5 * 0, # 0 / 255, win_size = (64, 64)
|
||||
'mae': 30 * 0,
|
||||
'mse': 30 * 0, # can smooth the saliency map
|
||||
'triplet': 3 * 0,
|
||||
'reg': 100 * 0,
|
||||
'ssim': 10 * 1, # help contours,
|
||||
'cnt': 5 * 0, # help contours
|
||||
'structure': 5 * 0, # structure loss from codes of MVANet. A little improvement on DIS-TE[1,2,3], a bit more decrease on DIS-TE4.
|
||||
}
|
||||
self.lambdas_cls = {
|
||||
'ce': 5.0
|
||||
}
|
||||
|
||||
# PATH settings - inactive
|
||||
# https://drive.google.com/drive/folders/1cmce_emsS8A5ha5XT2c_CZiJzlLM81ms
|
||||
# self.weights_root_dir = os.path.join(self.sys_home_dir, 'weights/cv')
|
||||
# self.weights = {
|
||||
# 'pvt_v2_b2': os.path.join(self.weights_root_dir, 'pvt_v2_b2.pth'),
|
||||
# 'pvt_v2_b5': os.path.join(self.weights_root_dir, ['pvt_v2_b5.pth', 'pvt_v2_b5_22k.pth'][0]),
|
||||
# 'swin_v1_b': os.path.join(self.weights_root_dir, ['swin_base_patch4_window12_384_22kto1k.pth', 'swin_base_patch4_window12_384_22k.pth'][0]),
|
||||
# 'swin_v1_l': os.path.join(self.weights_root_dir, ['swin_large_patch4_window12_384_22kto1k.pth', 'swin_large_patch4_window12_384_22k.pth'][0]),
|
||||
# 'swin_v1_t': os.path.join(self.weights_root_dir, ['swin_tiny_patch4_window7_224_22kto1k_finetune.pth'][0]),
|
||||
# 'swin_v1_s': os.path.join(self.weights_root_dir, ['swin_small_patch4_window7_224_22kto1k_finetune.pth'][0]),
|
||||
# 'pvt_v2_b0': os.path.join(self.weights_root_dir, ['pvt_v2_b0.pth'][0]),
|
||||
# 'pvt_v2_b1': os.path.join(self.weights_root_dir, ['pvt_v2_b1.pth'][0]),
|
||||
# }
|
||||
weight_paths_name = "birefnet"
|
||||
self.weights = {
|
||||
'pvt_v2_b2': folder_paths.get_full_path(weight_paths_name, 'pvt_v2_b2.pth'),
|
||||
'pvt_v2_b5': folder_paths.get_full_path(weight_paths_name, ['pvt_v2_b5.pth', 'pvt_v2_b5_22k.pth'][0]),
|
||||
'swin_v1_b': folder_paths.get_full_path(weight_paths_name, ['swin_base_patch4_window12_384_22kto1k.pth', 'swin_base_patch4_window12_384_22k.pth'][0]),
|
||||
'swin_v1_l': folder_paths.get_full_path(weight_paths_name, ['swin_large_patch4_window12_384_22kto1k.pth', 'swin_large_patch4_window12_384_22k.pth'][0]),
|
||||
'swin_v1_t': folder_paths.get_full_path(weight_paths_name, ['swin_tiny_patch4_window7_224_22kto1k_finetune.pth'][0]),
|
||||
'swin_v1_s': folder_paths.get_full_path(weight_paths_name, ['swin_small_patch4_window7_224_22kto1k_finetune.pth'][0]),
|
||||
'pvt_v2_b0': folder_paths.get_full_path(weight_paths_name, ['pvt_v2_b0.pth'][0]),
|
||||
'pvt_v2_b1': folder_paths.get_full_path(weight_paths_name, ['pvt_v2_b1.pth'][0]),
|
||||
}
|
||||
|
||||
# Callbacks - inactive
|
||||
self.verbose_eval = True
|
||||
self.only_S_MAE = False
|
||||
self.SDPA_enabled = False # Bugs. Slower and errors occur in multi-GPUs
|
||||
|
||||
# others
|
||||
self.device = [0, 'cpu'][0] # .to(0) == .to('cuda:0')
|
||||
|
||||
self.batch_size_valid = 1
|
||||
self.rand_seed = 7
|
||||
# run_sh_file = [f for f in os.listdir('.') if 'train.sh' == f] + [os.path.join('..', f) for f in os.listdir('..') if 'train.sh' == f]
|
||||
# if run_sh_file:
|
||||
# with open(run_sh_file[0], 'r') as f:
|
||||
# lines = f.readlines()
|
||||
# self.save_last = int([l.strip() for l in lines if '"{}")'.format(self.task) in l and 'val_last=' in l][0].split('val_last=')[-1].split()[0])
|
||||
# self.save_step = int([l.strip() for l in lines if '"{}")'.format(self.task) in l and 'step=' in l][0].split('step=')[-1].split()[0])
|
||||
|
||||
|
||||
+173
@@ -0,0 +1,173 @@
|
||||
import os
|
||||
import random
|
||||
import numpy as np
|
||||
import cv2
|
||||
from tqdm import tqdm
|
||||
from PIL import Image
|
||||
from torch.utils import data
|
||||
from torchvision import transforms
|
||||
|
||||
from .image_proc import preproc
|
||||
from .config import Config
|
||||
from .utils import path_to_image
|
||||
|
||||
|
||||
Image.MAX_IMAGE_PIXELS = None # remove DecompressionBombWarning
|
||||
config = Config()
|
||||
_class_labels_TR_sorted = (
|
||||
'Airplane, Ant, Antenna, Archery, Axe, BabyCarriage, Bag, BalanceBeam, Balcony, Balloon, Basket, BasketballHoop, Beatle, Bed, Bee, Bench, Bicycle, '
|
||||
'BicycleFrame, BicycleStand, Boat, Bonsai, BoomLift, Bridge, BunkBed, Butterfly, Button, Cable, CableLift, Cage, Camcorder, Cannon, Canoe, Car, '
|
||||
'CarParkDropArm, Carriage, Cart, Caterpillar, CeilingLamp, Centipede, Chair, Clip, Clock, Clothes, CoatHanger, Comb, ConcretePumpTruck, Crack, Crane, '
|
||||
'Cup, DentalChair, Desk, DeskChair, Diagram, DishRack, DoorHandle, Dragonfish, Dragonfly, Drum, Earphone, Easel, ElectricIron, Excavator, Eyeglasses, '
|
||||
'Fan, Fence, Fencing, FerrisWheel, FireExtinguisher, Fishing, Flag, FloorLamp, Forklift, GasStation, Gate, Gear, Goal, Golf, GymEquipment, Hammock, '
|
||||
'Handcart, Handcraft, Handrail, HangGlider, Harp, Harvester, Headset, Helicopter, Helmet, Hook, HorizontalBar, Hydrovalve, IroningTable, Jewelry, Key, '
|
||||
'KidsPlayground, Kitchenware, Kite, Knife, Ladder, LaundryRack, Lightning, Lobster, Locust, Machine, MachineGun, MagazineRack, Mantis, Medal, MemorialArchway, '
|
||||
'Microphone, Missile, MobileHolder, Monitor, Mosquito, Motorcycle, MovingTrolley, Mower, MusicPlayer, MusicStand, ObservationTower, Octopus, OilWell, '
|
||||
'OlympicLogo, OperatingTable, OutdoorFitnessEquipment, Parachute, Pavilion, Piano, Pipe, PlowHarrow, PoleVault, Punchbag, Rack, Racket, Rifle, Ring, Robot, '
|
||||
'RockClimbing, Rope, Sailboat, Satellite, Scaffold, Scale, Scissor, Scooter, Sculpture, Seadragon, Seahorse, Seal, SewingMachine, Ship, Shoe, ShoppingCart, '
|
||||
'ShoppingTrolley, Shower, Shrimp, Signboard, Skateboarding, Skeleton, Skiing, Spade, SpeedBoat, Spider, Spoon, Stair, Stand, Stationary, SteeringWheel, '
|
||||
'Stethoscope, Stool, Stove, StreetLamp, SweetStand, Swing, Sword, TV, Table, TableChair, TableLamp, TableTennis, Tank, Tapeline, Teapot, Telescope, Tent, '
|
||||
'TobaccoPipe, Toy, Tractor, TrafficLight, TrafficSign, Trampoline, TransmissionTower, Tree, Tricycle, TrimmerCover, Tripod, Trombone, Truck, Trumpet, Tuba, '
|
||||
'UAV, Umbrella, UnevenBars, UtilityPole, VacuumCleaner, Violin, Wakesurfing, Watch, WaterTower, WateringPot, Well, WellLid, Wheel, Wheelchair, WindTurbine, Windmill, WineGlass, WireWhisk, Yacht'
|
||||
)
|
||||
class_labels_TR_sorted = _class_labels_TR_sorted.split(', ')
|
||||
|
||||
|
||||
class MyData(data.Dataset):
|
||||
def __init__(self, datasets, data_size, is_train=True):
|
||||
# data_size is None when using dynamic_size or data_size is manually set to None (for inference in the original size).
|
||||
self.is_train = is_train
|
||||
self.data_size = data_size
|
||||
self.load_all = config.load_all
|
||||
self.device = config.device
|
||||
valid_extensions = ['.png', '.jpg', '.PNG', '.JPG', '.JPEG']
|
||||
|
||||
if self.is_train and config.auxiliary_classification:
|
||||
self.cls_name2id = {_name: _id for _id, _name in enumerate(class_labels_TR_sorted)}
|
||||
self.transform_image = transforms.Compose([
|
||||
transforms.ToTensor(),
|
||||
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
|
||||
])
|
||||
self.transform_label = transforms.Compose([
|
||||
transforms.ToTensor(),
|
||||
])
|
||||
dataset_root = os.path.join(config.data_root_dir, config.task)
|
||||
# datasets can be a list of different datasets for training on combined sets.
|
||||
self.image_paths = []
|
||||
for dataset in datasets.split('+'):
|
||||
image_root = os.path.join(dataset_root, dataset, 'im')
|
||||
self.image_paths += [os.path.join(image_root, p) for p in os.listdir(image_root) if any(p.endswith(ext) for ext in valid_extensions)]
|
||||
self.label_paths = []
|
||||
for p in self.image_paths:
|
||||
for ext in valid_extensions:
|
||||
## 'im' and 'gt' may need modifying
|
||||
p_gt = p.replace('/im/', '/gt/')[:-(len(p.split('.')[-1])+1)] + ext
|
||||
file_exists = False
|
||||
if os.path.exists(p_gt):
|
||||
self.label_paths.append(p_gt)
|
||||
file_exists = True
|
||||
break
|
||||
if not file_exists:
|
||||
print('Not exists:', p_gt)
|
||||
|
||||
if len(self.label_paths) != len(self.image_paths):
|
||||
set_image_paths = set([os.path.splitext(p.split(os.sep)[-1])[0] for p in self.image_paths])
|
||||
set_label_paths = set([os.path.splitext(p.split(os.sep)[-1])[0] for p in self.label_paths])
|
||||
print('Path diff:', set_image_paths - set_label_paths)
|
||||
raise ValueError(f"There are different numbers of images ({len(self.label_paths)}) and labels ({len(self.image_paths)})")
|
||||
|
||||
if self.load_all:
|
||||
self.images_loaded, self.labels_loaded = [], []
|
||||
self.class_labels_loaded = []
|
||||
# for image_path, label_path in zip(self.image_paths, self.label_paths):
|
||||
for image_path, label_path in tqdm(zip(self.image_paths, self.label_paths), total=len(self.image_paths)):
|
||||
_image = path_to_image(image_path, size=self.data_size, color_type='rgb')
|
||||
_label = path_to_image(label_path, size=self.data_size, color_type='gray')
|
||||
self.images_loaded.append(_image)
|
||||
self.labels_loaded.append(_label)
|
||||
self.class_labels_loaded.append(
|
||||
self.cls_name2id[label_path.split('/')[-1].split('#')[3]] if self.is_train and config.auxiliary_classification else -1
|
||||
)
|
||||
|
||||
def __getitem__(self, index):
|
||||
if self.load_all:
|
||||
image = self.images_loaded[index]
|
||||
label = self.labels_loaded[index]
|
||||
class_label = self.class_labels_loaded[index] if self.is_train and config.auxiliary_classification else -1
|
||||
else:
|
||||
image = path_to_image(self.image_paths[index], size=self.data_size, color_type='rgb')
|
||||
label = path_to_image(self.label_paths[index], size=self.data_size, color_type='gray')
|
||||
class_label = self.cls_name2id[self.label_paths[index].split('/')[-1].split('#')[3]] if self.is_train and config.auxiliary_classification else -1
|
||||
|
||||
# loading image and label
|
||||
if self.is_train:
|
||||
if config.background_color_synthesis:
|
||||
image.putalpha(label)
|
||||
array_image = np.array(image)
|
||||
array_foreground = array_image[:, :, :3].astype(np.float32)
|
||||
array_mask = (array_image[:, :, 3:] / 255).astype(np.float32)
|
||||
array_background = np.zeros_like(array_foreground)
|
||||
choice = random.random()
|
||||
if choice < 0.4:
|
||||
# Black/Gray/White backgrounds
|
||||
array_background[:, :, :] = random.randint(0, 255)
|
||||
elif choice < 0.8:
|
||||
# Background color that similar to the foreground object. Hard negative samples.
|
||||
foreground_pixel_number = np.sum(array_mask > 0)
|
||||
color_foreground_mean = np.mean(array_foreground * array_mask, axis=(0, 1)) * (np.prod(array_foreground.shape[:2]) / foreground_pixel_number)
|
||||
color_up_or_down = random.choice((-1, 1))
|
||||
# Up or down for 20% range from 255 or 0, respectively.
|
||||
color_foreground_mean += (255 - color_foreground_mean if color_up_or_down == 1 else color_foreground_mean) * (random.random() * 0.2) * color_up_or_down
|
||||
array_background[:, :, :] = color_foreground_mean
|
||||
else:
|
||||
# Any color
|
||||
for idx_channel in range(3):
|
||||
array_background[:, :, idx_channel] = random.randint(0, 255)
|
||||
array_foreground_background = array_foreground * array_mask + array_background * (1 - array_mask)
|
||||
image = Image.fromarray(array_foreground_background.astype(np.uint8))
|
||||
image, label = preproc(image, label, preproc_methods=config.preproc_methods)
|
||||
# else:
|
||||
# if _label.shape[0] > 2048 or _label.shape[1] > 2048:
|
||||
# _image = cv2.resize(_image, (2048, 2048), interpolation=cv2.INTER_LINEAR)
|
||||
# _label = cv2.resize(_label, (2048, 2048), interpolation=cv2.INTER_LINEAR)
|
||||
|
||||
# At present, we use fixed sizes in inference, instead of consistent dynamic size with training.
|
||||
if self.is_train:
|
||||
if config.dynamic_size is None:
|
||||
image, label = self.transform_image(image), self.transform_label(label)
|
||||
else:
|
||||
size_div_32 = (int(image.size[0] // 32 * 32), int(image.size[1] // 32 * 32))
|
||||
if image.size != size_div_32:
|
||||
image = image.resize(size_div_32)
|
||||
label = label.resize(size_div_32)
|
||||
image, label = self.transform_image(image), self.transform_label(label)
|
||||
|
||||
if self.is_train:
|
||||
return image, label, class_label
|
||||
else:
|
||||
return image, label, self.label_paths[index]
|
||||
|
||||
def __len__(self):
|
||||
return len(self.image_paths)
|
||||
|
||||
|
||||
def custom_collate_fn(batch):
|
||||
if config.dynamic_size:
|
||||
dynamic_size = tuple(sorted(config.dynamic_size))
|
||||
dynamic_size_batch = (random.randint(dynamic_size[0][0], dynamic_size[0][1]) // 32 * 32, random.randint(dynamic_size[1][0], dynamic_size[1][1]) // 32 * 32) # select a value randomly in the range of [dynamic_size[0/1][0], dynamic_size[0/1][1]].
|
||||
data_size = dynamic_size_batch
|
||||
else:
|
||||
data_size = config.size
|
||||
new_batch = []
|
||||
transform_image = transforms.Compose([
|
||||
transforms.Resize(data_size[::-1]),
|
||||
transforms.ToTensor(),
|
||||
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
|
||||
])
|
||||
transform_label = transforms.Compose([
|
||||
transforms.Resize(data_size[::-1]),
|
||||
transforms.ToTensor(),
|
||||
])
|
||||
for image, label, class_label in batch:
|
||||
new_batch.append((transform_image(image), transform_label(label), class_label))
|
||||
return data._utils.collate.default_collate(new_batch)
|
||||
+116
@@ -0,0 +1,116 @@
|
||||
import random
|
||||
from PIL import Image, ImageEnhance
|
||||
import numpy as np
|
||||
import cv2
|
||||
|
||||
|
||||
def refine_foreground(image, mask, r=90):
|
||||
if mask.size != image.size:
|
||||
mask = mask.resize(image.size)
|
||||
image = np.array(image) / 255.0
|
||||
mask = np.array(mask) / 255.0
|
||||
estimated_foreground = FB_blur_fusion_foreground_estimator_2(image, mask, r=r)
|
||||
image_masked = Image.fromarray((estimated_foreground * 255.0).astype(np.uint8))
|
||||
return image_masked
|
||||
|
||||
|
||||
def FB_blur_fusion_foreground_estimator_2(image, alpha, r=90):
|
||||
# Thanks to the source: https://github.com/Photoroom/fast-foreground-estimation
|
||||
alpha = alpha[:, :, None]
|
||||
F, blur_B = FB_blur_fusion_foreground_estimator(
|
||||
image, image, image, alpha, r)
|
||||
return FB_blur_fusion_foreground_estimator(image, F, blur_B, alpha, r=6)[0]
|
||||
|
||||
|
||||
def FB_blur_fusion_foreground_estimator(image, F, B, alpha, r=90):
|
||||
if isinstance(image, Image.Image):
|
||||
image = np.array(image) / 255.0
|
||||
blurred_alpha = cv2.blur(alpha, (r, r))[:, :, None]
|
||||
|
||||
blurred_FA = cv2.blur(F * alpha, (r, r))
|
||||
blurred_F = blurred_FA / (blurred_alpha + 1e-5)
|
||||
|
||||
blurred_B1A = cv2.blur(B * (1 - alpha), (r, r))
|
||||
blurred_B = blurred_B1A / ((1 - blurred_alpha) + 1e-5)
|
||||
F = blurred_F + alpha * \
|
||||
(image - alpha * blurred_F - (1 - alpha) * blurred_B)
|
||||
F = np.clip(F, 0, 1)
|
||||
return F, blurred_B
|
||||
|
||||
|
||||
def preproc(image, label, preproc_methods=['flip']):
|
||||
if 'flip' in preproc_methods:
|
||||
image, label = cv_random_flip(image, label)
|
||||
if 'crop' in preproc_methods:
|
||||
image, label = random_crop(image, label)
|
||||
if 'rotate' in preproc_methods:
|
||||
image, label = random_rotate(image, label)
|
||||
if 'enhance' in preproc_methods:
|
||||
image = color_enhance(image)
|
||||
if 'pepper' in preproc_methods:
|
||||
image = random_pepper(image)
|
||||
return image, label
|
||||
|
||||
|
||||
def cv_random_flip(img, label):
|
||||
if random.random() > 0.5:
|
||||
img = img.transpose(Image.FLIP_LEFT_RIGHT)
|
||||
label = label.transpose(Image.FLIP_LEFT_RIGHT)
|
||||
return img, label
|
||||
|
||||
|
||||
def random_crop(image, label):
|
||||
border = 30
|
||||
image_width = image.size[0]
|
||||
image_height = image.size[1]
|
||||
border = int(min(image_width, image_height) * 0.1)
|
||||
crop_win_width = np.random.randint(image_width - border, image_width)
|
||||
crop_win_height = np.random.randint(image_height - border, image_height)
|
||||
random_region = (
|
||||
(image_width - crop_win_width) >> 1, (image_height - crop_win_height) >> 1, (image_width + crop_win_width) >> 1,
|
||||
(image_height + crop_win_height) >> 1)
|
||||
return image.crop(random_region), label.crop(random_region)
|
||||
|
||||
|
||||
def random_rotate(image, label, angle=15):
|
||||
mode = Image.BICUBIC
|
||||
if random.random() > 0.8:
|
||||
random_angle = np.random.randint(-angle, angle)
|
||||
image = image.rotate(random_angle, mode)
|
||||
label = label.rotate(random_angle, mode)
|
||||
return image, label
|
||||
|
||||
|
||||
def color_enhance(image):
|
||||
bright_intensity = random.randint(5, 15) / 10.0
|
||||
image = ImageEnhance.Brightness(image).enhance(bright_intensity)
|
||||
contrast_intensity = random.randint(5, 15) / 10.0
|
||||
image = ImageEnhance.Contrast(image).enhance(contrast_intensity)
|
||||
color_intensity = random.randint(0, 20) / 10.0
|
||||
image = ImageEnhance.Color(image).enhance(color_intensity)
|
||||
sharp_intensity = random.randint(0, 30) / 10.0
|
||||
image = ImageEnhance.Sharpness(image).enhance(sharp_intensity)
|
||||
return image
|
||||
|
||||
|
||||
def random_gaussian(image, mean=0.1, sigma=0.35):
|
||||
def gaussianNoisy(im, mean=mean, sigma=sigma):
|
||||
for _i in range(len(im)):
|
||||
im[_i] += random.gauss(mean, sigma)
|
||||
return im
|
||||
|
||||
img = np.asarray(image)
|
||||
width, height = img.shape
|
||||
img = gaussianNoisy(img[:].flatten(), mean, sigma)
|
||||
img = img.reshape([width, height])
|
||||
return Image.fromarray(np.uint8(img))
|
||||
|
||||
|
||||
def random_pepper(img, N=0.0015):
|
||||
img = np.array(img)
|
||||
noiseNum = int(N * img.shape[0] * img.shape[1])
|
||||
for i in range(noiseNum):
|
||||
randX = random.randint(0, img.shape[0] - 1)
|
||||
randY = random.randint(0, img.shape[1] - 1)
|
||||
img[randX, randY] = random.randint(0, 1) * 255
|
||||
return Image.fromarray(img)
|
||||
@@ -0,0 +1,44 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from collections import OrderedDict
|
||||
from torchvision.models import vgg16, vgg16_bn, VGG16_Weights, VGG16_BN_Weights, resnet50, ResNet50_Weights
|
||||
from ..backbones.pvt_v2 import pvt_v2_b0, pvt_v2_b1, pvt_v2_b2, pvt_v2_b5
|
||||
from ..backbones.swin_v1 import swin_v1_t, swin_v1_s, swin_v1_b, swin_v1_l
|
||||
from ...config import Config
|
||||
|
||||
|
||||
config = Config()
|
||||
|
||||
def build_backbone(bb_name, pretrained=True, params_settings=''):
|
||||
if bb_name == 'vgg16':
|
||||
bb_net = list(vgg16(pretrained=VGG16_Weights.DEFAULT if pretrained else None).children())[0]
|
||||
bb = nn.Sequential(OrderedDict({'conv1': bb_net[:4], 'conv2': bb_net[4:9], 'conv3': bb_net[9:16], 'conv4': bb_net[16:23]}))
|
||||
elif bb_name == 'vgg16bn':
|
||||
bb_net = list(vgg16_bn(pretrained=VGG16_BN_Weights.DEFAULT if pretrained else None).children())[0]
|
||||
bb = nn.Sequential(OrderedDict({'conv1': bb_net[:6], 'conv2': bb_net[6:13], 'conv3': bb_net[13:23], 'conv4': bb_net[23:33]}))
|
||||
elif bb_name == 'resnet50':
|
||||
bb_net = list(resnet50(pretrained=ResNet50_Weights.DEFAULT if pretrained else None).children())
|
||||
bb = nn.Sequential(OrderedDict({'conv1': nn.Sequential(*bb_net[0:3]), 'conv2': bb_net[4], 'conv3': bb_net[5], 'conv4': bb_net[6]}))
|
||||
else:
|
||||
bb = eval('{}({})'.format(bb_name, params_settings))
|
||||
if pretrained:
|
||||
bb = load_weights(bb, bb_name)
|
||||
return bb
|
||||
|
||||
def load_weights(model, model_name):
|
||||
save_model = torch.load(config.weights[model_name], map_location='cpu', weights_only=True)
|
||||
model_dict = model.state_dict()
|
||||
state_dict = {k: v if v.size() == model_dict[k].size() else model_dict[k] for k, v in save_model.items() if k in model_dict.keys()}
|
||||
# to ignore the weights with mismatched size when I modify the backbone itself.
|
||||
if not state_dict:
|
||||
save_model_keys = list(save_model.keys())
|
||||
sub_item = save_model_keys[0] if len(save_model_keys) == 1 else None
|
||||
state_dict = {k: v if v.size() == model_dict[k].size() else model_dict[k] for k, v in save_model[sub_item].items() if k in model_dict.keys()}
|
||||
if not state_dict or not sub_item:
|
||||
print('Weights are not successfully loaded. Check the state dict of weights file.')
|
||||
return None
|
||||
else:
|
||||
print('Found correct weights in the "{}" item of loaded state_dict.'.format(sub_item))
|
||||
model_dict.update(state_dict)
|
||||
model.load_state_dict(model_dict)
|
||||
return model
|
||||
@@ -0,0 +1,433 @@
|
||||
import math
|
||||
from functools import partial
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
|
||||
try:
|
||||
# version > 0.6.13
|
||||
from timm.layers import DropPath, to_2tuple, trunc_normal_
|
||||
except Exception:
|
||||
from timm.models.layers import DropPath, to_2tuple, trunc_normal_
|
||||
|
||||
from ...config import Config
|
||||
|
||||
config = Config()
|
||||
|
||||
class Mlp(nn.Module):
|
||||
def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
|
||||
super().__init__()
|
||||
out_features = out_features or in_features
|
||||
hidden_features = hidden_features or in_features
|
||||
self.fc1 = nn.Linear(in_features, hidden_features)
|
||||
self.dwconv = DWConv(hidden_features)
|
||||
self.act = act_layer()
|
||||
self.fc2 = nn.Linear(hidden_features, out_features)
|
||||
self.drop = nn.Dropout(drop)
|
||||
|
||||
self.apply(self._init_weights)
|
||||
|
||||
def _init_weights(self, m):
|
||||
if isinstance(m, nn.Linear):
|
||||
trunc_normal_(m.weight, std=.02)
|
||||
if isinstance(m, nn.Linear) and m.bias is not None:
|
||||
nn.init.constant_(m.bias, 0)
|
||||
elif isinstance(m, nn.LayerNorm):
|
||||
nn.init.constant_(m.bias, 0)
|
||||
nn.init.constant_(m.weight, 1.0)
|
||||
elif isinstance(m, nn.Conv2d):
|
||||
fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
|
||||
fan_out //= m.groups
|
||||
m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
|
||||
if m.bias is not None:
|
||||
m.bias.data.zero_()
|
||||
|
||||
def forward(self, x, H, W):
|
||||
x = self.fc1(x)
|
||||
x = self.dwconv(x, H, W)
|
||||
x = self.act(x)
|
||||
x = self.drop(x)
|
||||
x = self.fc2(x)
|
||||
x = self.drop(x)
|
||||
return x
|
||||
|
||||
|
||||
class Attention(nn.Module):
|
||||
def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0., sr_ratio=1):
|
||||
super().__init__()
|
||||
assert dim % num_heads == 0, f"dim {dim} should be divided by num_heads {num_heads}."
|
||||
|
||||
self.dim = dim
|
||||
self.num_heads = num_heads
|
||||
head_dim = dim // num_heads
|
||||
self.scale = qk_scale or head_dim ** -0.5
|
||||
|
||||
self.q = nn.Linear(dim, dim, bias=qkv_bias)
|
||||
self.kv = nn.Linear(dim, dim * 2, bias=qkv_bias)
|
||||
self.attn_drop_prob = attn_drop
|
||||
self.attn_drop = nn.Dropout(attn_drop)
|
||||
self.proj = nn.Linear(dim, dim)
|
||||
self.proj_drop = nn.Dropout(proj_drop)
|
||||
|
||||
self.sr_ratio = sr_ratio
|
||||
if sr_ratio > 1:
|
||||
self.sr = nn.Conv2d(dim, dim, kernel_size=sr_ratio, stride=sr_ratio)
|
||||
self.norm = nn.LayerNorm(dim)
|
||||
|
||||
self.apply(self._init_weights)
|
||||
|
||||
def _init_weights(self, m):
|
||||
if isinstance(m, nn.Linear):
|
||||
trunc_normal_(m.weight, std=.02)
|
||||
if isinstance(m, nn.Linear) and m.bias is not None:
|
||||
nn.init.constant_(m.bias, 0)
|
||||
elif isinstance(m, nn.LayerNorm):
|
||||
nn.init.constant_(m.bias, 0)
|
||||
nn.init.constant_(m.weight, 1.0)
|
||||
elif isinstance(m, nn.Conv2d):
|
||||
fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
|
||||
fan_out //= m.groups
|
||||
m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
|
||||
if m.bias is not None:
|
||||
m.bias.data.zero_()
|
||||
|
||||
def forward(self, x, H, W):
|
||||
B, N, C = x.shape
|
||||
q = self.q(x).reshape(B, N, self.num_heads, C // self.num_heads).permute(0, 2, 1, 3)
|
||||
|
||||
if self.sr_ratio > 1:
|
||||
x_ = x.permute(0, 2, 1).reshape(B, C, H, W)
|
||||
x_ = self.sr(x_).reshape(B, C, -1).permute(0, 2, 1)
|
||||
x_ = self.norm(x_)
|
||||
kv = self.kv(x_).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
|
||||
else:
|
||||
kv = self.kv(x).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
|
||||
k, v = kv[0], kv[1]
|
||||
|
||||
if config.SDPA_enabled:
|
||||
x = torch.nn.functional.scaled_dot_product_attention(
|
||||
q, k, v,
|
||||
attn_mask=None, dropout_p=self.attn_drop_prob, is_causal=False
|
||||
).transpose(1, 2).reshape(B, N, C)
|
||||
else:
|
||||
attn = (q @ k.transpose(-2, -1)) * self.scale
|
||||
attn = attn.softmax(dim=-1)
|
||||
attn = self.attn_drop(attn)
|
||||
|
||||
x = (attn @ v).transpose(1, 2).reshape(B, N, C)
|
||||
x = self.proj(x)
|
||||
x = self.proj_drop(x)
|
||||
|
||||
return x
|
||||
|
||||
|
||||
class Block(nn.Module):
|
||||
|
||||
def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0.,
|
||||
drop_path=0., act_layer=nn.GELU, norm_layer=nn.LayerNorm, sr_ratio=1):
|
||||
super().__init__()
|
||||
self.norm1 = norm_layer(dim)
|
||||
self.attn = Attention(
|
||||
dim,
|
||||
num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale,
|
||||
attn_drop=attn_drop, proj_drop=drop, sr_ratio=sr_ratio)
|
||||
# NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
|
||||
self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
|
||||
self.norm2 = norm_layer(dim)
|
||||
mlp_hidden_dim = int(dim * mlp_ratio)
|
||||
self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
|
||||
|
||||
self.apply(self._init_weights)
|
||||
|
||||
def _init_weights(self, m):
|
||||
if isinstance(m, nn.Linear):
|
||||
trunc_normal_(m.weight, std=.02)
|
||||
if isinstance(m, nn.Linear) and m.bias is not None:
|
||||
nn.init.constant_(m.bias, 0)
|
||||
elif isinstance(m, nn.LayerNorm):
|
||||
nn.init.constant_(m.bias, 0)
|
||||
nn.init.constant_(m.weight, 1.0)
|
||||
elif isinstance(m, nn.Conv2d):
|
||||
fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
|
||||
fan_out //= m.groups
|
||||
m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
|
||||
if m.bias is not None:
|
||||
m.bias.data.zero_()
|
||||
|
||||
def forward(self, x, H, W):
|
||||
x = x + self.drop_path(self.attn(self.norm1(x), H, W))
|
||||
x = x + self.drop_path(self.mlp(self.norm2(x), H, W))
|
||||
|
||||
return x
|
||||
|
||||
|
||||
class OverlapPatchEmbed(nn.Module):
|
||||
""" Image to Patch Embedding
|
||||
"""
|
||||
|
||||
def __init__(self, img_size=224, patch_size=7, stride=4, in_channels=3, embed_dim=768):
|
||||
super().__init__()
|
||||
img_size = to_2tuple(img_size)
|
||||
patch_size = to_2tuple(patch_size)
|
||||
|
||||
self.img_size = img_size
|
||||
self.patch_size = patch_size
|
||||
self.H, self.W = img_size[0] // patch_size[0], img_size[1] // patch_size[1]
|
||||
self.num_patches = self.H * self.W
|
||||
self.proj = nn.Conv2d(in_channels, embed_dim, kernel_size=patch_size, stride=stride,
|
||||
padding=(patch_size[0] // 2, patch_size[1] // 2))
|
||||
self.norm = nn.LayerNorm(embed_dim)
|
||||
|
||||
self.apply(self._init_weights)
|
||||
|
||||
def _init_weights(self, m):
|
||||
if isinstance(m, nn.Linear):
|
||||
trunc_normal_(m.weight, std=.02)
|
||||
if isinstance(m, nn.Linear) and m.bias is not None:
|
||||
nn.init.constant_(m.bias, 0)
|
||||
elif isinstance(m, nn.LayerNorm):
|
||||
nn.init.constant_(m.bias, 0)
|
||||
nn.init.constant_(m.weight, 1.0)
|
||||
elif isinstance(m, nn.Conv2d):
|
||||
fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
|
||||
fan_out //= m.groups
|
||||
m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
|
||||
if m.bias is not None:
|
||||
m.bias.data.zero_()
|
||||
|
||||
def forward(self, x):
|
||||
x = self.proj(x)
|
||||
_, _, H, W = x.shape
|
||||
x = x.flatten(2).transpose(1, 2)
|
||||
x = self.norm(x)
|
||||
|
||||
return x, H, W
|
||||
|
||||
|
||||
class PyramidVisionTransformerImpr(nn.Module):
|
||||
def __init__(self, img_size=224, patch_size=16, in_channels=3, num_classes=1000, embed_dims=[64, 128, 256, 512],
|
||||
num_heads=[1, 2, 4, 8], mlp_ratios=[4, 4, 4, 4], qkv_bias=False, qk_scale=None, drop_rate=0.,
|
||||
attn_drop_rate=0., drop_path_rate=0., norm_layer=nn.LayerNorm,
|
||||
depths=[3, 4, 6, 3], sr_ratios=[8, 4, 2, 1]):
|
||||
super().__init__()
|
||||
self.num_classes = num_classes
|
||||
self.depths = depths
|
||||
|
||||
# patch_embed
|
||||
self.patch_embed1 = OverlapPatchEmbed(img_size=img_size, patch_size=7, stride=4, in_channels=in_channels,
|
||||
embed_dim=embed_dims[0])
|
||||
self.patch_embed2 = OverlapPatchEmbed(img_size=img_size // 4, patch_size=3, stride=2, in_channels=embed_dims[0],
|
||||
embed_dim=embed_dims[1])
|
||||
self.patch_embed3 = OverlapPatchEmbed(img_size=img_size // 8, patch_size=3, stride=2, in_channels=embed_dims[1],
|
||||
embed_dim=embed_dims[2])
|
||||
self.patch_embed4 = OverlapPatchEmbed(img_size=img_size // 16, patch_size=3, stride=2, in_channels=embed_dims[2],
|
||||
embed_dim=embed_dims[3])
|
||||
|
||||
# transformer encoder
|
||||
dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))] # stochastic depth decay rule
|
||||
cur = 0
|
||||
self.block1 = nn.ModuleList([Block(
|
||||
dim=embed_dims[0], num_heads=num_heads[0], mlp_ratio=mlp_ratios[0], qkv_bias=qkv_bias, qk_scale=qk_scale,
|
||||
drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,
|
||||
sr_ratio=sr_ratios[0])
|
||||
for i in range(depths[0])])
|
||||
self.norm1 = norm_layer(embed_dims[0])
|
||||
|
||||
cur += depths[0]
|
||||
self.block2 = nn.ModuleList([Block(
|
||||
dim=embed_dims[1], num_heads=num_heads[1], mlp_ratio=mlp_ratios[1], qkv_bias=qkv_bias, qk_scale=qk_scale,
|
||||
drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,
|
||||
sr_ratio=sr_ratios[1])
|
||||
for i in range(depths[1])])
|
||||
self.norm2 = norm_layer(embed_dims[1])
|
||||
|
||||
cur += depths[1]
|
||||
self.block3 = nn.ModuleList([Block(
|
||||
dim=embed_dims[2], num_heads=num_heads[2], mlp_ratio=mlp_ratios[2], qkv_bias=qkv_bias, qk_scale=qk_scale,
|
||||
drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,
|
||||
sr_ratio=sr_ratios[2])
|
||||
for i in range(depths[2])])
|
||||
self.norm3 = norm_layer(embed_dims[2])
|
||||
|
||||
cur += depths[2]
|
||||
self.block4 = nn.ModuleList([Block(
|
||||
dim=embed_dims[3], num_heads=num_heads[3], mlp_ratio=mlp_ratios[3], qkv_bias=qkv_bias, qk_scale=qk_scale,
|
||||
drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,
|
||||
sr_ratio=sr_ratios[3])
|
||||
for i in range(depths[3])])
|
||||
self.norm4 = norm_layer(embed_dims[3])
|
||||
|
||||
# classification head
|
||||
# self.head = nn.Linear(embed_dims[3], num_classes) if num_classes > 0 else nn.Identity()
|
||||
|
||||
self.apply(self._init_weights)
|
||||
|
||||
def _init_weights(self, m):
|
||||
if isinstance(m, nn.Linear):
|
||||
trunc_normal_(m.weight, std=.02)
|
||||
if isinstance(m, nn.Linear) and m.bias is not None:
|
||||
nn.init.constant_(m.bias, 0)
|
||||
elif isinstance(m, nn.LayerNorm):
|
||||
nn.init.constant_(m.bias, 0)
|
||||
nn.init.constant_(m.weight, 1.0)
|
||||
elif isinstance(m, nn.Conv2d):
|
||||
fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
|
||||
fan_out //= m.groups
|
||||
m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
|
||||
if m.bias is not None:
|
||||
m.bias.data.zero_()
|
||||
|
||||
def init_weights(self, pretrained=None):
|
||||
if isinstance(pretrained, str):
|
||||
logger = 1
|
||||
#load_checkpoint(self, pretrained, map_location='cpu', strict=False, logger=logger)
|
||||
|
||||
def reset_drop_path(self, drop_path_rate):
|
||||
dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(self.depths))]
|
||||
cur = 0
|
||||
for i in range(self.depths[0]):
|
||||
self.block1[i].drop_path.drop_prob = dpr[cur + i]
|
||||
|
||||
cur += self.depths[0]
|
||||
for i in range(self.depths[1]):
|
||||
self.block2[i].drop_path.drop_prob = dpr[cur + i]
|
||||
|
||||
cur += self.depths[1]
|
||||
for i in range(self.depths[2]):
|
||||
self.block3[i].drop_path.drop_prob = dpr[cur + i]
|
||||
|
||||
cur += self.depths[2]
|
||||
for i in range(self.depths[3]):
|
||||
self.block4[i].drop_path.drop_prob = dpr[cur + i]
|
||||
|
||||
def freeze_patch_emb(self):
|
||||
self.patch_embed1.requires_grad = False
|
||||
|
||||
@torch.jit.ignore
|
||||
def no_weight_decay(self):
|
||||
return {'pos_embed1', 'pos_embed2', 'pos_embed3', 'pos_embed4', 'cls_token'} # has pos_embed may be better
|
||||
|
||||
def get_classifier(self):
|
||||
return self.head
|
||||
|
||||
def reset_classifier(self, num_classes, global_pool=''):
|
||||
self.num_classes = num_classes
|
||||
self.head = nn.Linear(self.embed_dim, num_classes) if num_classes > 0 else nn.Identity()
|
||||
|
||||
def forward_features(self, x):
|
||||
B = x.shape[0]
|
||||
outs = []
|
||||
|
||||
# stage 1
|
||||
x, H, W = self.patch_embed1(x)
|
||||
for i, blk in enumerate(self.block1):
|
||||
x = blk(x, H, W)
|
||||
x = self.norm1(x)
|
||||
x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
|
||||
outs.append(x)
|
||||
|
||||
# stage 2
|
||||
x, H, W = self.patch_embed2(x)
|
||||
for i, blk in enumerate(self.block2):
|
||||
x = blk(x, H, W)
|
||||
x = self.norm2(x)
|
||||
x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
|
||||
outs.append(x)
|
||||
|
||||
# stage 3
|
||||
x, H, W = self.patch_embed3(x)
|
||||
for i, blk in enumerate(self.block3):
|
||||
x = blk(x, H, W)
|
||||
x = self.norm3(x)
|
||||
x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
|
||||
outs.append(x)
|
||||
|
||||
# stage 4
|
||||
x, H, W = self.patch_embed4(x)
|
||||
for i, blk in enumerate(self.block4):
|
||||
x = blk(x, H, W)
|
||||
x = self.norm4(x)
|
||||
x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
|
||||
outs.append(x)
|
||||
|
||||
return outs
|
||||
|
||||
# return x.mean(dim=1)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.forward_features(x)
|
||||
# x = self.head(x)
|
||||
|
||||
return x
|
||||
|
||||
|
||||
class DWConv(nn.Module):
|
||||
def __init__(self, dim=768):
|
||||
super(DWConv, self).__init__()
|
||||
self.dwconv = nn.Conv2d(dim, dim, 3, 1, 1, bias=True, groups=dim)
|
||||
|
||||
def forward(self, x, H, W):
|
||||
B, N, C = x.shape
|
||||
x = x.transpose(1, 2).view(B, C, H, W).contiguous()
|
||||
x = self.dwconv(x)
|
||||
x = x.flatten(2).transpose(1, 2)
|
||||
|
||||
return x
|
||||
|
||||
|
||||
def _conv_filter(state_dict, patch_size=16):
|
||||
""" convert patch embedding weight from manual patchify + linear proj to conv"""
|
||||
out_dict = {}
|
||||
for k, v in state_dict.items():
|
||||
if 'patch_embed.proj.weight' in k:
|
||||
v = v.reshape((v.shape[0], 3, patch_size, patch_size))
|
||||
out_dict[k] = v
|
||||
|
||||
return out_dict
|
||||
|
||||
|
||||
class pvt_v2_b0(PyramidVisionTransformerImpr):
|
||||
def __init__(self, **kwargs):
|
||||
super(pvt_v2_b0, self).__init__(
|
||||
patch_size=4, embed_dims=[32, 64, 160, 256], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
|
||||
qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[2, 2, 2, 2], sr_ratios=[8, 4, 2, 1],
|
||||
drop_rate=0.0, drop_path_rate=0.1)
|
||||
|
||||
|
||||
class pvt_v2_b1(PyramidVisionTransformerImpr):
|
||||
def __init__(self, **kwargs):
|
||||
super(pvt_v2_b1, self).__init__(
|
||||
patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
|
||||
qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[2, 2, 2, 2], sr_ratios=[8, 4, 2, 1],
|
||||
drop_rate=0.0, drop_path_rate=0.1)
|
||||
|
||||
|
||||
class pvt_v2_b2(PyramidVisionTransformerImpr):
|
||||
def __init__(self, in_channels=3, **kwargs):
|
||||
super(pvt_v2_b2, self).__init__(
|
||||
patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
|
||||
qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 4, 6, 3], sr_ratios=[8, 4, 2, 1],
|
||||
drop_rate=0.0, drop_path_rate=0.1, in_channels=in_channels)
|
||||
|
||||
|
||||
class pvt_v2_b3(PyramidVisionTransformerImpr):
|
||||
def __init__(self, **kwargs):
|
||||
super(pvt_v2_b3, self).__init__(
|
||||
patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
|
||||
qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 4, 18, 3], sr_ratios=[8, 4, 2, 1],
|
||||
drop_rate=0.0, drop_path_rate=0.1)
|
||||
|
||||
|
||||
class pvt_v2_b4(PyramidVisionTransformerImpr):
|
||||
def __init__(self, **kwargs):
|
||||
super(pvt_v2_b4, self).__init__(
|
||||
patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
|
||||
qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 8, 27, 3], sr_ratios=[8, 4, 2, 1],
|
||||
drop_rate=0.0, drop_path_rate=0.1)
|
||||
|
||||
|
||||
class pvt_v2_b5(PyramidVisionTransformerImpr):
|
||||
def __init__(self, **kwargs):
|
||||
super(pvt_v2_b5, self).__init__(
|
||||
patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[4, 4, 4, 4],
|
||||
qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 6, 40, 3], sr_ratios=[8, 4, 2, 1],
|
||||
drop_rate=0.0, drop_path_rate=0.1)
|
||||
@@ -0,0 +1,632 @@
|
||||
# --------------------------------------------------------
|
||||
# Swin Transformer
|
||||
# Copyright (c) 2021 Microsoft
|
||||
# Licensed under The MIT License [see LICENSE for details]
|
||||
# Written by Ze Liu, Yutong Lin, Yixuan Wei
|
||||
# --------------------------------------------------------
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
import torch.utils.checkpoint as checkpoint
|
||||
import numpy as np
|
||||
try:
|
||||
# version > 0.6.13
|
||||
from timm.layers import DropPath, to_2tuple, trunc_normal_
|
||||
except Exception:
|
||||
from timm.models.layers import DropPath, to_2tuple, trunc_normal_
|
||||
|
||||
from ...config import Config
|
||||
|
||||
|
||||
config = Config()
|
||||
|
||||
class Mlp(nn.Module):
|
||||
""" Multilayer perceptron."""
|
||||
|
||||
def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
|
||||
super().__init__()
|
||||
out_features = out_features or in_features
|
||||
hidden_features = hidden_features or in_features
|
||||
self.fc1 = nn.Linear(in_features, hidden_features)
|
||||
self.act = act_layer()
|
||||
self.fc2 = nn.Linear(hidden_features, out_features)
|
||||
self.drop = nn.Dropout(drop)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.fc1(x)
|
||||
x = self.act(x)
|
||||
x = self.drop(x)
|
||||
x = self.fc2(x)
|
||||
x = self.drop(x)
|
||||
return x
|
||||
|
||||
|
||||
def window_partition(x, window_size):
|
||||
"""
|
||||
Args:
|
||||
x: (B, H, W, C)
|
||||
window_size (int): window size
|
||||
|
||||
Returns:
|
||||
windows: (num_windows*B, window_size, window_size, C)
|
||||
"""
|
||||
B, H, W, C = x.shape
|
||||
x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)
|
||||
windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
|
||||
return windows
|
||||
|
||||
|
||||
def window_reverse(windows, window_size, H, W):
|
||||
"""
|
||||
Args:
|
||||
windows: (num_windows*B, window_size, window_size, C)
|
||||
window_size (int): Window size
|
||||
H (int): Height of image
|
||||
W (int): Width of image
|
||||
|
||||
Returns:
|
||||
x: (B, H, W, C)
|
||||
"""
|
||||
C = int(windows.shape[-1])
|
||||
x = windows.view(-1, H // window_size, W // window_size, window_size, window_size, C)
|
||||
x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, H, W, C)
|
||||
return x
|
||||
|
||||
|
||||
class WindowAttention(nn.Module):
|
||||
""" Window based multi-head self attention (W-MSA) module with relative position bias.
|
||||
It supports both of shifted and non-shifted window.
|
||||
|
||||
Args:
|
||||
dim (int): Number of input channels.
|
||||
window_size (tuple[int]): The height and width of the window.
|
||||
num_heads (int): Number of attention heads.
|
||||
qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
|
||||
qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set
|
||||
attn_drop (float, optional): Dropout ratio of attention weight. Default: 0.0
|
||||
proj_drop (float, optional): Dropout ratio of output. Default: 0.0
|
||||
"""
|
||||
|
||||
def __init__(self, dim, window_size, num_heads, qkv_bias=True, qk_scale=None, attn_drop=0., proj_drop=0.):
|
||||
|
||||
super().__init__()
|
||||
self.dim = dim
|
||||
self.window_size = window_size # Wh, Ww
|
||||
self.num_heads = num_heads
|
||||
head_dim = dim // num_heads
|
||||
self.scale = qk_scale or head_dim ** -0.5
|
||||
|
||||
# define a parameter table of relative position bias
|
||||
self.relative_position_bias_table = nn.Parameter(
|
||||
torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1), num_heads)) # 2*Wh-1 * 2*Ww-1, nH
|
||||
|
||||
# get pair-wise relative position index for each token inside the window
|
||||
coords_h = torch.arange(self.window_size[0])
|
||||
coords_w = torch.arange(self.window_size[1])
|
||||
coords = torch.stack(torch.meshgrid([coords_h, coords_w], indexing='ij')) # 2, Wh, Ww
|
||||
coords_flatten = torch.flatten(coords, 1) # 2, Wh*Ww
|
||||
relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :] # 2, Wh*Ww, Wh*Ww
|
||||
relative_coords = relative_coords.permute(1, 2, 0).contiguous() # Wh*Ww, Wh*Ww, 2
|
||||
relative_coords[:, :, 0] += self.window_size[0] - 1 # shift to start from 0
|
||||
relative_coords[:, :, 1] += self.window_size[1] - 1
|
||||
relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1
|
||||
relative_position_index = relative_coords.sum(-1) # Wh*Ww, Wh*Ww
|
||||
self.register_buffer("relative_position_index", relative_position_index)
|
||||
|
||||
self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
|
||||
self.attn_drop_prob = attn_drop
|
||||
self.attn_drop = nn.Dropout(attn_drop)
|
||||
self.proj = nn.Linear(dim, dim)
|
||||
self.proj_drop = nn.Dropout(proj_drop)
|
||||
|
||||
trunc_normal_(self.relative_position_bias_table, std=.02)
|
||||
self.softmax = nn.Softmax(dim=-1)
|
||||
|
||||
def forward(self, x, mask=None):
|
||||
""" Forward function.
|
||||
|
||||
Args:
|
||||
x: input features with shape of (num_windows*B, N, C)
|
||||
mask: (0/-inf) mask with shape of (num_windows, Wh*Ww, Wh*Ww) or None
|
||||
"""
|
||||
B_, N, C = x.shape
|
||||
qkv = self.qkv(x).reshape(B_, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
|
||||
q, k, v = qkv[0], qkv[1], qkv[2] # make torchscript happy (cannot use tensor as tuple)
|
||||
|
||||
q = q * self.scale
|
||||
|
||||
if config.SDPA_enabled:
|
||||
x = torch.nn.functional.scaled_dot_product_attention(
|
||||
q, k, v,
|
||||
attn_mask=None, dropout_p=self.attn_drop_prob, is_causal=False
|
||||
).transpose(1, 2).reshape(B_, N, C)
|
||||
else:
|
||||
attn = (q @ k.transpose(-2, -1))
|
||||
|
||||
relative_position_bias = self.relative_position_bias_table[self.relative_position_index.view(-1)].view(
|
||||
self.window_size[0] * self.window_size[1], self.window_size[0] * self.window_size[1], -1) # Wh*Ww,Wh*Ww,nH
|
||||
relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous() # nH, Wh*Ww, Wh*Ww
|
||||
attn = attn + relative_position_bias.unsqueeze(0)
|
||||
|
||||
if mask is not None:
|
||||
nW = mask.shape[0]
|
||||
attn = attn.view(B_ // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0)
|
||||
attn = attn.view(-1, self.num_heads, N, N)
|
||||
attn = self.softmax(attn)
|
||||
else:
|
||||
attn = self.softmax(attn)
|
||||
|
||||
attn = self.attn_drop(attn)
|
||||
|
||||
x = (attn @ v).transpose(1, 2).reshape(B_, N, C)
|
||||
x = self.proj(x)
|
||||
x = self.proj_drop(x)
|
||||
return x
|
||||
|
||||
|
||||
class SwinTransformerBlock(nn.Module):
|
||||
""" Swin Transformer Block.
|
||||
|
||||
Args:
|
||||
dim (int): Number of input channels.
|
||||
num_heads (int): Number of attention heads.
|
||||
window_size (int): Window size.
|
||||
shift_size (int): Shift size for SW-MSA.
|
||||
mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
|
||||
qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
|
||||
qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
|
||||
drop (float, optional): Dropout rate. Default: 0.0
|
||||
attn_drop (float, optional): Attention dropout rate. Default: 0.0
|
||||
drop_path (float, optional): Stochastic depth rate. Default: 0.0
|
||||
act_layer (nn.Module, optional): Activation layer. Default: nn.GELU
|
||||
norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm
|
||||
"""
|
||||
|
||||
def __init__(self, dim, num_heads, window_size=7, shift_size=0,
|
||||
mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0., drop_path=0.,
|
||||
act_layer=nn.GELU, norm_layer=nn.LayerNorm):
|
||||
super().__init__()
|
||||
self.dim = dim
|
||||
self.num_heads = num_heads
|
||||
self.window_size = window_size
|
||||
self.shift_size = shift_size
|
||||
self.mlp_ratio = mlp_ratio
|
||||
assert 0 <= self.shift_size < self.window_size, "shift_size must in 0-window_size"
|
||||
|
||||
self.norm1 = norm_layer(dim)
|
||||
self.attn = WindowAttention(
|
||||
dim, window_size=to_2tuple(self.window_size), num_heads=num_heads,
|
||||
qkv_bias=qkv_bias, qk_scale=qk_scale, attn_drop=attn_drop, proj_drop=drop)
|
||||
|
||||
self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
|
||||
self.norm2 = norm_layer(dim)
|
||||
mlp_hidden_dim = int(dim * mlp_ratio)
|
||||
self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
|
||||
|
||||
self.H = None
|
||||
self.W = None
|
||||
|
||||
def forward(self, x, mask_matrix):
|
||||
""" Forward function.
|
||||
|
||||
Args:
|
||||
x: Input feature, tensor size (B, H*W, C).
|
||||
H, W: Spatial resolution of the input feature.
|
||||
mask_matrix: Attention mask for cyclic shift.
|
||||
"""
|
||||
B, L, C = x.shape
|
||||
H, W = self.H, self.W
|
||||
assert L == H * W, "input feature has wrong size"
|
||||
|
||||
shortcut = x
|
||||
x = self.norm1(x)
|
||||
x = x.view(B, H, W, C)
|
||||
|
||||
# pad feature maps to multiples of window size
|
||||
pad_l = pad_t = 0
|
||||
pad_r = (self.window_size - W % self.window_size) % self.window_size
|
||||
pad_b = (self.window_size - H % self.window_size) % self.window_size
|
||||
x = F.pad(x, (0, 0, pad_l, pad_r, pad_t, pad_b))
|
||||
_, Hp, Wp, _ = x.shape
|
||||
|
||||
# cyclic shift
|
||||
if self.shift_size > 0:
|
||||
shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))
|
||||
attn_mask = mask_matrix
|
||||
else:
|
||||
shifted_x = x
|
||||
attn_mask = None
|
||||
|
||||
# partition windows
|
||||
x_windows = window_partition(shifted_x, self.window_size) # nW*B, window_size, window_size, C
|
||||
x_windows = x_windows.view(-1, self.window_size * self.window_size, C) # nW*B, window_size*window_size, C
|
||||
|
||||
# W-MSA/SW-MSA
|
||||
attn_windows = self.attn(x_windows, mask=attn_mask) # nW*B, window_size*window_size, C
|
||||
|
||||
# merge windows
|
||||
attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)
|
||||
shifted_x = window_reverse(attn_windows, self.window_size, Hp, Wp) # B H' W' C
|
||||
|
||||
# reverse cyclic shift
|
||||
if self.shift_size > 0:
|
||||
x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2))
|
||||
else:
|
||||
x = shifted_x
|
||||
|
||||
if pad_r > 0 or pad_b > 0:
|
||||
x = x[:, :H, :W, :].contiguous()
|
||||
|
||||
x = x.view(B, H * W, C)
|
||||
|
||||
# FFN
|
||||
x = shortcut + self.drop_path(x)
|
||||
x = x + self.drop_path(self.mlp(self.norm2(x)))
|
||||
|
||||
return x
|
||||
|
||||
|
||||
class PatchMerging(nn.Module):
|
||||
""" Patch Merging Layer
|
||||
|
||||
Args:
|
||||
dim (int): Number of input channels.
|
||||
norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm
|
||||
"""
|
||||
def __init__(self, dim, norm_layer=nn.LayerNorm):
|
||||
super().__init__()
|
||||
self.dim = dim
|
||||
self.reduction = nn.Linear(4 * dim, 2 * dim, bias=False)
|
||||
self.norm = norm_layer(4 * dim)
|
||||
|
||||
def forward(self, x, H, W):
|
||||
""" Forward function.
|
||||
|
||||
Args:
|
||||
x: Input feature, tensor size (B, H*W, C).
|
||||
H, W: Spatial resolution of the input feature.
|
||||
"""
|
||||
B, L, C = x.shape
|
||||
assert L == H * W, "input feature has wrong size"
|
||||
|
||||
x = x.view(B, H, W, C)
|
||||
|
||||
# padding
|
||||
pad_input = (H % 2 == 1) or (W % 2 == 1)
|
||||
if pad_input:
|
||||
x = F.pad(x, (0, 0, 0, W % 2, 0, H % 2))
|
||||
|
||||
x0 = x[:, 0::2, 0::2, :] # B H/2 W/2 C
|
||||
x1 = x[:, 1::2, 0::2, :] # B H/2 W/2 C
|
||||
x2 = x[:, 0::2, 1::2, :] # B H/2 W/2 C
|
||||
x3 = x[:, 1::2, 1::2, :] # B H/2 W/2 C
|
||||
x = torch.cat([x0, x1, x2, x3], -1) # B H/2 W/2 4*C
|
||||
x = x.view(B, -1, 4 * C) # B H/2*W/2 4*C
|
||||
|
||||
x = self.norm(x)
|
||||
x = self.reduction(x)
|
||||
|
||||
return x
|
||||
|
||||
|
||||
class BasicLayer(nn.Module):
|
||||
""" A basic Swin Transformer layer for one stage.
|
||||
|
||||
Args:
|
||||
dim (int): Number of feature channels
|
||||
depth (int): Depths of this stage.
|
||||
num_heads (int): Number of attention head.
|
||||
window_size (int): Local window size. Default: 7.
|
||||
mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. Default: 4.
|
||||
qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
|
||||
qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
|
||||
drop (float, optional): Dropout rate. Default: 0.0
|
||||
attn_drop (float, optional): Attention dropout rate. Default: 0.0
|
||||
drop_path (float | tuple[float], optional): Stochastic depth rate. Default: 0.0
|
||||
norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm
|
||||
downsample (nn.Module | None, optional): Downsample layer at the end of the layer. Default: None
|
||||
use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
|
||||
"""
|
||||
|
||||
def __init__(self,
|
||||
dim,
|
||||
depth,
|
||||
num_heads,
|
||||
window_size=7,
|
||||
mlp_ratio=4.,
|
||||
qkv_bias=True,
|
||||
qk_scale=None,
|
||||
drop=0.,
|
||||
attn_drop=0.,
|
||||
drop_path=0.,
|
||||
norm_layer=nn.LayerNorm,
|
||||
downsample=None,
|
||||
use_checkpoint=False):
|
||||
super().__init__()
|
||||
self.window_size = window_size
|
||||
self.shift_size = window_size // 2
|
||||
self.depth = depth
|
||||
self.use_checkpoint = use_checkpoint
|
||||
|
||||
# build blocks
|
||||
self.blocks = nn.ModuleList([
|
||||
SwinTransformerBlock(
|
||||
dim=dim,
|
||||
num_heads=num_heads,
|
||||
window_size=window_size,
|
||||
shift_size=0 if (i % 2 == 0) else window_size // 2,
|
||||
mlp_ratio=mlp_ratio,
|
||||
qkv_bias=qkv_bias,
|
||||
qk_scale=qk_scale,
|
||||
drop=drop,
|
||||
attn_drop=attn_drop,
|
||||
drop_path=drop_path[i] if isinstance(drop_path, list) else drop_path,
|
||||
norm_layer=norm_layer)
|
||||
for i in range(depth)])
|
||||
|
||||
# patch merging layer
|
||||
if downsample is not None:
|
||||
self.downsample = downsample(dim=dim, norm_layer=norm_layer)
|
||||
else:
|
||||
self.downsample = None
|
||||
|
||||
def forward(self, x, H, W):
|
||||
""" Forward function.
|
||||
|
||||
Args:
|
||||
x: Input feature, tensor size (B, H*W, C).
|
||||
H, W: Spatial resolution of the input feature.
|
||||
"""
|
||||
|
||||
# calculate attention mask for SW-MSA
|
||||
# Turn int to torch.tensor for the compatiability with torch.compile in PyTorch 2.5.
|
||||
Hp = torch.ceil(torch.tensor(H) / self.window_size).to(torch.int64) * self.window_size
|
||||
Wp = torch.ceil(torch.tensor(W) / self.window_size).to(torch.int64) * self.window_size
|
||||
img_mask = torch.zeros((1, Hp, Wp, 1), device=x.device) # 1 Hp Wp 1
|
||||
h_slices = (slice(0, -self.window_size),
|
||||
slice(-self.window_size, -self.shift_size),
|
||||
slice(-self.shift_size, None))
|
||||
w_slices = (slice(0, -self.window_size),
|
||||
slice(-self.window_size, -self.shift_size),
|
||||
slice(-self.shift_size, None))
|
||||
cnt = 0
|
||||
for h in h_slices:
|
||||
for w in w_slices:
|
||||
img_mask[:, h, w, :] = cnt
|
||||
cnt += 1
|
||||
|
||||
mask_windows = window_partition(img_mask, self.window_size) # nW, window_size, window_size, 1
|
||||
mask_windows = mask_windows.view(-1, self.window_size * self.window_size)
|
||||
attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)
|
||||
attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0)).to(x.dtype)
|
||||
|
||||
for blk in self.blocks:
|
||||
blk.H, blk.W = H, W
|
||||
if self.use_checkpoint:
|
||||
x = checkpoint.checkpoint(blk, x, attn_mask)
|
||||
else:
|
||||
x = blk(x, attn_mask)
|
||||
if self.downsample is not None:
|
||||
x_down = self.downsample(x, H, W)
|
||||
Wh, Ww = (H + 1) // 2, (W + 1) // 2
|
||||
return x, H, W, x_down, Wh, Ww
|
||||
else:
|
||||
return x, H, W, x, H, W
|
||||
|
||||
|
||||
class PatchEmbed(nn.Module):
|
||||
""" Image to Patch Embedding
|
||||
|
||||
Args:
|
||||
patch_size (int): Patch token size. Default: 4.
|
||||
in_channels (int): Number of input image channels. Default: 3.
|
||||
embed_dim (int): Number of linear projection output channels. Default: 96.
|
||||
norm_layer (nn.Module, optional): Normalization layer. Default: None
|
||||
"""
|
||||
|
||||
def __init__(self, patch_size=4, in_channels=3, embed_dim=96, norm_layer=None):
|
||||
super().__init__()
|
||||
patch_size = to_2tuple(patch_size)
|
||||
self.patch_size = patch_size
|
||||
|
||||
self.in_channels = in_channels
|
||||
self.embed_dim = embed_dim
|
||||
|
||||
self.proj = nn.Conv2d(in_channels, embed_dim, kernel_size=patch_size, stride=patch_size)
|
||||
if norm_layer is not None:
|
||||
self.norm = norm_layer(embed_dim)
|
||||
else:
|
||||
self.norm = None
|
||||
|
||||
def forward(self, x):
|
||||
"""Forward function."""
|
||||
# padding
|
||||
_, _, H, W = x.size()
|
||||
if W % self.patch_size[1] != 0:
|
||||
x = F.pad(x, (0, self.patch_size[1] - W % self.patch_size[1]))
|
||||
if H % self.patch_size[0] != 0:
|
||||
x = F.pad(x, (0, 0, 0, self.patch_size[0] - H % self.patch_size[0]))
|
||||
|
||||
x = self.proj(x) # B C Wh Ww
|
||||
if self.norm is not None:
|
||||
Wh, Ww = x.size(2), x.size(3)
|
||||
x = x.flatten(2).transpose(1, 2)
|
||||
x = self.norm(x)
|
||||
x = x.transpose(1, 2).view(-1, self.embed_dim, Wh, Ww)
|
||||
|
||||
return x
|
||||
|
||||
|
||||
class SwinTransformer(nn.Module):
|
||||
""" Swin Transformer backbone.
|
||||
A PyTorch impl of : `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows` -
|
||||
https://arxiv.org/pdf/2103.14030
|
||||
|
||||
Args:
|
||||
pretrain_img_size (int): Input image size for training the pretrained model,
|
||||
used in absolute postion embedding. Default 224.
|
||||
patch_size (int | tuple(int)): Patch size. Default: 4.
|
||||
in_channels (int): Number of input image channels. Default: 3.
|
||||
embed_dim (int): Number of linear projection output channels. Default: 96.
|
||||
depths (tuple[int]): Depths of each Swin Transformer stage.
|
||||
num_heads (tuple[int]): Number of attention head of each stage.
|
||||
window_size (int): Window size. Default: 7.
|
||||
mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. Default: 4.
|
||||
qkv_bias (bool): If True, add a learnable bias to query, key, value. Default: True
|
||||
qk_scale (float): Override default qk scale of head_dim ** -0.5 if set.
|
||||
drop_rate (float): Dropout rate.
|
||||
attn_drop_rate (float): Attention dropout rate. Default: 0.
|
||||
drop_path_rate (float): Stochastic depth rate. Default: 0.2.
|
||||
norm_layer (nn.Module): Normalization layer. Default: nn.LayerNorm.
|
||||
ape (bool): If True, add absolute position embedding to the patch embedding. Default: False.
|
||||
patch_norm (bool): If True, add normalization after patch embedding. Default: True.
|
||||
out_indices (Sequence[int]): Output from which stages.
|
||||
frozen_stages (int): Stages to be frozen (stop grad and set eval mode).
|
||||
-1 means not freezing any parameters.
|
||||
use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
|
||||
"""
|
||||
|
||||
def __init__(self,
|
||||
pretrain_img_size=224,
|
||||
patch_size=4,
|
||||
in_channels=3,
|
||||
embed_dim=96,
|
||||
depths=[2, 2, 6, 2],
|
||||
num_heads=[3, 6, 12, 24],
|
||||
window_size=7,
|
||||
mlp_ratio=4.,
|
||||
qkv_bias=True,
|
||||
qk_scale=None,
|
||||
drop_rate=0.,
|
||||
attn_drop_rate=0.,
|
||||
drop_path_rate=0.2,
|
||||
norm_layer=nn.LayerNorm,
|
||||
ape=False,
|
||||
patch_norm=True,
|
||||
out_indices=(0, 1, 2, 3),
|
||||
frozen_stages=-1,
|
||||
use_checkpoint=False):
|
||||
super().__init__()
|
||||
|
||||
self.pretrain_img_size = pretrain_img_size
|
||||
self.num_layers = len(depths)
|
||||
self.embed_dim = embed_dim
|
||||
self.ape = ape
|
||||
self.patch_norm = patch_norm
|
||||
self.out_indices = out_indices
|
||||
self.frozen_stages = frozen_stages
|
||||
|
||||
# split image into non-overlapping patches
|
||||
self.patch_embed = PatchEmbed(
|
||||
patch_size=patch_size, in_channels=in_channels, embed_dim=embed_dim,
|
||||
norm_layer=norm_layer if self.patch_norm else None)
|
||||
|
||||
# absolute position embedding
|
||||
if self.ape:
|
||||
pretrain_img_size = to_2tuple(pretrain_img_size)
|
||||
patch_size = to_2tuple(patch_size)
|
||||
patches_resolution = [pretrain_img_size[0] // patch_size[0], pretrain_img_size[1] // patch_size[1]]
|
||||
|
||||
self.absolute_pos_embed = nn.Parameter(torch.zeros(1, embed_dim, patches_resolution[0], patches_resolution[1]))
|
||||
trunc_normal_(self.absolute_pos_embed, std=.02)
|
||||
|
||||
self.pos_drop = nn.Dropout(p=drop_rate)
|
||||
|
||||
# stochastic depth
|
||||
dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))] # stochastic depth decay rule
|
||||
|
||||
# build layers
|
||||
self.layers = nn.ModuleList()
|
||||
for i_layer in range(self.num_layers):
|
||||
layer = BasicLayer(
|
||||
dim=int(embed_dim * 2 ** i_layer),
|
||||
depth=depths[i_layer],
|
||||
num_heads=num_heads[i_layer],
|
||||
window_size=window_size,
|
||||
mlp_ratio=mlp_ratio,
|
||||
qkv_bias=qkv_bias,
|
||||
qk_scale=qk_scale,
|
||||
drop=drop_rate,
|
||||
attn_drop=attn_drop_rate,
|
||||
drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])],
|
||||
norm_layer=norm_layer,
|
||||
downsample=PatchMerging if (i_layer < self.num_layers - 1) else None,
|
||||
use_checkpoint=use_checkpoint)
|
||||
self.layers.append(layer)
|
||||
|
||||
num_features = [int(embed_dim * 2 ** i) for i in range(self.num_layers)]
|
||||
self.num_features = num_features
|
||||
|
||||
# add a norm layer for each output
|
||||
for i_layer in out_indices:
|
||||
layer = norm_layer(num_features[i_layer])
|
||||
layer_name = f'norm{i_layer}'
|
||||
self.add_module(layer_name, layer)
|
||||
|
||||
self._freeze_stages()
|
||||
|
||||
def _freeze_stages(self):
|
||||
if self.frozen_stages >= 0:
|
||||
self.patch_embed.eval()
|
||||
for param in self.patch_embed.parameters():
|
||||
param.requires_grad = False
|
||||
|
||||
if self.frozen_stages >= 1 and self.ape:
|
||||
self.absolute_pos_embed.requires_grad = False
|
||||
|
||||
if self.frozen_stages >= 2:
|
||||
self.pos_drop.eval()
|
||||
for i in range(0, self.frozen_stages - 1):
|
||||
m = self.layers[i]
|
||||
m.eval()
|
||||
for param in m.parameters():
|
||||
param.requires_grad = False
|
||||
|
||||
|
||||
def forward(self, x):
|
||||
"""Forward function."""
|
||||
x = self.patch_embed(x)
|
||||
|
||||
Wh, Ww = x.size(2), x.size(3)
|
||||
if self.ape:
|
||||
# interpolate the position embedding to the corresponding size
|
||||
absolute_pos_embed = F.interpolate(self.absolute_pos_embed, size=(Wh, Ww), mode='bicubic')
|
||||
x = (x + absolute_pos_embed) # B Wh*Ww C
|
||||
|
||||
outs = []#x.contiguous()]
|
||||
x = x.flatten(2).transpose(1, 2)
|
||||
x = self.pos_drop(x)
|
||||
for i in range(self.num_layers):
|
||||
layer = self.layers[i]
|
||||
x_out, H, W, x, Wh, Ww = layer(x, Wh, Ww)
|
||||
|
||||
if i in self.out_indices:
|
||||
norm_layer = getattr(self, f'norm{i}')
|
||||
x_out = norm_layer(x_out)
|
||||
|
||||
out = x_out.view(-1, H, W, self.num_features[i]).permute(0, 3, 1, 2).contiguous()
|
||||
outs.append(out)
|
||||
|
||||
return tuple(outs)
|
||||
|
||||
def train(self, mode=True):
|
||||
"""Convert the model into training mode while keep layers freezed."""
|
||||
super(SwinTransformer, self).train(mode)
|
||||
self._freeze_stages()
|
||||
|
||||
def swin_v1_t():
|
||||
model = SwinTransformer(embed_dim=96, depths=[2, 2, 6, 2], num_heads=[3, 6, 12, 24], window_size=7)
|
||||
return model
|
||||
|
||||
def swin_v1_s():
|
||||
model = SwinTransformer(embed_dim=96, depths=[2, 2, 18, 2], num_heads=[3, 6, 12, 24], window_size=7)
|
||||
return model
|
||||
|
||||
def swin_v1_b():
|
||||
model = SwinTransformer(embed_dim=128, depths=[2, 2, 18, 2], num_heads=[4, 8, 16, 32], window_size=12)
|
||||
return model
|
||||
|
||||
def swin_v1_l():
|
||||
model = SwinTransformer(embed_dim=192, depths=[2, 2, 18, 2], num_heads=[6, 12, 24, 48], window_size=12)
|
||||
return model
|
||||
@@ -0,0 +1,338 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
from einops import rearrange
|
||||
from kornia.filters import laplacian
|
||||
from huggingface_hub import PyTorchModelHubMixin
|
||||
|
||||
from ..config import Config
|
||||
from ..dataset import class_labels_TR_sorted
|
||||
from .backbones.build_backbone import build_backbone
|
||||
from .modules.decoder_blocks import BasicDecBlk, ResBlk
|
||||
from .modules.lateral_blocks import BasicLatBlk
|
||||
from .modules.aspp import ASPP, ASPPDeformable
|
||||
from .refinement.refiner import Refiner, RefinerPVTInChannels4, RefUNet
|
||||
from .refinement.stem_layer import StemLayer
|
||||
|
||||
|
||||
def image2patches(image, grid_h=2, grid_w=2, patch_ref=None, transformation='b c (hg h) (wg w) -> (b hg wg) c h w'):
|
||||
if patch_ref is not None:
|
||||
grid_h, grid_w = image.shape[-2] // patch_ref.shape[-2], image.shape[-1] // patch_ref.shape[-1]
|
||||
patches = rearrange(image, transformation, hg=grid_h, wg=grid_w)
|
||||
return patches
|
||||
|
||||
def patches2image(patches, grid_h=2, grid_w=2, patch_ref=None, transformation='(b hg wg) c h w -> b c (hg h) (wg w)'):
|
||||
if patch_ref is not None:
|
||||
grid_h, grid_w = patch_ref.shape[-2] // patches[0].shape[-2], patch_ref.shape[-1] // patches[0].shape[-1]
|
||||
image = rearrange(patches, transformation, hg=grid_h, wg=grid_w)
|
||||
return image
|
||||
|
||||
class BiRefNet(nn.Module):
|
||||
def __init__(self, bb_pretrained=True, bb_index=6):
|
||||
super(BiRefNet, self).__init__()
|
||||
self.config = Config(bb_index)
|
||||
self.epoch = 1
|
||||
self.bb = build_backbone(self.config.bb, pretrained=bb_pretrained)
|
||||
|
||||
channels = self.config.lateral_channels_in_collection
|
||||
|
||||
if self.config.auxiliary_classification:
|
||||
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
|
||||
self.cls_head = nn.Sequential(
|
||||
nn.Linear(channels[0], len(class_labels_TR_sorted))
|
||||
)
|
||||
|
||||
if self.config.squeeze_block:
|
||||
self.squeeze_module = nn.Sequential(*[
|
||||
eval(self.config.squeeze_block.split('_x')[0])(channels[0]+sum(self.config.cxt), channels[0])
|
||||
for _ in range(eval(self.config.squeeze_block.split('_x')[1]))
|
||||
])
|
||||
|
||||
self.decoder = Decoder(channels)
|
||||
|
||||
if self.config.ender:
|
||||
self.dec_end = nn.Sequential(
|
||||
nn.Conv2d(1, 16, 3, 1, 1),
|
||||
nn.Conv2d(16, 1, 3, 1, 1),
|
||||
nn.ReLU(inplace=True),
|
||||
)
|
||||
|
||||
# refine patch-level segmentation
|
||||
if self.config.refine:
|
||||
if self.config.refine == 'itself':
|
||||
self.stem_layer = StemLayer(in_channels=3+1, inter_channels=48, out_channels=3, norm_layer='BN' if self.config.batch_size > 1 else 'LN')
|
||||
else:
|
||||
self.refiner = eval('{}({})'.format(self.config.refine, 'in_channels=3+1'))
|
||||
|
||||
if self.config.freeze_bb:
|
||||
# Freeze the backbone...
|
||||
print(self.named_parameters())
|
||||
for key, value in self.named_parameters():
|
||||
if 'bb.' in key and 'refiner.' not in key:
|
||||
value.requires_grad = False
|
||||
|
||||
def forward_enc(self, x):
|
||||
if self.config.bb in ['vgg16', 'vgg16bn', 'resnet50']:
|
||||
x1 = self.bb.conv1(x); x2 = self.bb.conv2(x1); x3 = self.bb.conv3(x2); x4 = self.bb.conv4(x3)
|
||||
else:
|
||||
x1, x2, x3, x4 = self.bb(x)
|
||||
if self.config.mul_scl_ipt == 'cat':
|
||||
B, C, H, W = x.shape
|
||||
x1_, x2_, x3_, x4_ = self.bb(F.interpolate(x, size=(H//2, W//2), mode='bilinear', align_corners=True))
|
||||
x1 = torch.cat([x1, F.interpolate(x1_, size=x1.shape[2:], mode='bilinear', align_corners=True)], dim=1)
|
||||
x2 = torch.cat([x2, F.interpolate(x2_, size=x2.shape[2:], mode='bilinear', align_corners=True)], dim=1)
|
||||
x3 = torch.cat([x3, F.interpolate(x3_, size=x3.shape[2:], mode='bilinear', align_corners=True)], dim=1)
|
||||
x4 = torch.cat([x4, F.interpolate(x4_, size=x4.shape[2:], mode='bilinear', align_corners=True)], dim=1)
|
||||
elif self.config.mul_scl_ipt == 'add':
|
||||
B, C, H, W = x.shape
|
||||
x1_, x2_, x3_, x4_ = self.bb(F.interpolate(x, size=(H//2, W//2), mode='bilinear', align_corners=True))
|
||||
x1 = x1 + F.interpolate(x1_, size=x1.shape[2:], mode='bilinear', align_corners=True)
|
||||
x2 = x2 + F.interpolate(x2_, size=x2.shape[2:], mode='bilinear', align_corners=True)
|
||||
x3 = x3 + F.interpolate(x3_, size=x3.shape[2:], mode='bilinear', align_corners=True)
|
||||
x4 = x4 + F.interpolate(x4_, size=x4.shape[2:], mode='bilinear', align_corners=True)
|
||||
class_preds = self.cls_head(self.avgpool(x4).view(x4.shape[0], -1)) if self.training and self.config.auxiliary_classification else None
|
||||
if self.config.cxt:
|
||||
x4 = torch.cat(
|
||||
(
|
||||
*[
|
||||
F.interpolate(x1, size=x4.shape[2:], mode='bilinear', align_corners=True),
|
||||
F.interpolate(x2, size=x4.shape[2:], mode='bilinear', align_corners=True),
|
||||
F.interpolate(x3, size=x4.shape[2:], mode='bilinear', align_corners=True),
|
||||
][-len(self.config.cxt):],
|
||||
x4
|
||||
),
|
||||
dim=1
|
||||
)
|
||||
return (x1, x2, x3, x4), class_preds
|
||||
|
||||
def forward_ori(self, x):
|
||||
########## Encoder ##########
|
||||
(x1, x2, x3, x4), class_preds = self.forward_enc(x)
|
||||
if self.config.squeeze_block:
|
||||
x4 = self.squeeze_module(x4)
|
||||
########## Decoder ##########
|
||||
features = [x, x1, x2, x3, x4]
|
||||
if self.training and self.config.out_ref:
|
||||
features.append(laplacian(torch.mean(x, dim=1).unsqueeze(1), kernel_size=5))
|
||||
scaled_preds = self.decoder(features)
|
||||
return scaled_preds, class_preds
|
||||
|
||||
def forward(self, x):
|
||||
scaled_preds, class_preds = self.forward_ori(x)
|
||||
class_preds_lst = [class_preds]
|
||||
return [scaled_preds, class_preds_lst] if self.training else scaled_preds
|
||||
|
||||
|
||||
class Decoder(nn.Module):
|
||||
def __init__(self, channels):
|
||||
super(Decoder, self).__init__()
|
||||
self.config = Config()
|
||||
DecoderBlock = eval(self.config.dec_blk)
|
||||
LateralBlock = eval(self.config.lat_blk)
|
||||
|
||||
if self.config.dec_ipt:
|
||||
self.split = self.config.dec_ipt_split
|
||||
N_dec_ipt = 64
|
||||
DBlock = SimpleConvs
|
||||
ic = 64
|
||||
ipt_cha_opt = 1
|
||||
self.ipt_blk5 = DBlock(2**10*3 if self.split else 3, [N_dec_ipt, channels[0]//8][ipt_cha_opt], inter_channels=ic)
|
||||
self.ipt_blk4 = DBlock(2**8*3 if self.split else 3, [N_dec_ipt, channels[0]//8][ipt_cha_opt], inter_channels=ic)
|
||||
self.ipt_blk3 = DBlock(2**6*3 if self.split else 3, [N_dec_ipt, channels[1]//8][ipt_cha_opt], inter_channels=ic)
|
||||
self.ipt_blk2 = DBlock(2**4*3 if self.split else 3, [N_dec_ipt, channels[2]//8][ipt_cha_opt], inter_channels=ic)
|
||||
self.ipt_blk1 = DBlock(2**0*3 if self.split else 3, [N_dec_ipt, channels[3]//8][ipt_cha_opt], inter_channels=ic)
|
||||
else:
|
||||
self.split = None
|
||||
|
||||
self.decoder_block4 = DecoderBlock(channels[0]+([N_dec_ipt, channels[0]//8][ipt_cha_opt] if self.config.dec_ipt else 0), channels[1])
|
||||
self.decoder_block3 = DecoderBlock(channels[1]+([N_dec_ipt, channels[0]//8][ipt_cha_opt] if self.config.dec_ipt else 0), channels[2])
|
||||
self.decoder_block2 = DecoderBlock(channels[2]+([N_dec_ipt, channels[1]//8][ipt_cha_opt] if self.config.dec_ipt else 0), channels[3])
|
||||
self.decoder_block1 = DecoderBlock(channels[3]+([N_dec_ipt, channels[2]//8][ipt_cha_opt] if self.config.dec_ipt else 0), channels[3]//2)
|
||||
self.conv_out1 = nn.Sequential(nn.Conv2d(channels[3]//2+([N_dec_ipt, channels[3]//8][ipt_cha_opt] if self.config.dec_ipt else 0), 1, 1, 1, 0))
|
||||
|
||||
self.lateral_block4 = LateralBlock(channels[1], channels[1])
|
||||
self.lateral_block3 = LateralBlock(channels[2], channels[2])
|
||||
self.lateral_block2 = LateralBlock(channels[3], channels[3])
|
||||
|
||||
if self.config.ms_supervision:
|
||||
self.conv_ms_spvn_4 = nn.Conv2d(channels[1], 1, 1, 1, 0)
|
||||
self.conv_ms_spvn_3 = nn.Conv2d(channels[2], 1, 1, 1, 0)
|
||||
self.conv_ms_spvn_2 = nn.Conv2d(channels[3], 1, 1, 1, 0)
|
||||
|
||||
if self.config.out_ref:
|
||||
_N = 16
|
||||
self.gdt_convs_4 = nn.Sequential(nn.Conv2d(channels[1], _N, 3, 1, 1), nn.BatchNorm2d(_N) if self.config.batch_size > 1 else nn.Identity(), nn.ReLU(inplace=True))
|
||||
self.gdt_convs_3 = nn.Sequential(nn.Conv2d(channels[2], _N, 3, 1, 1), nn.BatchNorm2d(_N) if self.config.batch_size > 1 else nn.Identity(), nn.ReLU(inplace=True))
|
||||
self.gdt_convs_2 = nn.Sequential(nn.Conv2d(channels[3], _N, 3, 1, 1), nn.BatchNorm2d(_N) if self.config.batch_size > 1 else nn.Identity(), nn.ReLU(inplace=True))
|
||||
|
||||
self.gdt_convs_pred_4 = nn.Sequential(nn.Conv2d(_N, 1, 1, 1, 0))
|
||||
self.gdt_convs_pred_3 = nn.Sequential(nn.Conv2d(_N, 1, 1, 1, 0))
|
||||
self.gdt_convs_pred_2 = nn.Sequential(nn.Conv2d(_N, 1, 1, 1, 0))
|
||||
|
||||
self.gdt_convs_attn_4 = nn.Sequential(nn.Conv2d(_N, 1, 1, 1, 0))
|
||||
self.gdt_convs_attn_3 = nn.Sequential(nn.Conv2d(_N, 1, 1, 1, 0))
|
||||
self.gdt_convs_attn_2 = nn.Sequential(nn.Conv2d(_N, 1, 1, 1, 0))
|
||||
|
||||
def forward(self, features):
|
||||
if self.training and self.config.out_ref:
|
||||
outs_gdt_pred = []
|
||||
outs_gdt_label = []
|
||||
x, x1, x2, x3, x4, gdt_gt = features
|
||||
else:
|
||||
x, x1, x2, x3, x4 = features
|
||||
outs = []
|
||||
|
||||
if self.config.dec_ipt:
|
||||
patches_batch = image2patches(x, patch_ref=x4, transformation='b c (hg h) (wg w) -> b (c hg wg) h w') if self.split else x
|
||||
x4 = torch.cat((x4, self.ipt_blk5(F.interpolate(patches_batch, size=x4.shape[2:], mode='bilinear', align_corners=True))), 1)
|
||||
p4 = self.decoder_block4(x4)
|
||||
m4 = self.conv_ms_spvn_4(p4) if self.config.ms_supervision and self.training else None
|
||||
if self.config.out_ref:
|
||||
p4_gdt = self.gdt_convs_4(p4)
|
||||
if self.training:
|
||||
# >> GT:
|
||||
m4_dia = m4
|
||||
gdt_label_main_4 = gdt_gt * F.interpolate(m4_dia, size=gdt_gt.shape[2:], mode='bilinear', align_corners=True)
|
||||
outs_gdt_label.append(gdt_label_main_4)
|
||||
# >> Pred:
|
||||
gdt_pred_4 = self.gdt_convs_pred_4(p4_gdt)
|
||||
outs_gdt_pred.append(gdt_pred_4)
|
||||
gdt_attn_4 = self.gdt_convs_attn_4(p4_gdt).sigmoid()
|
||||
# >> Finally:
|
||||
p4 = p4 * gdt_attn_4
|
||||
_p4 = F.interpolate(p4, size=x3.shape[2:], mode='bilinear', align_corners=True)
|
||||
_p3 = _p4 + self.lateral_block4(x3)
|
||||
|
||||
if self.config.dec_ipt:
|
||||
patches_batch = image2patches(x, patch_ref=_p3, transformation='b c (hg h) (wg w) -> b (c hg wg) h w') if self.split else x
|
||||
_p3 = torch.cat((_p3, self.ipt_blk4(F.interpolate(patches_batch, size=x3.shape[2:], mode='bilinear', align_corners=True))), 1)
|
||||
p3 = self.decoder_block3(_p3)
|
||||
m3 = self.conv_ms_spvn_3(p3) if self.config.ms_supervision and self.training else None
|
||||
if self.config.out_ref:
|
||||
p3_gdt = self.gdt_convs_3(p3)
|
||||
if self.training:
|
||||
# >> GT:
|
||||
# m3 --dilation--> m3_dia
|
||||
# G_3^gt * m3_dia --> G_3^m, which is the label of gradient
|
||||
m3_dia = m3
|
||||
gdt_label_main_3 = gdt_gt * F.interpolate(m3_dia, size=gdt_gt.shape[2:], mode='bilinear', align_corners=True)
|
||||
outs_gdt_label.append(gdt_label_main_3)
|
||||
# >> Pred:
|
||||
# p3 --conv--BN--> F_3^G, where F_3^G predicts the \hat{G_3} with xx
|
||||
# F_3^G --sigmoid--> A_3^G
|
||||
gdt_pred_3 = self.gdt_convs_pred_3(p3_gdt)
|
||||
outs_gdt_pred.append(gdt_pred_3)
|
||||
gdt_attn_3 = self.gdt_convs_attn_3(p3_gdt).sigmoid()
|
||||
# >> Finally:
|
||||
# p3 = p3 * A_3^G
|
||||
p3 = p3 * gdt_attn_3
|
||||
_p3 = F.interpolate(p3, size=x2.shape[2:], mode='bilinear', align_corners=True)
|
||||
_p2 = _p3 + self.lateral_block3(x2)
|
||||
|
||||
if self.config.dec_ipt:
|
||||
patches_batch = image2patches(x, patch_ref=_p2, transformation='b c (hg h) (wg w) -> b (c hg wg) h w') if self.split else x
|
||||
_p2 = torch.cat((_p2, self.ipt_blk3(F.interpolate(patches_batch, size=x2.shape[2:], mode='bilinear', align_corners=True))), 1)
|
||||
p2 = self.decoder_block2(_p2)
|
||||
m2 = self.conv_ms_spvn_2(p2) if self.config.ms_supervision and self.training else None
|
||||
if self.config.out_ref:
|
||||
p2_gdt = self.gdt_convs_2(p2)
|
||||
if self.training:
|
||||
# >> GT:
|
||||
m2_dia = m2
|
||||
gdt_label_main_2 = gdt_gt * F.interpolate(m2_dia, size=gdt_gt.shape[2:], mode='bilinear', align_corners=True)
|
||||
outs_gdt_label.append(gdt_label_main_2)
|
||||
# >> Pred:
|
||||
gdt_pred_2 = self.gdt_convs_pred_2(p2_gdt)
|
||||
outs_gdt_pred.append(gdt_pred_2)
|
||||
gdt_attn_2 = self.gdt_convs_attn_2(p2_gdt).sigmoid()
|
||||
# >> Finally:
|
||||
p2 = p2 * gdt_attn_2
|
||||
_p2 = F.interpolate(p2, size=x1.shape[2:], mode='bilinear', align_corners=True)
|
||||
_p1 = _p2 + self.lateral_block2(x1)
|
||||
|
||||
if self.config.dec_ipt:
|
||||
patches_batch = image2patches(x, patch_ref=_p1, transformation='b c (hg h) (wg w) -> b (c hg wg) h w') if self.split else x
|
||||
_p1 = torch.cat((_p1, self.ipt_blk2(F.interpolate(patches_batch, size=x1.shape[2:], mode='bilinear', align_corners=True))), 1)
|
||||
_p1 = self.decoder_block1(_p1)
|
||||
_p1 = F.interpolate(_p1, size=x.shape[2:], mode='bilinear', align_corners=True)
|
||||
|
||||
if self.config.dec_ipt:
|
||||
patches_batch = image2patches(x, patch_ref=_p1, transformation='b c (hg h) (wg w) -> b (c hg wg) h w') if self.split else x
|
||||
_p1 = torch.cat((_p1, self.ipt_blk1(F.interpolate(patches_batch, size=x.shape[2:], mode='bilinear', align_corners=True))), 1)
|
||||
p1_out = self.conv_out1(_p1)
|
||||
|
||||
if self.config.ms_supervision and self.training:
|
||||
outs.append(m4)
|
||||
outs.append(m3)
|
||||
outs.append(m2)
|
||||
outs.append(p1_out)
|
||||
return outs if not (self.config.out_ref and self.training) else ([outs_gdt_pred, outs_gdt_label], outs)
|
||||
|
||||
|
||||
class SimpleConvs(nn.Module):
|
||||
def __init__(
|
||||
self, in_channels: int, out_channels: int, inter_channels=64
|
||||
) -> None:
|
||||
super().__init__()
|
||||
self.conv1 = nn.Conv2d(in_channels, inter_channels, 3, 1, 1)
|
||||
self.conv_out = nn.Conv2d(inter_channels, out_channels, 3, 1, 1)
|
||||
|
||||
def forward(self, x):
|
||||
return self.conv_out(self.conv1(x))
|
||||
|
||||
|
||||
###########
|
||||
|
||||
|
||||
class BiRefNetC2F(
|
||||
nn.Module,
|
||||
PyTorchModelHubMixin,
|
||||
library_name="birefnet_c2f",
|
||||
repo_url="https://github.com/ZhengPeng7/BiRefNet_C2F",
|
||||
tags=['Image Segmentation', 'Background Removal', 'Mask Generation', 'Dichotomous Image Segmentation', 'Camouflaged Object Detection', 'Salient Object Detection']
|
||||
):
|
||||
def __init__(self, bb_pretrained=True):
|
||||
super(BiRefNetC2F, self).__init__()
|
||||
self.config = Config()
|
||||
self.epoch = 1
|
||||
self.grid = 4
|
||||
self.model_coarse = BiRefNet(bb_pretrained=True)
|
||||
self.model_fine = BiRefNet(bb_pretrained=True)
|
||||
self.input_mixer = nn.Conv2d(4, 3, 1, 1, 0)
|
||||
self.output_mixer_merge_post = nn.Sequential(nn.Conv2d(1, 16, 3, 1, 1), nn.Conv2d(16, 1, 3, 1, 1))
|
||||
|
||||
def forward(self, x):
|
||||
x_ori = x.clone()
|
||||
########## Coarse ##########
|
||||
x = F.interpolate(x, size=[s//self.grid for s in self.config.size[::-1]], mode='bilinear', align_corners=True)
|
||||
|
||||
if self.training:
|
||||
scaled_preds, class_preds_lst = self.model_coarse(x)
|
||||
else:
|
||||
scaled_preds = self.model_coarse(x)
|
||||
########## Fine ##########
|
||||
x_HR_patches = image2patches(x_ori, patch_ref=x, transformation='b c (hg h) (wg w) -> (b hg wg) c h w')
|
||||
pred = F.interpolate(scaled_preds[-1] if not (self.config.out_ref and self.training) else scaled_preds[1][-1], size=x_ori.shape[2:], mode='bilinear', align_corners=True)
|
||||
pred_patches = image2patches(pred, patch_ref=x, transformation='b c (hg h) (wg w) -> (b hg wg) c h w')
|
||||
t = torch.cat([x_HR_patches, pred_patches], dim=1)
|
||||
x_HR = self.input_mixer(t)
|
||||
|
||||
pred_patches = image2patches(pred, patch_ref=x_HR, transformation='b c (hg h) (wg w) -> b (c hg wg) h w')
|
||||
if self.training:
|
||||
scaled_preds_HR, class_preds_lst_HR = self.model_fine(x_HR)
|
||||
else:
|
||||
scaled_preds_HR = self.model_fine(x_HR)
|
||||
if self.training:
|
||||
if self.config.out_ref:
|
||||
[outs_gdt_pred, outs_gdt_label], outs = scaled_preds
|
||||
[outs_gdt_pred_HR, outs_gdt_label_HR], outs_HR = scaled_preds_HR
|
||||
for idx_out, out_HR in enumerate(outs_HR):
|
||||
outs_HR[idx_out] = self.output_mixer_merge_post(patches2image(out_HR, grid_h=self.grid, grid_w=self.grid, transformation='(b hg wg) c h w -> b c (hg h) (wg w)'))
|
||||
return [([outs_gdt_pred + outs_gdt_pred_HR, outs_gdt_label + outs_gdt_label_HR], outs + outs_HR), class_preds_lst] # handle gt here
|
||||
else:
|
||||
return [
|
||||
scaled_preds + [self.output_mixer_merge_post(patches2image(scaled_pred_HR, grid_h=self.grid, grid_w=self.grid, transformation='(b hg wg) c h w -> b c (hg h) (wg w)')) for scaled_pred_HR in scaled_preds_HR],
|
||||
class_preds_lst
|
||||
]
|
||||
else:
|
||||
return scaled_preds + [self.output_mixer_merge_post(patches2image(scaled_pred_HR, grid_h=self.grid, grid_w=self.grid, transformation='(b hg wg) c h w -> b c (hg h) (wg w)')) for scaled_pred_HR in scaled_preds_HR]
|
||||
@@ -0,0 +1,119 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
from ..modules.deform_conv import DeformableConv2d
|
||||
from ...config import Config
|
||||
|
||||
|
||||
config = Config()
|
||||
|
||||
|
||||
class _ASPPModule(nn.Module):
|
||||
def __init__(self, in_channels, planes, kernel_size, padding, dilation):
|
||||
super(_ASPPModule, self).__init__()
|
||||
self.atrous_conv = nn.Conv2d(in_channels, planes, kernel_size=kernel_size,
|
||||
stride=1, padding=padding, dilation=dilation, bias=False)
|
||||
self.bn = nn.BatchNorm2d(planes) if config.batch_size > 1 else nn.Identity()
|
||||
self.relu = nn.ReLU(inplace=True)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.atrous_conv(x)
|
||||
x = self.bn(x)
|
||||
|
||||
return self.relu(x)
|
||||
|
||||
|
||||
class ASPP(nn.Module):
|
||||
def __init__(self, in_channels=64, out_channels=None, output_stride=16):
|
||||
super(ASPP, self).__init__()
|
||||
self.down_scale = 1
|
||||
if out_channels is None:
|
||||
out_channels = in_channels
|
||||
self.in_channelster = 256 // self.down_scale
|
||||
if output_stride == 16:
|
||||
dilations = [1, 6, 12, 18]
|
||||
elif output_stride == 8:
|
||||
dilations = [1, 12, 24, 36]
|
||||
else:
|
||||
raise NotImplementedError
|
||||
|
||||
self.aspp1 = _ASPPModule(in_channels, self.in_channelster, 1, padding=0, dilation=dilations[0])
|
||||
self.aspp2 = _ASPPModule(in_channels, self.in_channelster, 3, padding=dilations[1], dilation=dilations[1])
|
||||
self.aspp3 = _ASPPModule(in_channels, self.in_channelster, 3, padding=dilations[2], dilation=dilations[2])
|
||||
self.aspp4 = _ASPPModule(in_channels, self.in_channelster, 3, padding=dilations[3], dilation=dilations[3])
|
||||
|
||||
self.global_avg_pool = nn.Sequential(nn.AdaptiveAvgPool2d((1, 1)),
|
||||
nn.Conv2d(in_channels, self.in_channelster, 1, stride=1, bias=False),
|
||||
nn.BatchNorm2d(self.in_channelster) if config.batch_size > 1 else nn.Identity(),
|
||||
nn.ReLU(inplace=True))
|
||||
self.conv1 = nn.Conv2d(self.in_channelster * 5, out_channels, 1, bias=False)
|
||||
self.bn1 = nn.BatchNorm2d(out_channels) if config.batch_size > 1 else nn.Identity()
|
||||
self.relu = nn.ReLU(inplace=True)
|
||||
self.dropout = nn.Dropout(0.5)
|
||||
|
||||
def forward(self, x):
|
||||
x1 = self.aspp1(x)
|
||||
x2 = self.aspp2(x)
|
||||
x3 = self.aspp3(x)
|
||||
x4 = self.aspp4(x)
|
||||
x5 = self.global_avg_pool(x)
|
||||
x5 = F.interpolate(x5, size=x1.size()[2:], mode='bilinear', align_corners=True)
|
||||
x = torch.cat((x1, x2, x3, x4, x5), dim=1)
|
||||
|
||||
x = self.conv1(x)
|
||||
x = self.bn1(x)
|
||||
x = self.relu(x)
|
||||
|
||||
return self.dropout(x)
|
||||
|
||||
|
||||
##################### Deformable
|
||||
class _ASPPModuleDeformable(nn.Module):
|
||||
def __init__(self, in_channels, planes, kernel_size, padding):
|
||||
super(_ASPPModuleDeformable, self).__init__()
|
||||
self.atrous_conv = DeformableConv2d(in_channels, planes, kernel_size=kernel_size,
|
||||
stride=1, padding=padding, bias=False)
|
||||
self.bn = nn.BatchNorm2d(planes) if config.batch_size > 1 else nn.Identity()
|
||||
self.relu = nn.ReLU(inplace=True)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.atrous_conv(x)
|
||||
x = self.bn(x)
|
||||
|
||||
return self.relu(x)
|
||||
|
||||
|
||||
class ASPPDeformable(nn.Module):
|
||||
def __init__(self, in_channels, out_channels=None, parallel_block_sizes=[1, 3, 7]):
|
||||
super(ASPPDeformable, self).__init__()
|
||||
self.down_scale = 1
|
||||
if out_channels is None:
|
||||
out_channels = in_channels
|
||||
self.in_channelster = 256 // self.down_scale
|
||||
|
||||
self.aspp1 = _ASPPModuleDeformable(in_channels, self.in_channelster, 1, padding=0)
|
||||
self.aspp_deforms = nn.ModuleList([
|
||||
_ASPPModuleDeformable(in_channels, self.in_channelster, conv_size, padding=int(conv_size//2)) for conv_size in parallel_block_sizes
|
||||
])
|
||||
|
||||
self.global_avg_pool = nn.Sequential(nn.AdaptiveAvgPool2d((1, 1)),
|
||||
nn.Conv2d(in_channels, self.in_channelster, 1, stride=1, bias=False),
|
||||
nn.BatchNorm2d(self.in_channelster) if config.batch_size > 1 else nn.Identity(),
|
||||
nn.ReLU(inplace=True))
|
||||
self.conv1 = nn.Conv2d(self.in_channelster * (2 + len(self.aspp_deforms)), out_channels, 1, bias=False)
|
||||
self.bn1 = nn.BatchNorm2d(out_channels) if config.batch_size > 1 else nn.Identity()
|
||||
self.relu = nn.ReLU(inplace=True)
|
||||
self.dropout = nn.Dropout(0.5)
|
||||
|
||||
def forward(self, x):
|
||||
x1 = self.aspp1(x)
|
||||
x_aspp_deforms = [aspp_deform(x) for aspp_deform in self.aspp_deforms]
|
||||
x5 = self.global_avg_pool(x)
|
||||
x5 = F.interpolate(x5, size=x1.size()[2:], mode='bilinear', align_corners=True)
|
||||
x = torch.cat((x1, *x_aspp_deforms, x5), dim=1)
|
||||
|
||||
x = self.conv1(x)
|
||||
x = self.bn1(x)
|
||||
x = self.relu(x)
|
||||
|
||||
return self.dropout(x)
|
||||
@@ -0,0 +1,65 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from ..modules.aspp import ASPP, ASPPDeformable
|
||||
from ...config import Config
|
||||
|
||||
|
||||
config = Config()
|
||||
|
||||
|
||||
class BasicDecBlk(nn.Module):
|
||||
def __init__(self, in_channels=64, out_channels=64, inter_channels=64):
|
||||
super(BasicDecBlk, self).__init__()
|
||||
inter_channels = in_channels // 4 if config.dec_channels_inter == 'adap' else 64
|
||||
self.conv_in = nn.Conv2d(in_channels, inter_channels, 3, 1, padding=1)
|
||||
self.relu_in = nn.ReLU(inplace=True)
|
||||
if config.dec_att == 'ASPP':
|
||||
self.dec_att = ASPP(in_channels=inter_channels)
|
||||
elif config.dec_att == 'ASPPDeformable':
|
||||
self.dec_att = ASPPDeformable(in_channels=inter_channels)
|
||||
self.conv_out = nn.Conv2d(inter_channels, out_channels, 3, 1, padding=1)
|
||||
self.bn_in = nn.BatchNorm2d(inter_channels) if config.batch_size > 1 else nn.Identity()
|
||||
self.bn_out = nn.BatchNorm2d(out_channels) if config.batch_size > 1 else nn.Identity()
|
||||
|
||||
def forward(self, x):
|
||||
x = self.conv_in(x)
|
||||
x = self.bn_in(x)
|
||||
x = self.relu_in(x)
|
||||
if hasattr(self, 'dec_att'):
|
||||
x = self.dec_att(x)
|
||||
x = self.conv_out(x)
|
||||
x = self.bn_out(x)
|
||||
return x
|
||||
|
||||
|
||||
class ResBlk(nn.Module):
|
||||
def __init__(self, in_channels=64, out_channels=None, inter_channels=64):
|
||||
super(ResBlk, self).__init__()
|
||||
if out_channels is None:
|
||||
out_channels = in_channels
|
||||
inter_channels = in_channels // 4 if config.dec_channels_inter == 'adap' else 64
|
||||
|
||||
self.conv_in = nn.Conv2d(in_channels, inter_channels, 3, 1, padding=1)
|
||||
self.bn_in = nn.BatchNorm2d(inter_channels) if config.batch_size > 1 else nn.Identity()
|
||||
self.relu_in = nn.ReLU(inplace=True)
|
||||
|
||||
if config.dec_att == 'ASPP':
|
||||
self.dec_att = ASPP(in_channels=inter_channels)
|
||||
elif config.dec_att == 'ASPPDeformable':
|
||||
self.dec_att = ASPPDeformable(in_channels=inter_channels)
|
||||
|
||||
self.conv_out = nn.Conv2d(inter_channels, out_channels, 3, 1, padding=1)
|
||||
self.bn_out = nn.BatchNorm2d(out_channels) if config.batch_size > 1 else nn.Identity()
|
||||
|
||||
self.conv_resi = nn.Conv2d(in_channels, out_channels, 1, 1, 0)
|
||||
|
||||
def forward(self, x):
|
||||
_x = self.conv_resi(x)
|
||||
x = self.conv_in(x)
|
||||
x = self.bn_in(x)
|
||||
x = self.relu_in(x)
|
||||
if hasattr(self, 'dec_att'):
|
||||
x = self.dec_att(x)
|
||||
x = self.conv_out(x)
|
||||
x = self.bn_out(x)
|
||||
return x + _x
|
||||
@@ -0,0 +1,66 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from torchvision.ops import deform_conv2d
|
||||
|
||||
|
||||
class DeformableConv2d(nn.Module):
|
||||
def __init__(self,
|
||||
in_channels,
|
||||
out_channels,
|
||||
kernel_size=3,
|
||||
stride=1,
|
||||
padding=1,
|
||||
bias=False):
|
||||
|
||||
super(DeformableConv2d, self).__init__()
|
||||
|
||||
assert type(kernel_size) == tuple or type(kernel_size) == int
|
||||
|
||||
kernel_size = kernel_size if type(kernel_size) == tuple else (kernel_size, kernel_size)
|
||||
self.stride = stride if type(stride) == tuple else (stride, stride)
|
||||
self.padding = padding
|
||||
|
||||
self.offset_conv = nn.Conv2d(in_channels,
|
||||
2 * kernel_size[0] * kernel_size[1],
|
||||
kernel_size=kernel_size,
|
||||
stride=stride,
|
||||
padding=self.padding,
|
||||
bias=True)
|
||||
|
||||
nn.init.constant_(self.offset_conv.weight, 0.)
|
||||
nn.init.constant_(self.offset_conv.bias, 0.)
|
||||
|
||||
self.modulator_conv = nn.Conv2d(in_channels,
|
||||
1 * kernel_size[0] * kernel_size[1],
|
||||
kernel_size=kernel_size,
|
||||
stride=stride,
|
||||
padding=self.padding,
|
||||
bias=True)
|
||||
|
||||
nn.init.constant_(self.modulator_conv.weight, 0.)
|
||||
nn.init.constant_(self.modulator_conv.bias, 0.)
|
||||
|
||||
self.regular_conv = nn.Conv2d(in_channels,
|
||||
out_channels=out_channels,
|
||||
kernel_size=kernel_size,
|
||||
stride=stride,
|
||||
padding=self.padding,
|
||||
bias=bias)
|
||||
|
||||
def forward(self, x):
|
||||
#h, w = x.shape[2:]
|
||||
#max_offset = max(h, w)/4.
|
||||
|
||||
offset = self.offset_conv(x)#.clamp(-max_offset, max_offset)
|
||||
modulator = 2. * torch.sigmoid(self.modulator_conv(x))
|
||||
|
||||
x = deform_conv2d(
|
||||
input=x,
|
||||
offset=offset,
|
||||
weight=self.regular_conv.weight,
|
||||
bias=self.regular_conv.bias,
|
||||
padding=self.padding,
|
||||
mask=modulator,
|
||||
stride=self.stride,
|
||||
)
|
||||
return x
|
||||
@@ -0,0 +1,21 @@
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
from functools import partial
|
||||
|
||||
from ...config import Config
|
||||
|
||||
|
||||
config = Config()
|
||||
|
||||
|
||||
class BasicLatBlk(nn.Module):
|
||||
def __init__(self, in_channels=64, out_channels=64, inter_channels=64):
|
||||
super(BasicLatBlk, self).__init__()
|
||||
inter_channels = in_channels // 4 if config.dec_channels_inter == 'adap' else 64
|
||||
self.conv = nn.Conv2d(in_channels, out_channels, 1, 1, 0)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.conv(x)
|
||||
return x
|
||||
@@ -0,0 +1,222 @@
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from typing import Any, Optional, Tuple, Type
|
||||
|
||||
|
||||
class PromptEncoder(nn.Module):
|
||||
def __init__(
|
||||
self,
|
||||
embed_dim=256,
|
||||
image_embedding_size=1024,
|
||||
input_image_size=(1024, 1024),
|
||||
mask_in_chans=16,
|
||||
activation=nn.GELU
|
||||
) -> None:
|
||||
super().__init__()
|
||||
"""
|
||||
Codes are partially from SAM: https://github.com/facebookresearch/segment-anything/blob/6fdee8f2727f4506cfbbe553e23b895e27956588/segment_anything/modeling/prompt_encoder.py.
|
||||
|
||||
Arguments:
|
||||
embed_dim (int): The prompts' embedding dimension
|
||||
image_embedding_size (tuple(int, int)): The spatial size of the
|
||||
image embedding, as (H, W).
|
||||
input_image_size (int): The padded size of the image as input
|
||||
to the image encoder, as (H, W).
|
||||
mask_in_chans (int): The number of hidden channels used for
|
||||
encoding input masks.
|
||||
activation (nn.Module): The activation to use when encoding
|
||||
input masks.
|
||||
"""
|
||||
super().__init__()
|
||||
self.embed_dim = embed_dim
|
||||
self.input_image_size = input_image_size
|
||||
self.image_embedding_size = image_embedding_size
|
||||
self.pe_layer = PositionEmbeddingRandom(embed_dim // 2)
|
||||
|
||||
self.num_point_embeddings: int = 4 # pos/neg point + 2 box corners
|
||||
point_embeddings = [nn.Embedding(1, embed_dim) for i in range(self.num_point_embeddings)]
|
||||
self.point_embeddings = nn.ModuleList(point_embeddings)
|
||||
self.not_a_point_embed = nn.Embedding(1, embed_dim)
|
||||
|
||||
self.mask_input_size = (4 * image_embedding_size[0], 4 * image_embedding_size[1])
|
||||
self.mask_downscaling = nn.Sequential(
|
||||
nn.Conv2d(1, mask_in_chans // 4, kernel_size=2, stride=2),
|
||||
LayerNorm2d(mask_in_chans // 4),
|
||||
activation(),
|
||||
nn.Conv2d(mask_in_chans // 4, mask_in_chans, kernel_size=2, stride=2),
|
||||
LayerNorm2d(mask_in_chans),
|
||||
activation(),
|
||||
nn.Conv2d(mask_in_chans, embed_dim, kernel_size=1),
|
||||
)
|
||||
self.no_mask_embed = nn.Embedding(1, embed_dim)
|
||||
|
||||
def get_dense_pe(self) -> torch.Tensor:
|
||||
"""
|
||||
Returns the positional encoding used to encode point prompts,
|
||||
applied to a dense set of points the shape of the image encoding.
|
||||
|
||||
Returns:
|
||||
torch.Tensor: Positional encoding with shape
|
||||
1x(embed_dim)x(embedding_h)x(embedding_w)
|
||||
"""
|
||||
return self.pe_layer(self.image_embedding_size).unsqueeze(0)
|
||||
|
||||
def _embed_points(
|
||||
self,
|
||||
points: torch.Tensor,
|
||||
labels: torch.Tensor,
|
||||
pad: bool,
|
||||
) -> torch.Tensor:
|
||||
"""Embeds point prompts."""
|
||||
points = points + 0.5 # Shift to center of pixel
|
||||
if pad:
|
||||
padding_point = torch.zeros((points.shape[0], 1, 2), device=points.device)
|
||||
padding_label = -torch.ones((labels.shape[0], 1), device=labels.device)
|
||||
points = torch.cat([points, padding_point], dim=1)
|
||||
labels = torch.cat([labels, padding_label], dim=1)
|
||||
point_embedding = self.pe_layer.forward_with_coords(points, self.input_image_size)
|
||||
point_embedding[labels == -1] = 0.0
|
||||
point_embedding[labels == -1] += self.not_a_point_embed.weight
|
||||
point_embedding[labels == 0] += self.point_embeddings[0].weight
|
||||
point_embedding[labels == 1] += self.point_embeddings[1].weight
|
||||
return point_embedding
|
||||
|
||||
def _embed_boxes(self, boxes: torch.Tensor) -> torch.Tensor:
|
||||
"""Embeds box prompts."""
|
||||
boxes = boxes + 0.5 # Shift to center of pixel
|
||||
coords = boxes.reshape(-1, 2, 2)
|
||||
corner_embedding = self.pe_layer.forward_with_coords(coords, self.input_image_size)
|
||||
corner_embedding[:, 0, :] += self.point_embeddings[2].weight
|
||||
corner_embedding[:, 1, :] += self.point_embeddings[3].weight
|
||||
return corner_embedding
|
||||
|
||||
def _embed_masks(self, masks: torch.Tensor) -> torch.Tensor:
|
||||
"""Embeds mask inputs."""
|
||||
mask_embedding = self.mask_downscaling(masks)
|
||||
return mask_embedding
|
||||
|
||||
def _get_batch_size(
|
||||
self,
|
||||
points: Optional[Tuple[torch.Tensor, torch.Tensor]],
|
||||
boxes: Optional[torch.Tensor],
|
||||
masks: Optional[torch.Tensor],
|
||||
) -> int:
|
||||
"""
|
||||
Gets the batch size of the output given the batch size of the input prompts.
|
||||
"""
|
||||
if points is not None:
|
||||
return points[0].shape[0]
|
||||
elif boxes is not None:
|
||||
return boxes.shape[0]
|
||||
elif masks is not None:
|
||||
return masks.shape[0]
|
||||
else:
|
||||
return 1
|
||||
|
||||
def _get_device(self) -> torch.device:
|
||||
return self.point_embeddings[0].weight.device
|
||||
|
||||
def forward(
|
||||
self,
|
||||
points: Optional[Tuple[torch.Tensor, torch.Tensor]],
|
||||
boxes: Optional[torch.Tensor],
|
||||
masks: Optional[torch.Tensor],
|
||||
) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
"""
|
||||
Embeds different types of prompts, returning both sparse and dense
|
||||
embeddings.
|
||||
|
||||
Arguments:
|
||||
points (tuple(torch.Tensor, torch.Tensor) or none): point coordinates
|
||||
and labels to embed.
|
||||
boxes (torch.Tensor or none): boxes to embed
|
||||
masks (torch.Tensor or none): masks to embed
|
||||
|
||||
Returns:
|
||||
torch.Tensor: sparse embeddings for the points and boxes, with shape
|
||||
BxNx(embed_dim), where N is determined by the number of input points
|
||||
and boxes.
|
||||
torch.Tensor: dense embeddings for the masks, in the shape
|
||||
Bx(embed_dim)x(embed_H)x(embed_W)
|
||||
"""
|
||||
bs = self._get_batch_size(points, boxes, masks)
|
||||
sparse_embeddings = torch.empty((bs, 0, self.embed_dim), device=self._get_device())
|
||||
if points is not None:
|
||||
coords, labels = points
|
||||
point_embeddings = self._embed_points(coords, labels, pad=(boxes is None))
|
||||
sparse_embeddings = torch.cat([sparse_embeddings, point_embeddings], dim=1)
|
||||
if boxes is not None:
|
||||
box_embeddings = self._embed_boxes(boxes)
|
||||
sparse_embeddings = torch.cat([sparse_embeddings, box_embeddings], dim=1)
|
||||
|
||||
if masks is not None:
|
||||
dense_embeddings = self._embed_masks(masks)
|
||||
else:
|
||||
dense_embeddings = self.no_mask_embed.weight.reshape(1, -1, 1, 1).expand(
|
||||
bs, -1, self.image_embedding_size[0], self.image_embedding_size[1]
|
||||
)
|
||||
|
||||
return sparse_embeddings, dense_embeddings
|
||||
|
||||
|
||||
class PositionEmbeddingRandom(nn.Module):
|
||||
"""
|
||||
Positional encoding using random spatial frequencies.
|
||||
"""
|
||||
|
||||
def __init__(self, num_pos_feats: int = 64, scale: Optional[float] = None) -> None:
|
||||
super().__init__()
|
||||
if scale is None or scale <= 0.0:
|
||||
scale = 1.0
|
||||
self.register_buffer(
|
||||
"positional_encoding_gaussian_matrix",
|
||||
scale * torch.randn((2, num_pos_feats)),
|
||||
)
|
||||
|
||||
def _pe_encoding(self, coords: torch.Tensor) -> torch.Tensor:
|
||||
"""Positionally encode points that are normalized to [0,1]."""
|
||||
# assuming coords are in [0, 1]^2 square and have d_1 x ... x d_n x 2 shape
|
||||
coords = 2 * coords - 1
|
||||
coords = coords @ self.positional_encoding_gaussian_matrix
|
||||
coords = 2 * np.pi * coords
|
||||
# outputs d_1 x ... x d_n x C shape
|
||||
return torch.cat([torch.sin(coords), torch.cos(coords)], dim=-1)
|
||||
|
||||
def forward(self, size: Tuple[int, int]) -> torch.Tensor:
|
||||
"""Generate positional encoding for a grid of the specified size."""
|
||||
h, w = size
|
||||
device: Any = self.positional_encoding_gaussian_matrix.device
|
||||
grid = torch.ones((h, w), device=device, dtype=torch.float32)
|
||||
y_embed = grid.cumsum(dim=0) - 0.5
|
||||
x_embed = grid.cumsum(dim=1) - 0.5
|
||||
y_embed = y_embed / h
|
||||
x_embed = x_embed / w
|
||||
|
||||
pe = self._pe_encoding(torch.stack([x_embed, y_embed], dim=-1))
|
||||
return pe.permute(2, 0, 1) # C x H x W
|
||||
|
||||
def forward_with_coords(
|
||||
self, coords_input: torch.Tensor, image_size: Tuple[int, int]
|
||||
) -> torch.Tensor:
|
||||
"""Positionally encode points that are not normalized to [0,1]."""
|
||||
coords = coords_input.clone()
|
||||
coords[:, :, 0] = coords[:, :, 0] / image_size[1]
|
||||
coords[:, :, 1] = coords[:, :, 1] / image_size[0]
|
||||
return self._pe_encoding(coords.to(torch.float)) # B x N x C
|
||||
|
||||
|
||||
class LayerNorm2d(nn.Module):
|
||||
def __init__(self, num_channels: int, eps: float = 1e-6) -> None:
|
||||
super().__init__()
|
||||
self.weight = nn.Parameter(torch.ones(num_channels))
|
||||
self.bias = nn.Parameter(torch.zeros(num_channels))
|
||||
self.eps = eps
|
||||
|
||||
def forward(self, x: torch.Tensor) -> torch.Tensor:
|
||||
u = x.mean(1, keepdim=True)
|
||||
s = (x - u).pow(2).mean(1, keepdim=True)
|
||||
x = (x - u) / torch.sqrt(s + self.eps)
|
||||
x = self.weight[:, None, None] * x + self.bias[:, None, None]
|
||||
return x
|
||||
|
||||
@@ -0,0 +1,54 @@
|
||||
import torch.nn as nn
|
||||
|
||||
|
||||
def build_act_layer(act_layer):
|
||||
if act_layer == 'ReLU':
|
||||
return nn.ReLU(inplace=True)
|
||||
elif act_layer == 'SiLU':
|
||||
return nn.SiLU(inplace=True)
|
||||
elif act_layer == 'GELU':
|
||||
return nn.GELU()
|
||||
|
||||
raise NotImplementedError(f'build_act_layer does not support {act_layer}')
|
||||
|
||||
|
||||
def build_norm_layer(dim,
|
||||
norm_layer,
|
||||
in_format='channels_last',
|
||||
out_format='channels_last',
|
||||
eps=1e-6):
|
||||
layers = []
|
||||
if norm_layer == 'BN':
|
||||
if in_format == 'channels_last':
|
||||
layers.append(to_channels_first())
|
||||
layers.append(nn.BatchNorm2d(dim))
|
||||
if out_format == 'channels_last':
|
||||
layers.append(to_channels_last())
|
||||
elif norm_layer == 'LN':
|
||||
if in_format == 'channels_first':
|
||||
layers.append(to_channels_last())
|
||||
layers.append(nn.LayerNorm(dim, eps=eps))
|
||||
if out_format == 'channels_first':
|
||||
layers.append(to_channels_first())
|
||||
else:
|
||||
raise NotImplementedError(
|
||||
f'build_norm_layer does not support {norm_layer}')
|
||||
return nn.Sequential(*layers)
|
||||
|
||||
|
||||
class to_channels_first(nn.Module):
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
|
||||
def forward(self, x):
|
||||
return x.permute(0, 3, 1, 2)
|
||||
|
||||
|
||||
class to_channels_last(nn.Module):
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
|
||||
def forward(self, x):
|
||||
return x.permute(0, 2, 3, 1)
|
||||
@@ -0,0 +1,252 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from collections import OrderedDict
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
from torchvision.models import vgg16, vgg16_bn
|
||||
from torchvision.models import resnet50
|
||||
|
||||
from ...config import Config
|
||||
from ...dataset import class_labels_TR_sorted
|
||||
from ..backbones.build_backbone import build_backbone
|
||||
from ..modules.decoder_blocks import BasicDecBlk
|
||||
from ..modules.lateral_blocks import BasicLatBlk
|
||||
from ..refinement.stem_layer import StemLayer
|
||||
|
||||
|
||||
class RefinerPVTInChannels4(nn.Module):
|
||||
def __init__(self, in_channels=3+1):
|
||||
super(RefinerPVTInChannels4, self).__init__()
|
||||
self.config = Config()
|
||||
self.epoch = 1
|
||||
self.bb = build_backbone(self.config.bb, params_settings='in_channels=4')
|
||||
|
||||
lateral_channels_in_collection = {
|
||||
'vgg16': [512, 256, 128, 64], 'vgg16bn': [512, 256, 128, 64], 'resnet50': [1024, 512, 256, 64],
|
||||
'pvt_v2_b2': [512, 320, 128, 64], 'pvt_v2_b5': [512, 320, 128, 64],
|
||||
'swin_v1_b': [1024, 512, 256, 128], 'swin_v1_l': [1536, 768, 384, 192],
|
||||
}
|
||||
channels = lateral_channels_in_collection[self.config.bb]
|
||||
self.squeeze_module = BasicDecBlk(channels[0], channels[0])
|
||||
|
||||
self.decoder = Decoder(channels)
|
||||
|
||||
if 0:
|
||||
for key, value in self.named_parameters():
|
||||
if 'bb.' in key:
|
||||
value.requires_grad = False
|
||||
|
||||
def forward(self, x):
|
||||
if isinstance(x, list):
|
||||
x = torch.cat(x, dim=1)
|
||||
########## Encoder ##########
|
||||
if self.config.bb in ['vgg16', 'vgg16bn', 'resnet50']:
|
||||
x1 = self.bb.conv1(x)
|
||||
x2 = self.bb.conv2(x1)
|
||||
x3 = self.bb.conv3(x2)
|
||||
x4 = self.bb.conv4(x3)
|
||||
else:
|
||||
x1, x2, x3, x4 = self.bb(x)
|
||||
|
||||
x4 = self.squeeze_module(x4)
|
||||
|
||||
########## Decoder ##########
|
||||
|
||||
features = [x, x1, x2, x3, x4]
|
||||
scaled_preds = self.decoder(features)
|
||||
|
||||
return scaled_preds
|
||||
|
||||
|
||||
class Refiner(nn.Module):
|
||||
def __init__(self, in_channels=3+1):
|
||||
super(Refiner, self).__init__()
|
||||
self.config = Config()
|
||||
self.epoch = 1
|
||||
self.stem_layer = StemLayer(in_channels=in_channels, inter_channels=48, out_channels=3, norm_layer='BN' if self.config.batch_size > 1 else 'LN')
|
||||
self.bb = build_backbone(self.config.bb)
|
||||
|
||||
lateral_channels_in_collection = {
|
||||
'vgg16': [512, 256, 128, 64], 'vgg16bn': [512, 256, 128, 64], 'resnet50': [1024, 512, 256, 64],
|
||||
'pvt_v2_b2': [512, 320, 128, 64], 'pvt_v2_b5': [512, 320, 128, 64],
|
||||
'swin_v1_b': [1024, 512, 256, 128], 'swin_v1_l': [1536, 768, 384, 192],
|
||||
}
|
||||
channels = lateral_channels_in_collection[self.config.bb]
|
||||
self.squeeze_module = BasicDecBlk(channels[0], channels[0])
|
||||
|
||||
self.decoder = Decoder(channels)
|
||||
|
||||
if 0:
|
||||
for key, value in self.named_parameters():
|
||||
if 'bb.' in key:
|
||||
value.requires_grad = False
|
||||
|
||||
def forward(self, x):
|
||||
if isinstance(x, list):
|
||||
x = torch.cat(x, dim=1)
|
||||
x = self.stem_layer(x)
|
||||
########## Encoder ##########
|
||||
if self.config.bb in ['vgg16', 'vgg16bn', 'resnet50']:
|
||||
x1 = self.bb.conv1(x)
|
||||
x2 = self.bb.conv2(x1)
|
||||
x3 = self.bb.conv3(x2)
|
||||
x4 = self.bb.conv4(x3)
|
||||
else:
|
||||
x1, x2, x3, x4 = self.bb(x)
|
||||
|
||||
x4 = self.squeeze_module(x4)
|
||||
|
||||
########## Decoder ##########
|
||||
|
||||
features = [x, x1, x2, x3, x4]
|
||||
scaled_preds = self.decoder(features)
|
||||
|
||||
return scaled_preds
|
||||
|
||||
|
||||
class Decoder(nn.Module):
|
||||
def __init__(self, channels):
|
||||
super(Decoder, self).__init__()
|
||||
self.config = Config()
|
||||
DecoderBlock = eval('BasicDecBlk')
|
||||
LateralBlock = eval('BasicLatBlk')
|
||||
|
||||
self.decoder_block4 = DecoderBlock(channels[0], channels[1])
|
||||
self.decoder_block3 = DecoderBlock(channels[1], channels[2])
|
||||
self.decoder_block2 = DecoderBlock(channels[2], channels[3])
|
||||
self.decoder_block1 = DecoderBlock(channels[3], channels[3]//2)
|
||||
|
||||
self.lateral_block4 = LateralBlock(channels[1], channels[1])
|
||||
self.lateral_block3 = LateralBlock(channels[2], channels[2])
|
||||
self.lateral_block2 = LateralBlock(channels[3], channels[3])
|
||||
|
||||
if self.config.ms_supervision:
|
||||
self.conv_ms_spvn_4 = nn.Conv2d(channels[1], 1, 1, 1, 0)
|
||||
self.conv_ms_spvn_3 = nn.Conv2d(channels[2], 1, 1, 1, 0)
|
||||
self.conv_ms_spvn_2 = nn.Conv2d(channels[3], 1, 1, 1, 0)
|
||||
self.conv_out1 = nn.Sequential(nn.Conv2d(channels[3]//2, 1, 1, 1, 0))
|
||||
|
||||
def forward(self, features):
|
||||
x, x1, x2, x3, x4 = features
|
||||
outs = []
|
||||
p4 = self.decoder_block4(x4)
|
||||
_p4 = F.interpolate(p4, size=x3.shape[2:], mode='bilinear', align_corners=True)
|
||||
_p3 = _p4 + self.lateral_block4(x3)
|
||||
|
||||
p3 = self.decoder_block3(_p3)
|
||||
_p3 = F.interpolate(p3, size=x2.shape[2:], mode='bilinear', align_corners=True)
|
||||
_p2 = _p3 + self.lateral_block3(x2)
|
||||
|
||||
p2 = self.decoder_block2(_p2)
|
||||
_p2 = F.interpolate(p2, size=x1.shape[2:], mode='bilinear', align_corners=True)
|
||||
_p1 = _p2 + self.lateral_block2(x1)
|
||||
|
||||
_p1 = self.decoder_block1(_p1)
|
||||
_p1 = F.interpolate(_p1, size=x.shape[2:], mode='bilinear', align_corners=True)
|
||||
p1_out = self.conv_out1(_p1)
|
||||
|
||||
if self.config.ms_supervision:
|
||||
outs.append(self.conv_ms_spvn_4(p4))
|
||||
outs.append(self.conv_ms_spvn_3(p3))
|
||||
outs.append(self.conv_ms_spvn_2(p2))
|
||||
outs.append(p1_out)
|
||||
return outs
|
||||
|
||||
|
||||
class RefUNet(nn.Module):
|
||||
# Refinement
|
||||
def __init__(self, in_channels=3+1):
|
||||
super(RefUNet, self).__init__()
|
||||
self.encoder_1 = nn.Sequential(
|
||||
nn.Conv2d(in_channels, 64, 3, 1, 1),
|
||||
nn.Conv2d(64, 64, 3, 1, 1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True)
|
||||
)
|
||||
|
||||
self.encoder_2 = nn.Sequential(
|
||||
nn.MaxPool2d(2, 2, ceil_mode=True),
|
||||
nn.Conv2d(64, 64, 3, 1, 1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True)
|
||||
)
|
||||
|
||||
self.encoder_3 = nn.Sequential(
|
||||
nn.MaxPool2d(2, 2, ceil_mode=True),
|
||||
nn.Conv2d(64, 64, 3, 1, 1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True)
|
||||
)
|
||||
|
||||
self.encoder_4 = nn.Sequential(
|
||||
nn.MaxPool2d(2, 2, ceil_mode=True),
|
||||
nn.Conv2d(64, 64, 3, 1, 1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True)
|
||||
)
|
||||
|
||||
self.pool4 = nn.MaxPool2d(2, 2, ceil_mode=True)
|
||||
#####
|
||||
self.decoder_5 = nn.Sequential(
|
||||
nn.Conv2d(64, 64, 3, 1, 1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True)
|
||||
)
|
||||
#####
|
||||
self.decoder_4 = nn.Sequential(
|
||||
nn.Conv2d(128, 64, 3, 1, 1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True)
|
||||
)
|
||||
|
||||
self.decoder_3 = nn.Sequential(
|
||||
nn.Conv2d(128, 64, 3, 1, 1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True)
|
||||
)
|
||||
|
||||
self.decoder_2 = nn.Sequential(
|
||||
nn.Conv2d(128, 64, 3, 1, 1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True)
|
||||
)
|
||||
|
||||
self.decoder_1 = nn.Sequential(
|
||||
nn.Conv2d(128, 64, 3, 1, 1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True)
|
||||
)
|
||||
|
||||
self.conv_d0 = nn.Conv2d(64, 1, 3, 1, 1)
|
||||
|
||||
self.upscore2 = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
|
||||
|
||||
def forward(self, x):
|
||||
outs = []
|
||||
if isinstance(x, list):
|
||||
x = torch.cat(x, dim=1)
|
||||
hx = x
|
||||
|
||||
hx1 = self.encoder_1(hx)
|
||||
hx2 = self.encoder_2(hx1)
|
||||
hx3 = self.encoder_3(hx2)
|
||||
hx4 = self.encoder_4(hx3)
|
||||
|
||||
hx = self.decoder_5(self.pool4(hx4))
|
||||
hx = torch.cat((self.upscore2(hx), hx4), 1)
|
||||
|
||||
d4 = self.decoder_4(hx)
|
||||
hx = torch.cat((self.upscore2(d4), hx3), 1)
|
||||
|
||||
d3 = self.decoder_3(hx)
|
||||
hx = torch.cat((self.upscore2(d3), hx2), 1)
|
||||
|
||||
d2 = self.decoder_2(hx)
|
||||
hx = torch.cat((self.upscore2(d2), hx1), 1)
|
||||
|
||||
d1 = self.decoder_1(hx)
|
||||
|
||||
x = self.conv_d0(d1)
|
||||
outs.append(x)
|
||||
return outs
|
||||
@@ -0,0 +1,45 @@
|
||||
import torch.nn as nn
|
||||
from ..modules.utils import build_act_layer, build_norm_layer
|
||||
|
||||
|
||||
class StemLayer(nn.Module):
|
||||
r""" Stem layer of InternImage
|
||||
Args:
|
||||
in_channels (int): number of input channels
|
||||
out_channels (int): number of output channels
|
||||
act_layer (str): activation layer
|
||||
norm_layer (str): normalization layer
|
||||
"""
|
||||
|
||||
def __init__(self,
|
||||
in_channels=3+1,
|
||||
inter_channels=48,
|
||||
out_channels=96,
|
||||
act_layer='GELU',
|
||||
norm_layer='BN'):
|
||||
super().__init__()
|
||||
self.conv1 = nn.Conv2d(in_channels,
|
||||
inter_channels,
|
||||
kernel_size=3,
|
||||
stride=1,
|
||||
padding=1)
|
||||
self.norm1 = build_norm_layer(
|
||||
inter_channels, norm_layer, 'channels_first', 'channels_first'
|
||||
)
|
||||
self.act = build_act_layer(act_layer)
|
||||
self.conv2 = nn.Conv2d(inter_channels,
|
||||
out_channels,
|
||||
kernel_size=3,
|
||||
stride=1,
|
||||
padding=1)
|
||||
self.norm2 = build_norm_layer(
|
||||
out_channels, norm_layer, 'channels_first', 'channels_first'
|
||||
)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.conv1(x)
|
||||
x = self.norm1(x)
|
||||
x = self.act(x)
|
||||
x = self.conv2(x)
|
||||
x = self.norm2(x)
|
||||
return x
|
||||
+100
@@ -0,0 +1,100 @@
|
||||
import logging
|
||||
import os
|
||||
import torch
|
||||
from torchvision import transforms
|
||||
import numpy as np
|
||||
import random
|
||||
import cv2
|
||||
from PIL import Image
|
||||
|
||||
|
||||
def path_to_image(path, size=(1024, 1024), color_type=['rgb', 'gray'][0]):
|
||||
if color_type.lower() == 'rgb':
|
||||
image = cv2.imread(path)
|
||||
elif color_type.lower() == 'gray':
|
||||
image = cv2.imread(path, cv2.IMREAD_GRAYSCALE)
|
||||
else:
|
||||
print('Select the color_type to return, either to RGB or gray image.')
|
||||
return
|
||||
if size:
|
||||
image = cv2.resize(image, size, interpolation=cv2.INTER_LINEAR)
|
||||
if color_type.lower() == 'rgb':
|
||||
image = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB)).convert('RGB')
|
||||
else:
|
||||
image = Image.fromarray(image).convert('L')
|
||||
return image
|
||||
|
||||
|
||||
|
||||
def check_state_dict(state_dict, unwanted_prefixes=['module.', '_orig_mod.']):
|
||||
for k, v in list(state_dict.items()):
|
||||
prefix_length = 0
|
||||
for unwanted_prefix in unwanted_prefixes:
|
||||
if k[prefix_length:].startswith(unwanted_prefix):
|
||||
prefix_length += len(unwanted_prefix)
|
||||
state_dict[k[prefix_length:]] = state_dict.pop(k)
|
||||
return state_dict
|
||||
|
||||
|
||||
def generate_smoothed_gt(gts):
|
||||
epsilon = 0.001
|
||||
new_gts = (1-epsilon)*gts+epsilon/2
|
||||
return new_gts
|
||||
|
||||
|
||||
class Logger():
|
||||
def __init__(self, path="log.txt"):
|
||||
self.logger = logging.getLogger('BiRefNet')
|
||||
self.file_handler = logging.FileHandler(path, "w")
|
||||
self.stdout_handler = logging.StreamHandler()
|
||||
self.stdout_handler.setFormatter(logging.Formatter('%(asctime)s %(levelname)s %(message)s'))
|
||||
self.file_handler.setFormatter(logging.Formatter('%(asctime)s %(levelname)s %(message)s'))
|
||||
self.logger.addHandler(self.file_handler)
|
||||
self.logger.addHandler(self.stdout_handler)
|
||||
self.logger.setLevel(logging.INFO)
|
||||
self.logger.propagate = False
|
||||
|
||||
def info(self, txt):
|
||||
self.logger.info(txt)
|
||||
|
||||
def close(self):
|
||||
self.file_handler.close()
|
||||
self.stdout_handler.close()
|
||||
|
||||
|
||||
class AverageMeter(object):
|
||||
"""Computes and stores the average and current value"""
|
||||
def __init__(self):
|
||||
self.reset()
|
||||
|
||||
def reset(self):
|
||||
self.val = 0.0
|
||||
self.avg = 0.0
|
||||
self.sum = 0.0
|
||||
self.count = 0.0
|
||||
|
||||
def update(self, val, n=1):
|
||||
self.val = val
|
||||
self.sum += val * n
|
||||
self.count += n
|
||||
self.avg = self.sum / self.count
|
||||
|
||||
|
||||
def save_checkpoint(state, path, filename="latest.pth"):
|
||||
torch.save(state, os.path.join(path, filename))
|
||||
|
||||
|
||||
def save_tensor_img(tenor_im, path):
|
||||
im = tenor_im.cpu().clone()
|
||||
im = im.squeeze(0)
|
||||
tensor2pil = transforms.ToPILImage()
|
||||
im = tensor2pil(im)
|
||||
im.save(path)
|
||||
|
||||
|
||||
def set_seed(seed):
|
||||
torch.manual_seed(seed)
|
||||
torch.cuda.manual_seed_all(seed)
|
||||
np.random.seed(seed)
|
||||
random.seed(seed)
|
||||
torch.backends.cudnn.deterministic = True
|
||||
+135
@@ -0,0 +1,135 @@
|
||||
import os
|
||||
import math
|
||||
import torch
|
||||
import folder_paths
|
||||
|
||||
|
||||
class Config:
|
||||
def __init__(self) -> None:
|
||||
self.ms_supervision = True
|
||||
self.out_ref = self.ms_supervision and True
|
||||
self.dec_ipt = True
|
||||
self.dec_ipt_split = True
|
||||
self.locate_head = False
|
||||
self.cxt_num = [0, 3][1] # multi-scale skip connections from encoder
|
||||
self.mul_scl_ipt = ['', 'add', 'cat'][2]
|
||||
self.refine = ['', 'itself', 'RefUNet', 'Refiner', 'RefinerPVTInChannels4'][0]
|
||||
self.progressive_ref = self.refine and True
|
||||
self.ender = self.progressive_ref and False
|
||||
self.scale = self.progressive_ref and 2
|
||||
self.dec_att = ['', 'ASPP', 'ASPPDeformable'][2]
|
||||
self.squeeze_block = ['', 'BasicDecBlk_x1', 'ResBlk_x4', 'ASPP_x3', 'ASPPDeformable_x3'][1]
|
||||
self.dec_blk = ['BasicDecBlk', 'ResBlk', 'HierarAttDecBlk'][0]
|
||||
self.auxiliary_classification = False
|
||||
self.refine_iteration = 1
|
||||
self.freeze_bb = False
|
||||
self.precisionHigh = True
|
||||
self.compile = True
|
||||
self.load_all = True
|
||||
self.verbose_eval = True
|
||||
|
||||
self.size = 1024
|
||||
self.batch_size = 2
|
||||
self.IoU_finetune_last_epochs = [0, -20][1] # choose 0 to skip
|
||||
if self.dec_blk == 'HierarAttDecBlk':
|
||||
self.batch_size = 2 ** [0, 1, 2, 3, 4][2]
|
||||
self.model = [
|
||||
'BiRefNet',
|
||||
][0]
|
||||
|
||||
# Components
|
||||
self.lat_blk = ['BasicLatBlk'][0]
|
||||
self.dec_channels_inter = ['fixed', 'adap'][0]
|
||||
|
||||
# Backbone
|
||||
self.bb = [
|
||||
'vgg16', 'vgg16bn', 'resnet50', # 0, 1, 2
|
||||
'pvt_v2_b2', 'pvt_v2_b5', # 3-bs10, 4-bs5
|
||||
'swin_v1_b', 'swin_v1_l', # 5-bs9, 6-bs6
|
||||
'swin_v1_t', 'swin_v1_s', # 7, 8
|
||||
'pvt_v2_b0', 'pvt_v2_b1', # 9, 10
|
||||
][6]
|
||||
self.lateral_channels_in_collection = {
|
||||
'vgg16': [512, 256, 128, 64], 'vgg16bn': [512, 256, 128, 64], 'resnet50': [1024, 512, 256, 64],
|
||||
'pvt_v2_b2': [512, 320, 128, 64], 'pvt_v2_b5': [512, 320, 128, 64],
|
||||
'swin_v1_b': [1024, 512, 256, 128], 'swin_v1_l': [1536, 768, 384, 192],
|
||||
'swin_v1_t': [768, 384, 192, 96], 'swin_v1_s': [768, 384, 192, 96],
|
||||
'pvt_v2_b0': [256, 160, 64, 32], 'pvt_v2_b1': [512, 320, 128, 64],
|
||||
}[self.bb]
|
||||
if self.mul_scl_ipt == 'cat':
|
||||
self.lateral_channels_in_collection = [channel * 2 for channel in self.lateral_channels_in_collection]
|
||||
self.cxt = self.lateral_channels_in_collection[1:][::-1][-self.cxt_num:] if self.cxt_num else []
|
||||
# self.sys_home_dir = '/root/autodl-tmp'
|
||||
# self.weights_root_dir = os.path.join(self.sys_home_dir, 'weights')
|
||||
# self.weights = {
|
||||
# 'pvt_v2_b2': os.path.join(self.weights_root_dir, 'pvt_v2_b2.pth'),
|
||||
# 'pvt_v2_b5': os.path.join(self.weights_root_dir, ['pvt_v2_b5.pth', 'pvt_v2_b5_22k.pth'][0]),
|
||||
# 'swin_v1_b': os.path.join(self.weights_root_dir, ['swin_base_patch4_window12_384_22kto1k.pth', 'swin_base_patch4_window12_384_22k.pth'][0]),
|
||||
# 'swin_v1_l': os.path.join(self.weights_root_dir, ['swin_large_patch4_window12_384_22kto1k.pth', 'swin_large_patch4_window12_384_22k.pth'][0]),
|
||||
# 'swin_v1_t': os.path.join(self.weights_root_dir, ['swin_tiny_patch4_window7_224_22kto1k_finetune.pth'][0]),
|
||||
# 'swin_v1_s': os.path.join(self.weights_root_dir, ['swin_small_patch4_window7_224_22kto1k_finetune.pth'][0]),
|
||||
# 'pvt_v2_b0': os.path.join(self.weights_root_dir, ['pvt_v2_b0.pth'][0]),
|
||||
# 'pvt_v2_b1': os.path.join(self.weights_root_dir, ['pvt_v2_b1.pth'][0]),
|
||||
# }
|
||||
weight_paths_name = "birefnet"
|
||||
self.weights = {
|
||||
'pvt_v2_b2': folder_paths.get_full_path(weight_paths_name, 'pvt_v2_b2.pth'),
|
||||
'pvt_v2_b5': folder_paths.get_full_path(weight_paths_name, ['pvt_v2_b5.pth', 'pvt_v2_b5_22k.pth'][0]),
|
||||
'swin_v1_b': folder_paths.get_full_path(weight_paths_name, ['swin_base_patch4_window12_384_22kto1k.pth', 'swin_base_patch4_window12_384_22k.pth'][0]),
|
||||
'swin_v1_l': folder_paths.get_full_path(weight_paths_name, ['swin_large_patch4_window12_384_22kto1k.pth', 'swin_large_patch4_window12_384_22k.pth'][0]),
|
||||
'swin_v1_t': folder_paths.get_full_path(weight_paths_name, ['swin_tiny_patch4_window7_224_22kto1k_finetune.pth'][0]),
|
||||
'swin_v1_s': folder_paths.get_full_path(weight_paths_name, ['swin_small_patch4_window7_224_22kto1k_finetune.pth'][0]),
|
||||
'pvt_v2_b0': folder_paths.get_full_path(weight_paths_name, ['pvt_v2_b0.pth'][0]),
|
||||
'pvt_v2_b1': folder_paths.get_full_path(weight_paths_name, ['pvt_v2_b1.pth'][0]),
|
||||
}
|
||||
|
||||
# Training
|
||||
self.num_workers = 5 # will be decrease to min(it, batch_size) at the initialization of the data_loader
|
||||
self.optimizer = ['Adam', 'AdamW'][0]
|
||||
self.lr = 1e-5 * math.sqrt(self.batch_size / 5) # adapt the lr linearly
|
||||
self.lr_decay_epochs = [1e4] # Set to negative N to decay the lr in the last N-th epoch.
|
||||
self.lr_decay_rate = 0.5
|
||||
self.only_S_MAE = False
|
||||
self.SDPA_enabled = False # Bug. Slower and errors occur in multi-GPUs
|
||||
|
||||
# Data
|
||||
# self.data_root_dir = os.path.join(self.sys_home_dir, 'datasets/dis')
|
||||
self.task = ['DIS5K', 'COD', 'HRSOD'][0]
|
||||
self.training_set = {
|
||||
'DIS5K': 'DIS-TR',
|
||||
'COD': 'TR-COD10K+TR-CAMO',
|
||||
'HRSOD': ['TR-DUTS', 'TR-HRSOD+TR-UHRSD', 'TR-DUTS+TR-HRSOD+TR-UHRSD'][1]
|
||||
}[self.task]
|
||||
self.preproc_methods = ['flip', 'enhance', 'rotate', 'pepper', 'crop'][:4]
|
||||
|
||||
# Loss
|
||||
self.lambdas_pix_last = {
|
||||
# not 0 means opening this loss
|
||||
# original rate -- 1 : 30 : 1.5 : 0.2, bce x 30
|
||||
'bce': 30 * 1, # high performance
|
||||
'iou': 0.5 * 1, # 0 / 255
|
||||
'iou_patch': 0.5 * 0, # 0 / 255, win_size = (64, 64)
|
||||
'mse': 150 * 0, # can smooth the saliency map
|
||||
'triplet': 3 * 0,
|
||||
'reg': 100 * 0,
|
||||
'ssim': 10 * 1, # help contours,
|
||||
'cnt': 5 * 0, # help contours
|
||||
}
|
||||
self.lambdas_cls = {
|
||||
'ce': 5.0
|
||||
}
|
||||
# Adv
|
||||
self.lambda_adv_g = 10. * 0 # turn to 0 to avoid adv training
|
||||
self.lambda_adv_d = 3. * (self.lambda_adv_g > 0)
|
||||
|
||||
# others
|
||||
self.device = [0, 'cpu'][0 if torch.cuda.is_available() else 1] # .to(0) == .to('cuda:0')
|
||||
|
||||
self.batch_size_valid = 1
|
||||
self.rand_seed = 7
|
||||
# run_sh_file = [f for f in os.listdir('.') if 'train.sh' == f] + [os.path.join('..', f) for f in os.listdir('..') if 'train.sh' == f]
|
||||
# with open(run_sh_file[0], 'r') as f:
|
||||
# lines = f.readlines()
|
||||
# self.save_last = int([l.strip() for l in lines if 'val_last=' in l][0].split('=')[-1])
|
||||
# self.save_step = int([l.strip() for l in lines if 'step=' in l][0].split('=')[-1])
|
||||
# self.val_step = [0, self.save_step][0]
|
||||
@@ -0,0 +1,94 @@
|
||||
import os
|
||||
# import cv2
|
||||
from tqdm import tqdm
|
||||
from PIL import Image
|
||||
from torch.utils import data
|
||||
from torchvision import transforms
|
||||
|
||||
from birefnet_old.preproc import preproc
|
||||
from birefnet_old.config import Config
|
||||
from birefnet_old.utils import path_to_image
|
||||
|
||||
|
||||
Image.MAX_IMAGE_PIXELS = None # remove DecompressionBombWarning
|
||||
config = Config()
|
||||
_class_labels_TR_sorted = 'Airplane, Ant, Antenna, Archery, Axe, BabyCarriage, Bag, BalanceBeam, Balcony, Balloon, Basket, BasketballHoop, Beatle, Bed, Bee, Bench, Bicycle, BicycleFrame, BicycleStand, Boat, Bonsai, BoomLift, Bridge, BunkBed, Butterfly, Button, Cable, CableLift, Cage, Camcorder, Cannon, Canoe, Car, CarParkDropArm, Carriage, Cart, Caterpillar, CeilingLamp, Centipede, Chair, Clip, Clock, Clothes, CoatHanger, Comb, ConcretePumpTruck, Crack, Crane, Cup, DentalChair, Desk, DeskChair, Diagram, DishRack, DoorHandle, Dragonfish, Dragonfly, Drum, Earphone, Easel, ElectricIron, Excavator, Eyeglasses, Fan, Fence, Fencing, FerrisWheel, FireExtinguisher, Fishing, Flag, FloorLamp, Forklift, GasStation, Gate, Gear, Goal, Golf, GymEquipment, Hammock, Handcart, Handcraft, Handrail, HangGlider, Harp, Harvester, Headset, Helicopter, Helmet, Hook, HorizontalBar, Hydrovalve, IroningTable, Jewelry, Key, KidsPlayground, Kitchenware, Kite, Knife, Ladder, LaundryRack, Lightning, Lobster, Locust, Machine, MachineGun, MagazineRack, Mantis, Medal, MemorialArchway, Microphone, Missile, MobileHolder, Monitor, Mosquito, Motorcycle, MovingTrolley, Mower, MusicPlayer, MusicStand, ObservationTower, Octopus, OilWell, OlympicLogo, OperatingTable, OutdoorFitnessEquipment, Parachute, Pavilion, Piano, Pipe, PlowHarrow, PoleVault, Punchbag, Rack, Racket, Rifle, Ring, Robot, RockClimbing, Rope, Sailboat, Satellite, Scaffold, Scale, Scissor, Scooter, Sculpture, Seadragon, Seahorse, Seal, SewingMachine, Ship, Shoe, ShoppingCart, ShoppingTrolley, Shower, Shrimp, Signboard, Skateboarding, Skeleton, Skiing, Spade, SpeedBoat, Spider, Spoon, Stair, Stand, Stationary, SteeringWheel, Stethoscope, Stool, Stove, StreetLamp, SweetStand, Swing, Sword, TV, Table, TableChair, TableLamp, TableTennis, Tank, Tapeline, Teapot, Telescope, Tent, TobaccoPipe, Toy, Tractor, TrafficLight, TrafficSign, Trampoline, TransmissionTower, Tree, Tricycle, TrimmerCover, Tripod, Trombone, Truck, Trumpet, Tuba, UAV, Umbrella, UnevenBars, UtilityPole, VacuumCleaner, Violin, Wakesurfing, Watch, WaterTower, WateringPot, Well, WellLid, Wheel, Wheelchair, WindTurbine, Windmill, WineGlass, WireWhisk, Yacht'
|
||||
class_labels_TR_sorted = _class_labels_TR_sorted.split(', ')
|
||||
|
||||
|
||||
class MyData(data.Dataset):
|
||||
def __init__(self, datasets, image_size, is_train=True):
|
||||
self.size_train = image_size
|
||||
self.size_test = image_size
|
||||
self.keep_size = not config.size
|
||||
self.data_size = (config.size, config.size)
|
||||
self.is_train = is_train
|
||||
self.load_all = config.load_all
|
||||
self.device = config.device
|
||||
if self.is_train and config.auxiliary_classification:
|
||||
self.cls_name2id = {_name: _id for _id, _name in enumerate(class_labels_TR_sorted)}
|
||||
self.transform_image = transforms.Compose([
|
||||
transforms.Resize(self.data_size),
|
||||
transforms.ToTensor(),
|
||||
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
|
||||
][self.load_all or self.keep_size:])
|
||||
self.transform_label = transforms.Compose([
|
||||
transforms.Resize(self.data_size),
|
||||
transforms.ToTensor(),
|
||||
][self.load_all or self.keep_size:])
|
||||
dataset_root = os.path.join(config.data_root_dir, config.task)
|
||||
# datasets can be a list of different datasets for training on combined sets.
|
||||
self.image_paths = []
|
||||
for dataset in datasets.split('+'):
|
||||
image_root = os.path.join(dataset_root, dataset, 'im')
|
||||
self.image_paths += [os.path.join(image_root, p) for p in os.listdir(image_root)]
|
||||
self.label_paths = []
|
||||
for p in self.image_paths:
|
||||
for ext in ['.png', '.jpg', '.PNG', '.JPG', '.JPEG']:
|
||||
## 'im' and 'gt' may need modifying
|
||||
p_gt = p.replace('/im/', '/gt/').replace('.'+p.split('.')[-1], ext)
|
||||
if os.path.exists(p_gt):
|
||||
self.label_paths.append(p_gt)
|
||||
break
|
||||
if self.load_all:
|
||||
self.images_loaded, self.labels_loaded = [], []
|
||||
self.class_labels_loaded = []
|
||||
# for image_path, label_path in zip(self.image_paths, self.label_paths):
|
||||
for image_path, label_path in tqdm(zip(self.image_paths, self.label_paths), total=len(self.image_paths)):
|
||||
_image = path_to_image(image_path, size=(config.size, config.size), color_type='rgb')
|
||||
_label = path_to_image(label_path, size=(config.size, config.size), color_type='gray')
|
||||
self.images_loaded.append(_image)
|
||||
self.labels_loaded.append(_label)
|
||||
self.class_labels_loaded.append(
|
||||
self.cls_name2id[label_path.split('/')[-1].split('#')[3]] if self.is_train and config.auxiliary_classification else -1
|
||||
)
|
||||
|
||||
|
||||
def __getitem__(self, index):
|
||||
|
||||
if self.load_all:
|
||||
image = self.images_loaded[index]
|
||||
label = self.labels_loaded[index]
|
||||
class_label = self.class_labels_loaded[index] if self.is_train and config.auxiliary_classification else -1
|
||||
else:
|
||||
image = path_to_image(self.image_paths[index], size=(config.size, config.size), color_type='rgb')
|
||||
label = path_to_image(self.label_paths[index], size=(config.size, config.size), color_type='gray')
|
||||
class_label = self.cls_name2id[self.label_paths[index].split('/')[-1].split('#')[3]] if self.is_train and config.auxiliary_classification else -1
|
||||
|
||||
# loading image and label
|
||||
if self.is_train:
|
||||
image, label = preproc(image, label, preproc_methods=config.preproc_methods)
|
||||
# else:
|
||||
# if _label.shape[0] > 2048 or _label.shape[1] > 2048:
|
||||
# _image = cv2.resize(_image, (2048, 2048), interpolation=cv2.INTER_LINEAR)
|
||||
# _label = cv2.resize(_label, (2048, 2048), interpolation=cv2.INTER_LINEAR)
|
||||
|
||||
image, label = self.transform_image(image), self.transform_label(label)
|
||||
|
||||
if self.is_train:
|
||||
return image, label, class_label
|
||||
else:
|
||||
return image, label, self.label_paths[index]
|
||||
|
||||
def __len__(self):
|
||||
return len(self.image_paths)
|
||||
@@ -0,0 +1,44 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from collections import OrderedDict
|
||||
from torchvision.models import vgg16, vgg16_bn, VGG16_Weights, VGG16_BN_Weights, resnet50, ResNet50_Weights
|
||||
from ..backbones.pvt_v2 import pvt_v2_b0, pvt_v2_b1, pvt_v2_b2, pvt_v2_b5
|
||||
from ..backbones.swin_v1 import swin_v1_t, swin_v1_s, swin_v1_b, swin_v1_l
|
||||
from ...config import Config
|
||||
|
||||
|
||||
config = Config()
|
||||
|
||||
def build_backbone(bb_name, pretrained=True, params_settings=''):
|
||||
if bb_name == 'vgg16':
|
||||
bb_net = list(vgg16(pretrained=VGG16_Weights.DEFAULT if pretrained else None).children())[0]
|
||||
bb = nn.Sequential(OrderedDict({'conv1': bb_net[:4], 'conv2': bb_net[4:9], 'conv3': bb_net[9:16], 'conv4': bb_net[16:23]}))
|
||||
elif bb_name == 'vgg16bn':
|
||||
bb_net = list(vgg16_bn(pretrained=VGG16_BN_Weights.DEFAULT if pretrained else None).children())[0]
|
||||
bb = nn.Sequential(OrderedDict({'conv1': bb_net[:6], 'conv2': bb_net[6:13], 'conv3': bb_net[13:23], 'conv4': bb_net[23:33]}))
|
||||
elif bb_name == 'resnet50':
|
||||
bb_net = list(resnet50(pretrained=ResNet50_Weights.DEFAULT if pretrained else None).children())
|
||||
bb = nn.Sequential(OrderedDict({'conv1': nn.Sequential(*bb_net[0:3]), 'conv2': bb_net[4], 'conv3': bb_net[5], 'conv4': bb_net[6]}))
|
||||
else:
|
||||
bb = eval('{}({})'.format(bb_name, params_settings))
|
||||
if pretrained:
|
||||
bb = load_weights(bb, bb_name)
|
||||
return bb
|
||||
|
||||
def load_weights(model, model_name):
|
||||
save_model = torch.load(config.weights[model_name])
|
||||
model_dict = model.state_dict()
|
||||
state_dict = {k: v if v.size() == model_dict[k].size() else model_dict[k] for k, v in save_model.items() if k in model_dict.keys()}
|
||||
# to ignore the weights with mismatched size when I modify the backbone itself.
|
||||
if not state_dict:
|
||||
save_model_keys = list(save_model.keys())
|
||||
sub_item = save_model_keys[0] if len(save_model_keys) == 1 else None
|
||||
state_dict = {k: v if v.size() == model_dict[k].size() else model_dict[k] for k, v in save_model[sub_item].items() if k in model_dict.keys()}
|
||||
if not state_dict or not sub_item:
|
||||
print('Weights are not successully loaded. Check the state dict of weights file.')
|
||||
return None
|
||||
else:
|
||||
print('Found correct weights in the "{}" item of loaded state_dict.'.format(sub_item))
|
||||
model_dict.update(state_dict)
|
||||
model.load_state_dict(model_dict)
|
||||
return model
|
||||
@@ -0,0 +1,438 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from functools import partial
|
||||
|
||||
try:
|
||||
# version > 0.6.13
|
||||
from timm.layers import DropPath, to_2tuple, trunc_normal_
|
||||
except Exception:
|
||||
from timm.models.layers import DropPath, to_2tuple, trunc_normal_
|
||||
|
||||
import math
|
||||
|
||||
from ...config import Config
|
||||
|
||||
config = Config()
|
||||
|
||||
class Mlp(nn.Module):
|
||||
def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
|
||||
super().__init__()
|
||||
out_features = out_features or in_features
|
||||
hidden_features = hidden_features or in_features
|
||||
self.fc1 = nn.Linear(in_features, hidden_features)
|
||||
self.dwconv = DWConv(hidden_features)
|
||||
self.act = act_layer()
|
||||
self.fc2 = nn.Linear(hidden_features, out_features)
|
||||
self.drop = nn.Dropout(drop)
|
||||
|
||||
self.apply(self._init_weights)
|
||||
|
||||
def _init_weights(self, m):
|
||||
if isinstance(m, nn.Linear):
|
||||
trunc_normal_(m.weight, std=.02)
|
||||
if isinstance(m, nn.Linear) and m.bias is not None:
|
||||
nn.init.constant_(m.bias, 0)
|
||||
elif isinstance(m, nn.LayerNorm):
|
||||
nn.init.constant_(m.bias, 0)
|
||||
nn.init.constant_(m.weight, 1.0)
|
||||
elif isinstance(m, nn.Conv2d):
|
||||
fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
|
||||
fan_out //= m.groups
|
||||
m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
|
||||
if m.bias is not None:
|
||||
m.bias.data.zero_()
|
||||
|
||||
def forward(self, x, H, W):
|
||||
x = self.fc1(x)
|
||||
x = self.dwconv(x, H, W)
|
||||
x = self.act(x)
|
||||
x = self.drop(x)
|
||||
x = self.fc2(x)
|
||||
x = self.drop(x)
|
||||
return x
|
||||
|
||||
|
||||
class Attention(nn.Module):
|
||||
def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0., sr_ratio=1):
|
||||
super().__init__()
|
||||
assert dim % num_heads == 0, f"dim {dim} should be divided by num_heads {num_heads}."
|
||||
|
||||
self.dim = dim
|
||||
self.num_heads = num_heads
|
||||
head_dim = dim // num_heads
|
||||
self.scale = qk_scale or head_dim ** -0.5
|
||||
|
||||
self.q = nn.Linear(dim, dim, bias=qkv_bias)
|
||||
self.kv = nn.Linear(dim, dim * 2, bias=qkv_bias)
|
||||
self.attn_drop_prob = attn_drop
|
||||
self.attn_drop = nn.Dropout(attn_drop)
|
||||
self.proj = nn.Linear(dim, dim)
|
||||
self.proj_drop = nn.Dropout(proj_drop)
|
||||
|
||||
self.sr_ratio = sr_ratio
|
||||
if sr_ratio > 1:
|
||||
self.sr = nn.Conv2d(dim, dim, kernel_size=sr_ratio, stride=sr_ratio)
|
||||
self.norm = nn.LayerNorm(dim)
|
||||
|
||||
self.apply(self._init_weights)
|
||||
|
||||
def _init_weights(self, m):
|
||||
if isinstance(m, nn.Linear):
|
||||
trunc_normal_(m.weight, std=.02)
|
||||
if isinstance(m, nn.Linear) and m.bias is not None:
|
||||
nn.init.constant_(m.bias, 0)
|
||||
elif isinstance(m, nn.LayerNorm):
|
||||
nn.init.constant_(m.bias, 0)
|
||||
nn.init.constant_(m.weight, 1.0)
|
||||
elif isinstance(m, nn.Conv2d):
|
||||
fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
|
||||
fan_out //= m.groups
|
||||
m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
|
||||
if m.bias is not None:
|
||||
m.bias.data.zero_()
|
||||
|
||||
def forward(self, x, H, W):
|
||||
B, N, C = x.shape
|
||||
q = self.q(x).reshape(B, N, self.num_heads, C // self.num_heads).permute(0, 2, 1, 3)
|
||||
|
||||
if self.sr_ratio > 1:
|
||||
x_ = x.permute(0, 2, 1).reshape(B, C, H, W)
|
||||
x_ = self.sr(x_).reshape(B, C, -1).permute(0, 2, 1)
|
||||
x_ = self.norm(x_)
|
||||
kv = self.kv(x_).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
|
||||
else:
|
||||
kv = self.kv(x).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
|
||||
k, v = kv[0], kv[1]
|
||||
|
||||
if config.SDPA_enabled:
|
||||
x = torch.nn.functional.scaled_dot_product_attention(
|
||||
q, k, v,
|
||||
attn_mask=None, dropout_p=self.attn_drop_prob, is_causal=False
|
||||
).transpose(1, 2).reshape(B, N, C)
|
||||
else:
|
||||
attn = (q @ k.transpose(-2, -1)) * self.scale
|
||||
attn = attn.softmax(dim=-1)
|
||||
attn = self.attn_drop(attn)
|
||||
|
||||
x = (attn @ v).transpose(1, 2).reshape(B, N, C)
|
||||
x = self.proj(x)
|
||||
x = self.proj_drop(x)
|
||||
|
||||
return x
|
||||
|
||||
|
||||
class Block(nn.Module):
|
||||
|
||||
def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0.,
|
||||
drop_path=0., act_layer=nn.GELU, norm_layer=nn.LayerNorm, sr_ratio=1):
|
||||
super().__init__()
|
||||
self.norm1 = norm_layer(dim)
|
||||
self.attn = Attention(
|
||||
dim,
|
||||
num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale,
|
||||
attn_drop=attn_drop, proj_drop=drop, sr_ratio=sr_ratio)
|
||||
# NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
|
||||
self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
|
||||
self.norm2 = norm_layer(dim)
|
||||
mlp_hidden_dim = int(dim * mlp_ratio)
|
||||
self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
|
||||
|
||||
self.apply(self._init_weights)
|
||||
|
||||
def _init_weights(self, m):
|
||||
if isinstance(m, nn.Linear):
|
||||
trunc_normal_(m.weight, std=.02)
|
||||
if isinstance(m, nn.Linear) and m.bias is not None:
|
||||
nn.init.constant_(m.bias, 0)
|
||||
elif isinstance(m, nn.LayerNorm):
|
||||
nn.init.constant_(m.bias, 0)
|
||||
nn.init.constant_(m.weight, 1.0)
|
||||
elif isinstance(m, nn.Conv2d):
|
||||
fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
|
||||
fan_out //= m.groups
|
||||
m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
|
||||
if m.bias is not None:
|
||||
m.bias.data.zero_()
|
||||
|
||||
def forward(self, x, H, W):
|
||||
x = x + self.drop_path(self.attn(self.norm1(x), H, W))
|
||||
x = x + self.drop_path(self.mlp(self.norm2(x), H, W))
|
||||
|
||||
return x
|
||||
|
||||
|
||||
class OverlapPatchEmbed(nn.Module):
|
||||
""" Image to Patch Embedding
|
||||
"""
|
||||
|
||||
def __init__(self, img_size=224, patch_size=7, stride=4, in_channels=3, embed_dim=768):
|
||||
super().__init__()
|
||||
img_size = to_2tuple(img_size)
|
||||
patch_size = to_2tuple(patch_size)
|
||||
|
||||
self.img_size = img_size
|
||||
self.patch_size = patch_size
|
||||
self.H, self.W = img_size[0] // patch_size[0], img_size[1] // patch_size[1]
|
||||
self.num_patches = self.H * self.W
|
||||
self.proj = nn.Conv2d(in_channels, embed_dim, kernel_size=patch_size, stride=stride,
|
||||
padding=(patch_size[0] // 2, patch_size[1] // 2))
|
||||
self.norm = nn.LayerNorm(embed_dim)
|
||||
|
||||
self.apply(self._init_weights)
|
||||
|
||||
def _init_weights(self, m):
|
||||
if isinstance(m, nn.Linear):
|
||||
trunc_normal_(m.weight, std=.02)
|
||||
if isinstance(m, nn.Linear) and m.bias is not None:
|
||||
nn.init.constant_(m.bias, 0)
|
||||
elif isinstance(m, nn.LayerNorm):
|
||||
nn.init.constant_(m.bias, 0)
|
||||
nn.init.constant_(m.weight, 1.0)
|
||||
elif isinstance(m, nn.Conv2d):
|
||||
fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
|
||||
fan_out //= m.groups
|
||||
m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
|
||||
if m.bias is not None:
|
||||
m.bias.data.zero_()
|
||||
|
||||
def forward(self, x):
|
||||
x = self.proj(x)
|
||||
_, _, H, W = x.shape
|
||||
x = x.flatten(2).transpose(1, 2)
|
||||
x = self.norm(x)
|
||||
|
||||
return x, H, W
|
||||
|
||||
|
||||
class PyramidVisionTransformerImpr(nn.Module):
|
||||
def __init__(self, img_size=224, patch_size=16, in_channels=3, num_classes=1000, embed_dims=[64, 128, 256, 512],
|
||||
num_heads=[1, 2, 4, 8], mlp_ratios=[4, 4, 4, 4], qkv_bias=False, qk_scale=None, drop_rate=0.,
|
||||
attn_drop_rate=0., drop_path_rate=0., norm_layer=nn.LayerNorm,
|
||||
depths=[3, 4, 6, 3], sr_ratios=[8, 4, 2, 1]):
|
||||
super().__init__()
|
||||
self.num_classes = num_classes
|
||||
self.depths = depths
|
||||
|
||||
# patch_embed
|
||||
self.patch_embed1 = OverlapPatchEmbed(img_size=img_size, patch_size=7, stride=4, in_channels=in_channels,
|
||||
embed_dim=embed_dims[0])
|
||||
self.patch_embed2 = OverlapPatchEmbed(img_size=img_size // 4, patch_size=3, stride=2, in_channels=embed_dims[0],
|
||||
embed_dim=embed_dims[1])
|
||||
self.patch_embed3 = OverlapPatchEmbed(img_size=img_size // 8, patch_size=3, stride=2, in_channels=embed_dims[1],
|
||||
embed_dim=embed_dims[2])
|
||||
self.patch_embed4 = OverlapPatchEmbed(img_size=img_size // 16, patch_size=3, stride=2, in_channels=embed_dims[2],
|
||||
embed_dim=embed_dims[3])
|
||||
|
||||
# transformer encoder
|
||||
dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))] # stochastic depth decay rule
|
||||
cur = 0
|
||||
self.block1 = nn.ModuleList([Block(
|
||||
dim=embed_dims[0], num_heads=num_heads[0], mlp_ratio=mlp_ratios[0], qkv_bias=qkv_bias, qk_scale=qk_scale,
|
||||
drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,
|
||||
sr_ratio=sr_ratios[0])
|
||||
for i in range(depths[0])])
|
||||
self.norm1 = norm_layer(embed_dims[0])
|
||||
|
||||
cur += depths[0]
|
||||
self.block2 = nn.ModuleList([Block(
|
||||
dim=embed_dims[1], num_heads=num_heads[1], mlp_ratio=mlp_ratios[1], qkv_bias=qkv_bias, qk_scale=qk_scale,
|
||||
drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,
|
||||
sr_ratio=sr_ratios[1])
|
||||
for i in range(depths[1])])
|
||||
self.norm2 = norm_layer(embed_dims[1])
|
||||
|
||||
cur += depths[1]
|
||||
self.block3 = nn.ModuleList([Block(
|
||||
dim=embed_dims[2], num_heads=num_heads[2], mlp_ratio=mlp_ratios[2], qkv_bias=qkv_bias, qk_scale=qk_scale,
|
||||
drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,
|
||||
sr_ratio=sr_ratios[2])
|
||||
for i in range(depths[2])])
|
||||
self.norm3 = norm_layer(embed_dims[2])
|
||||
|
||||
cur += depths[2]
|
||||
self.block4 = nn.ModuleList([Block(
|
||||
dim=embed_dims[3], num_heads=num_heads[3], mlp_ratio=mlp_ratios[3], qkv_bias=qkv_bias, qk_scale=qk_scale,
|
||||
drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,
|
||||
sr_ratio=sr_ratios[3])
|
||||
for i in range(depths[3])])
|
||||
self.norm4 = norm_layer(embed_dims[3])
|
||||
|
||||
# classification head
|
||||
# self.head = nn.Linear(embed_dims[3], num_classes) if num_classes > 0 else nn.Identity()
|
||||
|
||||
self.apply(self._init_weights)
|
||||
|
||||
def _init_weights(self, m):
|
||||
if isinstance(m, nn.Linear):
|
||||
trunc_normal_(m.weight, std=.02)
|
||||
if isinstance(m, nn.Linear) and m.bias is not None:
|
||||
nn.init.constant_(m.bias, 0)
|
||||
elif isinstance(m, nn.LayerNorm):
|
||||
nn.init.constant_(m.bias, 0)
|
||||
nn.init.constant_(m.weight, 1.0)
|
||||
elif isinstance(m, nn.Conv2d):
|
||||
fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
|
||||
fan_out //= m.groups
|
||||
m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
|
||||
if m.bias is not None:
|
||||
m.bias.data.zero_()
|
||||
|
||||
def init_weights(self, pretrained=None):
|
||||
if isinstance(pretrained, str):
|
||||
logger = 1
|
||||
#load_checkpoint(self, pretrained, map_location='cpu', strict=False, logger=logger)
|
||||
|
||||
def reset_drop_path(self, drop_path_rate):
|
||||
dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(self.depths))]
|
||||
cur = 0
|
||||
for i in range(self.depths[0]):
|
||||
self.block1[i].drop_path.drop_prob = dpr[cur + i]
|
||||
|
||||
cur += self.depths[0]
|
||||
for i in range(self.depths[1]):
|
||||
self.block2[i].drop_path.drop_prob = dpr[cur + i]
|
||||
|
||||
cur += self.depths[1]
|
||||
for i in range(self.depths[2]):
|
||||
self.block3[i].drop_path.drop_prob = dpr[cur + i]
|
||||
|
||||
cur += self.depths[2]
|
||||
for i in range(self.depths[3]):
|
||||
self.block4[i].drop_path.drop_prob = dpr[cur + i]
|
||||
|
||||
def freeze_patch_emb(self):
|
||||
self.patch_embed1.requires_grad = False
|
||||
|
||||
@torch.jit.ignore
|
||||
def no_weight_decay(self):
|
||||
return {'pos_embed1', 'pos_embed2', 'pos_embed3', 'pos_embed4', 'cls_token'} # has pos_embed may be better
|
||||
|
||||
def get_classifier(self):
|
||||
return self.head
|
||||
|
||||
def reset_classifier(self, num_classes, global_pool=''):
|
||||
self.num_classes = num_classes
|
||||
self.head = nn.Linear(self.embed_dim, num_classes) if num_classes > 0 else nn.Identity()
|
||||
|
||||
def forward_features(self, x):
|
||||
B = x.shape[0]
|
||||
outs = []
|
||||
|
||||
# stage 1
|
||||
x, H, W = self.patch_embed1(x)
|
||||
for i, blk in enumerate(self.block1):
|
||||
x = blk(x, H, W)
|
||||
x = self.norm1(x)
|
||||
x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
|
||||
outs.append(x)
|
||||
|
||||
# stage 2
|
||||
x, H, W = self.patch_embed2(x)
|
||||
for i, blk in enumerate(self.block2):
|
||||
x = blk(x, H, W)
|
||||
x = self.norm2(x)
|
||||
x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
|
||||
outs.append(x)
|
||||
|
||||
# stage 3
|
||||
x, H, W = self.patch_embed3(x)
|
||||
for i, blk in enumerate(self.block3):
|
||||
x = blk(x, H, W)
|
||||
x = self.norm3(x)
|
||||
x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
|
||||
outs.append(x)
|
||||
|
||||
# stage 4
|
||||
x, H, W = self.patch_embed4(x)
|
||||
for i, blk in enumerate(self.block4):
|
||||
x = blk(x, H, W)
|
||||
x = self.norm4(x)
|
||||
x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
|
||||
outs.append(x)
|
||||
|
||||
return outs
|
||||
|
||||
# return x.mean(dim=1)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.forward_features(x)
|
||||
# x = self.head(x)
|
||||
|
||||
return x
|
||||
|
||||
|
||||
class DWConv(nn.Module):
|
||||
def __init__(self, dim=768):
|
||||
super(DWConv, self).__init__()
|
||||
self.dwconv = nn.Conv2d(dim, dim, 3, 1, 1, bias=True, groups=dim)
|
||||
|
||||
def forward(self, x, H, W):
|
||||
B, N, C = x.shape
|
||||
x = x.transpose(1, 2).view(B, C, H, W).contiguous()
|
||||
x = self.dwconv(x)
|
||||
x = x.flatten(2).transpose(1, 2)
|
||||
|
||||
return x
|
||||
|
||||
|
||||
def _conv_filter(state_dict, patch_size=16):
|
||||
""" convert patch embedding weight from manual patchify + linear proj to conv"""
|
||||
out_dict = {}
|
||||
for k, v in state_dict.items():
|
||||
if 'patch_embed.proj.weight' in k:
|
||||
v = v.reshape((v.shape[0], 3, patch_size, patch_size))
|
||||
out_dict[k] = v
|
||||
|
||||
return out_dict
|
||||
|
||||
|
||||
## @register_model
|
||||
class pvt_v2_b0(PyramidVisionTransformerImpr):
|
||||
def __init__(self, **kwargs):
|
||||
super(pvt_v2_b0, self).__init__(
|
||||
patch_size=4, embed_dims=[32, 64, 160, 256], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
|
||||
qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[2, 2, 2, 2], sr_ratios=[8, 4, 2, 1],
|
||||
drop_rate=0.0, drop_path_rate=0.1)
|
||||
|
||||
|
||||
|
||||
## @register_model
|
||||
class pvt_v2_b1(PyramidVisionTransformerImpr):
|
||||
def __init__(self, **kwargs):
|
||||
super(pvt_v2_b1, self).__init__(
|
||||
patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
|
||||
qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[2, 2, 2, 2], sr_ratios=[8, 4, 2, 1],
|
||||
drop_rate=0.0, drop_path_rate=0.1)
|
||||
|
||||
## @register_model
|
||||
class pvt_v2_b2(PyramidVisionTransformerImpr):
|
||||
def __init__(self, in_channels=3, **kwargs):
|
||||
super(pvt_v2_b2, self).__init__(
|
||||
patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
|
||||
qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 4, 6, 3], sr_ratios=[8, 4, 2, 1],
|
||||
drop_rate=0.0, drop_path_rate=0.1, in_channels=in_channels)
|
||||
|
||||
## @register_model
|
||||
class pvt_v2_b3(PyramidVisionTransformerImpr):
|
||||
def __init__(self, **kwargs):
|
||||
super(pvt_v2_b3, self).__init__(
|
||||
patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
|
||||
qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 4, 18, 3], sr_ratios=[8, 4, 2, 1],
|
||||
drop_rate=0.0, drop_path_rate=0.1)
|
||||
|
||||
## @register_model
|
||||
class pvt_v2_b4(PyramidVisionTransformerImpr):
|
||||
def __init__(self, **kwargs):
|
||||
super(pvt_v2_b4, self).__init__(
|
||||
patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
|
||||
qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 8, 27, 3], sr_ratios=[8, 4, 2, 1],
|
||||
drop_rate=0.0, drop_path_rate=0.1)
|
||||
|
||||
|
||||
## @register_model
|
||||
class pvt_v2_b5(PyramidVisionTransformerImpr):
|
||||
def __init__(self, **kwargs):
|
||||
super(pvt_v2_b5, self).__init__(
|
||||
patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[4, 4, 4, 4],
|
||||
qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 6, 40, 3], sr_ratios=[8, 4, 2, 1],
|
||||
drop_rate=0.0, drop_path_rate=0.1)
|
||||
@@ -0,0 +1,657 @@
|
||||
# --------------------------------------------------------
|
||||
# Swin Transformer
|
||||
# Copyright (c) 2021 Microsoft
|
||||
# Licensed under The MIT License [see LICENSE for details]
|
||||
# Written by Ze Liu, Yutong Lin, Yixuan Wei
|
||||
# --------------------------------------------------------
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
import torch.utils.checkpoint as checkpoint
|
||||
import numpy as np
|
||||
try:
|
||||
# version > 0.6.13
|
||||
from timm.layers import DropPath, to_2tuple, trunc_normal_
|
||||
except Exception:
|
||||
from timm.models.layers import DropPath, to_2tuple, trunc_normal_
|
||||
|
||||
from ...config import Config
|
||||
|
||||
|
||||
config = Config()
|
||||
|
||||
class Mlp(nn.Module):
|
||||
""" Multilayer perceptron."""
|
||||
|
||||
def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
|
||||
super().__init__()
|
||||
out_features = out_features or in_features
|
||||
hidden_features = hidden_features or in_features
|
||||
self.fc1 = nn.Linear(in_features, hidden_features)
|
||||
self.act = act_layer()
|
||||
self.fc2 = nn.Linear(hidden_features, out_features)
|
||||
self.drop = nn.Dropout(drop)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.fc1(x)
|
||||
x = self.act(x)
|
||||
x = self.drop(x)
|
||||
x = self.fc2(x)
|
||||
x = self.drop(x)
|
||||
return x
|
||||
|
||||
|
||||
def window_partition(x, window_size):
|
||||
"""
|
||||
Args:
|
||||
x: (B, H, W, C)
|
||||
window_size (int): window size
|
||||
|
||||
Returns:
|
||||
windows: (num_windows*B, window_size, window_size, C)
|
||||
"""
|
||||
B, H, W, C = x.shape
|
||||
x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)
|
||||
windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
|
||||
return windows
|
||||
|
||||
|
||||
def window_reverse(windows, window_size, H, W):
|
||||
"""
|
||||
Args:
|
||||
windows: (num_windows*B, window_size, window_size, C)
|
||||
window_size (int): Window size
|
||||
H (int): Height of image
|
||||
W (int): Width of image
|
||||
|
||||
Returns:
|
||||
x: (B, H, W, C)
|
||||
"""
|
||||
B = int(windows.shape[0] / (H * W / window_size / window_size))
|
||||
x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)
|
||||
x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)
|
||||
return x
|
||||
|
||||
|
||||
class WindowAttention(nn.Module):
|
||||
""" Window based multi-head self attention (W-MSA) module with relative position bias.
|
||||
It supports both of shifted and non-shifted window.
|
||||
|
||||
Args:
|
||||
dim (int): Number of input channels.
|
||||
window_size (tuple[int]): The height and width of the window.
|
||||
num_heads (int): Number of attention heads.
|
||||
qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
|
||||
qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set
|
||||
attn_drop (float, optional): Dropout ratio of attention weight. Default: 0.0
|
||||
proj_drop (float, optional): Dropout ratio of output. Default: 0.0
|
||||
"""
|
||||
|
||||
def __init__(self, dim, window_size, num_heads, qkv_bias=True, qk_scale=None, attn_drop=0., proj_drop=0.):
|
||||
|
||||
super().__init__()
|
||||
self.dim = dim
|
||||
self.window_size = window_size # Wh, Ww
|
||||
self.num_heads = num_heads
|
||||
head_dim = dim // num_heads
|
||||
self.scale = qk_scale or head_dim ** -0.5
|
||||
|
||||
# define a parameter table of relative position bias
|
||||
self.relative_position_bias_table = nn.Parameter(
|
||||
torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1), num_heads)) # 2*Wh-1 * 2*Ww-1, nH
|
||||
|
||||
# get pair-wise relative position index for each token inside the window
|
||||
coords_h = torch.arange(self.window_size[0])
|
||||
coords_w = torch.arange(self.window_size[1])
|
||||
coords = torch.stack(torch.meshgrid([coords_h, coords_w], indexing='ij')) # 2, Wh, Ww
|
||||
coords_flatten = torch.flatten(coords, 1) # 2, Wh*Ww
|
||||
relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :] # 2, Wh*Ww, Wh*Ww
|
||||
relative_coords = relative_coords.permute(1, 2, 0).contiguous() # Wh*Ww, Wh*Ww, 2
|
||||
relative_coords[:, :, 0] += self.window_size[0] - 1 # shift to start from 0
|
||||
relative_coords[:, :, 1] += self.window_size[1] - 1
|
||||
relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1
|
||||
relative_position_index = relative_coords.sum(-1) # Wh*Ww, Wh*Ww
|
||||
self.register_buffer("relative_position_index", relative_position_index)
|
||||
|
||||
self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
|
||||
self.attn_drop_prob = attn_drop
|
||||
self.attn_drop = nn.Dropout(attn_drop)
|
||||
self.proj = nn.Linear(dim, dim)
|
||||
self.proj_drop = nn.Dropout(proj_drop)
|
||||
|
||||
trunc_normal_(self.relative_position_bias_table, std=.02)
|
||||
self.softmax = nn.Softmax(dim=-1)
|
||||
|
||||
def forward(self, x, mask=None):
|
||||
""" Forward function.
|
||||
|
||||
Args:
|
||||
x: input features with shape of (num_windows*B, N, C)
|
||||
mask: (0/-inf) mask with shape of (num_windows, Wh*Ww, Wh*Ww) or None
|
||||
"""
|
||||
B_, N, C = x.shape
|
||||
qkv = self.qkv(x).reshape(B_, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
|
||||
q, k, v = qkv[0], qkv[1], qkv[2] # make torchscript happy (cannot use tensor as tuple)
|
||||
|
||||
q = q * self.scale
|
||||
|
||||
if config.SDPA_enabled:
|
||||
x = torch.nn.functional.scaled_dot_product_attention(
|
||||
q, k, v,
|
||||
attn_mask=None, dropout_p=self.attn_drop_prob, is_causal=False
|
||||
).transpose(1, 2).reshape(B_, N, C)
|
||||
else:
|
||||
attn = (q @ k.transpose(-2, -1))
|
||||
|
||||
relative_position_bias = self.relative_position_bias_table[self.relative_position_index.view(-1)].view(
|
||||
self.window_size[0] * self.window_size[1], self.window_size[0] * self.window_size[1], -1) # Wh*Ww,Wh*Ww,nH
|
||||
relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous() # nH, Wh*Ww, Wh*Ww
|
||||
attn = attn + relative_position_bias.unsqueeze(0)
|
||||
|
||||
if mask is not None:
|
||||
nW = mask.shape[0]
|
||||
attn = attn.view(B_ // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0)
|
||||
attn = attn.view(-1, self.num_heads, N, N)
|
||||
attn = self.softmax(attn)
|
||||
else:
|
||||
attn = self.softmax(attn)
|
||||
|
||||
attn = self.attn_drop(attn)
|
||||
|
||||
x = (attn @ v).transpose(1, 2).reshape(B_, N, C)
|
||||
x = self.proj(x)
|
||||
x = self.proj_drop(x)
|
||||
return x
|
||||
|
||||
|
||||
class SwinTransformerBlock(nn.Module):
|
||||
""" Swin Transformer Block.
|
||||
|
||||
Args:
|
||||
dim (int): Number of input channels.
|
||||
num_heads (int): Number of attention heads.
|
||||
window_size (int): Window size.
|
||||
shift_size (int): Shift size for SW-MSA.
|
||||
mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
|
||||
qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
|
||||
qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
|
||||
drop (float, optional): Dropout rate. Default: 0.0
|
||||
attn_drop (float, optional): Attention dropout rate. Default: 0.0
|
||||
drop_path (float, optional): Stochastic depth rate. Default: 0.0
|
||||
act_layer (nn.Module, optional): Activation layer. Default: nn.GELU
|
||||
norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm
|
||||
"""
|
||||
|
||||
def __init__(self, dim, num_heads, window_size=7, shift_size=0,
|
||||
mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0., drop_path=0.,
|
||||
act_layer=nn.GELU, norm_layer=nn.LayerNorm):
|
||||
super().__init__()
|
||||
self.dim = dim
|
||||
self.num_heads = num_heads
|
||||
self.window_size = window_size
|
||||
self.shift_size = shift_size
|
||||
self.mlp_ratio = mlp_ratio
|
||||
assert 0 <= self.shift_size < self.window_size, "shift_size must in 0-window_size"
|
||||
|
||||
self.norm1 = norm_layer(dim)
|
||||
self.attn = WindowAttention(
|
||||
dim, window_size=to_2tuple(self.window_size), num_heads=num_heads,
|
||||
qkv_bias=qkv_bias, qk_scale=qk_scale, attn_drop=attn_drop, proj_drop=drop)
|
||||
|
||||
self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
|
||||
self.norm2 = norm_layer(dim)
|
||||
mlp_hidden_dim = int(dim * mlp_ratio)
|
||||
self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
|
||||
|
||||
self.H = None
|
||||
self.W = None
|
||||
|
||||
def forward(self, x, mask_matrix):
|
||||
""" Forward function.
|
||||
|
||||
Args:
|
||||
x: Input feature, tensor size (B, H*W, C).
|
||||
H, W: Spatial resolution of the input feature.
|
||||
mask_matrix: Attention mask for cyclic shift.
|
||||
"""
|
||||
B, L, C = x.shape
|
||||
H, W = self.H, self.W
|
||||
assert L == H * W, "input feature has wrong size"
|
||||
|
||||
shortcut = x
|
||||
x = self.norm1(x)
|
||||
x = x.view(B, H, W, C)
|
||||
|
||||
# pad feature maps to multiples of window size
|
||||
pad_l = pad_t = 0
|
||||
pad_r = (self.window_size - W % self.window_size) % self.window_size
|
||||
pad_b = (self.window_size - H % self.window_size) % self.window_size
|
||||
x = F.pad(x, (0, 0, pad_l, pad_r, pad_t, pad_b))
|
||||
_, Hp, Wp, _ = x.shape
|
||||
|
||||
# cyclic shift
|
||||
if self.shift_size > 0:
|
||||
shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))
|
||||
attn_mask = mask_matrix
|
||||
else:
|
||||
shifted_x = x
|
||||
attn_mask = None
|
||||
|
||||
# partition windows
|
||||
x_windows = window_partition(shifted_x, self.window_size) # nW*B, window_size, window_size, C
|
||||
x_windows = x_windows.view(-1, self.window_size * self.window_size, C) # nW*B, window_size*window_size, C
|
||||
|
||||
# W-MSA/SW-MSA
|
||||
attn_windows = self.attn(x_windows, mask=attn_mask) # nW*B, window_size*window_size, C
|
||||
|
||||
# merge windows
|
||||
attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)
|
||||
shifted_x = window_reverse(attn_windows, self.window_size, Hp, Wp) # B H' W' C
|
||||
|
||||
# reverse cyclic shift
|
||||
if self.shift_size > 0:
|
||||
x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2))
|
||||
else:
|
||||
x = shifted_x
|
||||
|
||||
if pad_r > 0 or pad_b > 0:
|
||||
x = x[:, :H, :W, :].contiguous()
|
||||
|
||||
x = x.view(B, H * W, C)
|
||||
|
||||
# FFN
|
||||
x = shortcut + self.drop_path(x)
|
||||
x = x + self.drop_path(self.mlp(self.norm2(x)))
|
||||
|
||||
return x
|
||||
|
||||
|
||||
class PatchMerging(nn.Module):
|
||||
""" Patch Merging Layer
|
||||
|
||||
Args:
|
||||
dim (int): Number of input channels.
|
||||
norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm
|
||||
"""
|
||||
def __init__(self, dim, norm_layer=nn.LayerNorm):
|
||||
super().__init__()
|
||||
self.dim = dim
|
||||
self.reduction = nn.Linear(4 * dim, 2 * dim, bias=False)
|
||||
self.norm = norm_layer(4 * dim)
|
||||
|
||||
def forward(self, x, H, W):
|
||||
""" Forward function.
|
||||
|
||||
Args:
|
||||
x: Input feature, tensor size (B, H*W, C).
|
||||
H, W: Spatial resolution of the input feature.
|
||||
"""
|
||||
B, L, C = x.shape
|
||||
assert L == H * W, "input feature has wrong size"
|
||||
|
||||
x = x.view(B, H, W, C)
|
||||
|
||||
# padding
|
||||
pad_input = (H % 2 == 1) or (W % 2 == 1)
|
||||
if pad_input:
|
||||
x = F.pad(x, (0, 0, 0, W % 2, 0, H % 2))
|
||||
|
||||
x0 = x[:, 0::2, 0::2, :] # B H/2 W/2 C
|
||||
x1 = x[:, 1::2, 0::2, :] # B H/2 W/2 C
|
||||
x2 = x[:, 0::2, 1::2, :] # B H/2 W/2 C
|
||||
x3 = x[:, 1::2, 1::2, :] # B H/2 W/2 C
|
||||
x = torch.cat([x0, x1, x2, x3], -1) # B H/2 W/2 4*C
|
||||
x = x.view(B, -1, 4 * C) # B H/2*W/2 4*C
|
||||
|
||||
x = self.norm(x)
|
||||
x = self.reduction(x)
|
||||
|
||||
return x
|
||||
|
||||
|
||||
class BasicLayer(nn.Module):
|
||||
""" A basic Swin Transformer layer for one stage.
|
||||
|
||||
Args:
|
||||
dim (int): Number of feature channels
|
||||
depth (int): Depths of this stage.
|
||||
num_heads (int): Number of attention head.
|
||||
window_size (int): Local window size. Default: 7.
|
||||
mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. Default: 4.
|
||||
qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
|
||||
qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
|
||||
drop (float, optional): Dropout rate. Default: 0.0
|
||||
attn_drop (float, optional): Attention dropout rate. Default: 0.0
|
||||
drop_path (float | tuple[float], optional): Stochastic depth rate. Default: 0.0
|
||||
norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm
|
||||
downsample (nn.Module | None, optional): Downsample layer at the end of the layer. Default: None
|
||||
use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
|
||||
"""
|
||||
|
||||
def __init__(self,
|
||||
dim,
|
||||
depth,
|
||||
num_heads,
|
||||
window_size=7,
|
||||
mlp_ratio=4.,
|
||||
qkv_bias=True,
|
||||
qk_scale=None,
|
||||
drop=0.,
|
||||
attn_drop=0.,
|
||||
drop_path=0.,
|
||||
norm_layer=nn.LayerNorm,
|
||||
downsample=None,
|
||||
use_checkpoint=False):
|
||||
super().__init__()
|
||||
self.window_size = window_size
|
||||
self.shift_size = window_size // 2
|
||||
self.depth = depth
|
||||
self.use_checkpoint = use_checkpoint
|
||||
|
||||
# build blocks
|
||||
self.blocks = nn.ModuleList([
|
||||
SwinTransformerBlock(
|
||||
dim=dim,
|
||||
num_heads=num_heads,
|
||||
window_size=window_size,
|
||||
shift_size=0 if (i % 2 == 0) else window_size // 2,
|
||||
mlp_ratio=mlp_ratio,
|
||||
qkv_bias=qkv_bias,
|
||||
qk_scale=qk_scale,
|
||||
drop=drop,
|
||||
attn_drop=attn_drop,
|
||||
drop_path=drop_path[i] if isinstance(drop_path, list) else drop_path,
|
||||
norm_layer=norm_layer)
|
||||
for i in range(depth)])
|
||||
|
||||
# patch merging layer
|
||||
if downsample is not None:
|
||||
self.downsample = downsample(dim=dim, norm_layer=norm_layer)
|
||||
else:
|
||||
self.downsample = None
|
||||
|
||||
def forward(self, x, H, W):
|
||||
""" Forward function.
|
||||
|
||||
Args:
|
||||
x: Input feature, tensor size (B, H*W, C).
|
||||
H, W: Spatial resolution of the input feature.
|
||||
"""
|
||||
|
||||
# calculate attention mask for SW-MSA
|
||||
# Turn int to torch.tensor for the compatiability with torch.compile in PyTorch 2.5.
|
||||
Hp = torch.ceil(torch.tensor(H) / self.window_size).to(torch.int64) * self.window_size
|
||||
Wp = torch.ceil(torch.tensor(W) / self.window_size).to(torch.int64) * self.window_size
|
||||
img_mask = torch.zeros((1, Hp, Wp, 1), device=x.device) # 1 Hp Wp 1
|
||||
h_slices = (slice(0, -self.window_size),
|
||||
slice(-self.window_size, -self.shift_size),
|
||||
slice(-self.shift_size, None))
|
||||
w_slices = (slice(0, -self.window_size),
|
||||
slice(-self.window_size, -self.shift_size),
|
||||
slice(-self.shift_size, None))
|
||||
cnt = 0
|
||||
for h in h_slices:
|
||||
for w in w_slices:
|
||||
img_mask[:, h, w, :] = cnt
|
||||
cnt += 1
|
||||
|
||||
mask_windows = window_partition(img_mask, self.window_size) # nW, window_size, window_size, 1
|
||||
mask_windows = mask_windows.view(-1, self.window_size * self.window_size)
|
||||
attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)
|
||||
attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))
|
||||
|
||||
for blk in self.blocks:
|
||||
blk.H, blk.W = H, W
|
||||
if self.use_checkpoint:
|
||||
x = checkpoint.checkpoint(blk, x, attn_mask)
|
||||
else:
|
||||
x = blk(x, attn_mask)
|
||||
if self.downsample is not None:
|
||||
x_down = self.downsample(x, H, W)
|
||||
Wh, Ww = (H + 1) // 2, (W + 1) // 2
|
||||
return x, H, W, x_down, Wh, Ww
|
||||
else:
|
||||
return x, H, W, x, H, W
|
||||
|
||||
|
||||
class PatchEmbed(nn.Module):
|
||||
""" Image to Patch Embedding
|
||||
|
||||
Args:
|
||||
patch_size (int): Patch token size. Default: 4.
|
||||
in_channels (int): Number of input image channels. Default: 3.
|
||||
embed_dim (int): Number of linear projection output channels. Default: 96.
|
||||
norm_layer (nn.Module, optional): Normalization layer. Default: None
|
||||
"""
|
||||
|
||||
def __init__(self, patch_size=4, in_channels=3, embed_dim=96, norm_layer=None):
|
||||
super().__init__()
|
||||
patch_size = to_2tuple(patch_size)
|
||||
self.patch_size = patch_size
|
||||
|
||||
self.in_channels = in_channels
|
||||
self.embed_dim = embed_dim
|
||||
|
||||
self.proj = nn.Conv2d(in_channels, embed_dim, kernel_size=patch_size, stride=patch_size)
|
||||
if norm_layer is not None:
|
||||
self.norm = norm_layer(embed_dim)
|
||||
else:
|
||||
self.norm = None
|
||||
|
||||
def forward(self, x):
|
||||
"""Forward function."""
|
||||
# padding
|
||||
_, _, H, W = x.size()
|
||||
if W % self.patch_size[1] != 0:
|
||||
x = F.pad(x, (0, self.patch_size[1] - W % self.patch_size[1]))
|
||||
if H % self.patch_size[0] != 0:
|
||||
x = F.pad(x, (0, 0, 0, self.patch_size[0] - H % self.patch_size[0]))
|
||||
|
||||
x = self.proj(x) # B C Wh Ww
|
||||
if self.norm is not None:
|
||||
Wh, Ww = x.size(2), x.size(3)
|
||||
x = x.flatten(2).transpose(1, 2)
|
||||
x = self.norm(x)
|
||||
x = x.transpose(1, 2).view(-1, self.embed_dim, Wh, Ww)
|
||||
|
||||
return x
|
||||
|
||||
|
||||
class SwinTransformer(nn.Module):
|
||||
""" Swin Transformer backbone.
|
||||
A PyTorch impl of : `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows` -
|
||||
https://arxiv.org/pdf/2103.14030
|
||||
|
||||
Args:
|
||||
pretrain_img_size (int): Input image size for training the pretrained model,
|
||||
used in absolute postion embedding. Default 224.
|
||||
patch_size (int | tuple(int)): Patch size. Default: 4.
|
||||
in_channels (int): Number of input image channels. Default: 3.
|
||||
embed_dim (int): Number of linear projection output channels. Default: 96.
|
||||
depths (tuple[int]): Depths of each Swin Transformer stage.
|
||||
num_heads (tuple[int]): Number of attention head of each stage.
|
||||
window_size (int): Window size. Default: 7.
|
||||
mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. Default: 4.
|
||||
qkv_bias (bool): If True, add a learnable bias to query, key, value. Default: True
|
||||
qk_scale (float): Override default qk scale of head_dim ** -0.5 if set.
|
||||
drop_rate (float): Dropout rate.
|
||||
attn_drop_rate (float): Attention dropout rate. Default: 0.
|
||||
drop_path_rate (float): Stochastic depth rate. Default: 0.2.
|
||||
norm_layer (nn.Module): Normalization layer. Default: nn.LayerNorm.
|
||||
ape (bool): If True, add absolute position embedding to the patch embedding. Default: False.
|
||||
patch_norm (bool): If True, add normalization after patch embedding. Default: True.
|
||||
out_indices (Sequence[int]): Output from which stages.
|
||||
frozen_stages (int): Stages to be frozen (stop grad and set eval mode).
|
||||
-1 means not freezing any parameters.
|
||||
use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
|
||||
"""
|
||||
|
||||
def __init__(self,
|
||||
pretrain_img_size=224,
|
||||
patch_size=4,
|
||||
in_channels=3,
|
||||
embed_dim=96,
|
||||
depths=[2, 2, 6, 2],
|
||||
num_heads=[3, 6, 12, 24],
|
||||
window_size=7,
|
||||
mlp_ratio=4.,
|
||||
qkv_bias=True,
|
||||
qk_scale=None,
|
||||
drop_rate=0.,
|
||||
attn_drop_rate=0.,
|
||||
drop_path_rate=0.2,
|
||||
norm_layer=nn.LayerNorm,
|
||||
ape=False,
|
||||
patch_norm=True,
|
||||
out_indices=(0, 1, 2, 3),
|
||||
frozen_stages=-1,
|
||||
use_checkpoint=False):
|
||||
super().__init__()
|
||||
|
||||
self.pretrain_img_size = pretrain_img_size
|
||||
self.num_layers = len(depths)
|
||||
self.embed_dim = embed_dim
|
||||
self.ape = ape
|
||||
self.patch_norm = patch_norm
|
||||
self.out_indices = out_indices
|
||||
self.frozen_stages = frozen_stages
|
||||
|
||||
# split image into non-overlapping patches
|
||||
self.patch_embed = PatchEmbed(
|
||||
patch_size=patch_size, in_channels=in_channels, embed_dim=embed_dim,
|
||||
norm_layer=norm_layer if self.patch_norm else None)
|
||||
|
||||
# absolute position embedding
|
||||
if self.ape:
|
||||
pretrain_img_size = to_2tuple(pretrain_img_size)
|
||||
patch_size = to_2tuple(patch_size)
|
||||
patches_resolution = [pretrain_img_size[0] // patch_size[0], pretrain_img_size[1] // patch_size[1]]
|
||||
|
||||
self.absolute_pos_embed = nn.Parameter(torch.zeros(1, embed_dim, patches_resolution[0], patches_resolution[1]))
|
||||
trunc_normal_(self.absolute_pos_embed, std=.02)
|
||||
|
||||
self.pos_drop = nn.Dropout(p=drop_rate)
|
||||
|
||||
# stochastic depth
|
||||
dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))] # stochastic depth decay rule
|
||||
|
||||
# build layers
|
||||
self.layers = nn.ModuleList()
|
||||
for i_layer in range(self.num_layers):
|
||||
layer = BasicLayer(
|
||||
dim=int(embed_dim * 2 ** i_layer),
|
||||
depth=depths[i_layer],
|
||||
num_heads=num_heads[i_layer],
|
||||
window_size=window_size,
|
||||
mlp_ratio=mlp_ratio,
|
||||
qkv_bias=qkv_bias,
|
||||
qk_scale=qk_scale,
|
||||
drop=drop_rate,
|
||||
attn_drop=attn_drop_rate,
|
||||
drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])],
|
||||
norm_layer=norm_layer,
|
||||
downsample=PatchMerging if (i_layer < self.num_layers - 1) else None,
|
||||
use_checkpoint=use_checkpoint)
|
||||
self.layers.append(layer)
|
||||
|
||||
num_features = [int(embed_dim * 2 ** i) for i in range(self.num_layers)]
|
||||
self.num_features = num_features
|
||||
|
||||
# add a norm layer for each output
|
||||
for i_layer in out_indices:
|
||||
layer = norm_layer(num_features[i_layer])
|
||||
layer_name = f'norm{i_layer}'
|
||||
self.add_module(layer_name, layer)
|
||||
|
||||
self._freeze_stages()
|
||||
|
||||
def _freeze_stages(self):
|
||||
if self.frozen_stages >= 0:
|
||||
self.patch_embed.eval()
|
||||
for param in self.patch_embed.parameters():
|
||||
param.requires_grad = False
|
||||
|
||||
if self.frozen_stages >= 1 and self.ape:
|
||||
self.absolute_pos_embed.requires_grad = False
|
||||
|
||||
if self.frozen_stages >= 2:
|
||||
self.pos_drop.eval()
|
||||
for i in range(0, self.frozen_stages - 1):
|
||||
m = self.layers[i]
|
||||
m.eval()
|
||||
for param in m.parameters():
|
||||
param.requires_grad = False
|
||||
|
||||
# def init_weights(self, pretrained=None):
|
||||
# """Initialize the weights in backbone.
|
||||
#
|
||||
# Args:
|
||||
# pretrained (str, optional): Path to pre-trained weights.
|
||||
# Defaults to None.
|
||||
# """
|
||||
#
|
||||
# def _init_weights(m):
|
||||
# if isinstance(m, nn.Linear):
|
||||
# trunc_normal_(m.weight, std=.02)
|
||||
# if isinstance(m, nn.Linear) and m.bias is not None:
|
||||
# nn.init.constant_(m.bias, 0)
|
||||
# elif isinstance(m, nn.LayerNorm):
|
||||
# nn.init.constant_(m.bias, 0)
|
||||
# nn.init.constant_(m.weight, 1.0)
|
||||
#
|
||||
# if isinstance(pretrained, str):
|
||||
# self.apply(_init_weights)
|
||||
# logger = get_root_logger()
|
||||
# load_checkpoint(self, pretrained, strict=False, logger=logger)
|
||||
# elif pretrained is None:
|
||||
# self.apply(_init_weights)
|
||||
# else:
|
||||
# raise TypeError('pretrained must be a str or None')
|
||||
|
||||
def forward(self, x):
|
||||
"""Forward function."""
|
||||
x = self.patch_embed(x)
|
||||
|
||||
Wh, Ww = x.size(2), x.size(3)
|
||||
if self.ape:
|
||||
# interpolate the position embedding to the corresponding size
|
||||
absolute_pos_embed = F.interpolate(self.absolute_pos_embed, size=(Wh, Ww), mode='bicubic')
|
||||
x = (x + absolute_pos_embed) # B Wh*Ww C
|
||||
|
||||
outs = []#x.contiguous()]
|
||||
x = x.flatten(2).transpose(1, 2)
|
||||
x = self.pos_drop(x)
|
||||
for i in range(self.num_layers):
|
||||
layer = self.layers[i]
|
||||
x_out, H, W, x, Wh, Ww = layer(x, Wh, Ww)
|
||||
|
||||
if i in self.out_indices:
|
||||
norm_layer = getattr(self, f'norm{i}')
|
||||
x_out = norm_layer(x_out)
|
||||
|
||||
out = x_out.view(-1, H, W, self.num_features[i]).permute(0, 3, 1, 2).contiguous()
|
||||
outs.append(out)
|
||||
|
||||
return tuple(outs)
|
||||
|
||||
def train(self, mode=True):
|
||||
"""Convert the model into training mode while keep layers freezed."""
|
||||
super(SwinTransformer, self).train(mode)
|
||||
self._freeze_stages()
|
||||
|
||||
def swin_v1_t():
|
||||
model = SwinTransformer(embed_dim=96, depths=[2, 2, 6, 2], num_heads=[3, 6, 12, 24], window_size=7)
|
||||
return model
|
||||
|
||||
def swin_v1_s():
|
||||
model = SwinTransformer(embed_dim=96, depths=[2, 2, 18, 2], num_heads=[3, 6, 12, 24], window_size=7)
|
||||
return model
|
||||
|
||||
def swin_v1_b():
|
||||
model = SwinTransformer(embed_dim=128, depths=[2, 2, 18, 2], num_heads=[4, 8, 16, 32], window_size=12)
|
||||
return model
|
||||
|
||||
def swin_v1_l():
|
||||
model = SwinTransformer(embed_dim=192, depths=[2, 2, 18, 2], num_heads=[6, 12, 24, 48], window_size=12)
|
||||
return model
|
||||
@@ -0,0 +1,291 @@
|
||||
# import torch
|
||||
# import torch.nn as nn
|
||||
from collections import OrderedDict
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
from torchvision.models import vgg16, vgg16_bn
|
||||
from torchvision.models import resnet50
|
||||
from kornia.filters import laplacian
|
||||
|
||||
from ..config import Config
|
||||
from ..dataset import class_labels_TR_sorted
|
||||
from .backbones.build_backbone import build_backbone
|
||||
from .modules.decoder_blocks import BasicDecBlk, ResBlk, HierarAttDecBlk
|
||||
from .modules.lateral_blocks import BasicLatBlk
|
||||
from .modules.aspp import ASPP, ASPPDeformable
|
||||
from .modules.ing import *
|
||||
from .refinement.refiner import Refiner, RefinerPVTInChannels4, RefUNet
|
||||
from .refinement.stem_layer import StemLayer
|
||||
|
||||
|
||||
class BiRefNet(nn.Module):
|
||||
def __init__(self, bb_pretrained=True):
|
||||
super(BiRefNet, self).__init__()
|
||||
self.config = Config()
|
||||
self.epoch = 1
|
||||
self.bb = build_backbone(self.config.bb, pretrained=bb_pretrained)
|
||||
|
||||
channels = self.config.lateral_channels_in_collection
|
||||
|
||||
if self.config.auxiliary_classification:
|
||||
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
|
||||
self.cls_head = nn.Sequential(
|
||||
nn.Linear(channels[0], len(class_labels_TR_sorted))
|
||||
)
|
||||
|
||||
if self.config.squeeze_block:
|
||||
self.squeeze_module = nn.Sequential(*[
|
||||
eval(self.config.squeeze_block.split('_x')[0])(channels[0]+sum(self.config.cxt), channels[0])
|
||||
for _ in range(eval(self.config.squeeze_block.split('_x')[1]))
|
||||
])
|
||||
|
||||
self.decoder = Decoder(channels)
|
||||
|
||||
if self.config.locate_head:
|
||||
self.locate_header = nn.ModuleList([
|
||||
BasicDecBlk(channels[0], channels[-1]),
|
||||
nn.Sequential(
|
||||
nn.Conv2d(channels[-1], 1, 1, 1, 0),
|
||||
)
|
||||
])
|
||||
|
||||
if self.config.ender:
|
||||
self.dec_end = nn.Sequential(
|
||||
nn.Conv2d(1, 16, 3, 1, 1),
|
||||
nn.Conv2d(16, 1, 3, 1, 1),
|
||||
nn.ReLU(inplace=True),
|
||||
)
|
||||
|
||||
# refine patch-level segmentation
|
||||
if self.config.refine:
|
||||
if self.config.refine == 'itself':
|
||||
self.stem_layer = StemLayer(in_channels=3+1, inter_channels=48, out_channels=3)
|
||||
else:
|
||||
self.refiner = eval('{}({})'.format(self.config.refine, 'in_channels=3+1'))
|
||||
|
||||
if self.config.freeze_bb:
|
||||
# Freeze the backbone...
|
||||
print(self.named_parameters())
|
||||
for key, value in self.named_parameters():
|
||||
if 'bb.' in key and 'refiner.' not in key:
|
||||
value.requires_grad = False
|
||||
|
||||
def forward_enc(self, x):
|
||||
if self.config.bb in ['vgg16', 'vgg16bn', 'resnet50']:
|
||||
x1 = self.bb.conv1(x); x2 = self.bb.conv2(x1); x3 = self.bb.conv3(x2); x4 = self.bb.conv4(x3)
|
||||
else:
|
||||
x1, x2, x3, x4 = self.bb(x)
|
||||
if self.config.mul_scl_ipt == 'cat':
|
||||
B, C, H, W = x.shape
|
||||
x1_, x2_, x3_, x4_ = self.bb(F.interpolate(x, size=(H//2, W//2), mode='bilinear', align_corners=True))
|
||||
x1 = torch.cat([x1, F.interpolate(x1_, size=x1.shape[2:], mode='bilinear', align_corners=True)], dim=1)
|
||||
x2 = torch.cat([x2, F.interpolate(x2_, size=x2.shape[2:], mode='bilinear', align_corners=True)], dim=1)
|
||||
x3 = torch.cat([x3, F.interpolate(x3_, size=x3.shape[2:], mode='bilinear', align_corners=True)], dim=1)
|
||||
x4 = torch.cat([x4, F.interpolate(x4_, size=x4.shape[2:], mode='bilinear', align_corners=True)], dim=1)
|
||||
elif self.config.mul_scl_ipt == 'add':
|
||||
B, C, H, W = x.shape
|
||||
x1_, x2_, x3_, x4_ = self.bb(F.interpolate(x, size=(H//2, W//2), mode='bilinear', align_corners=True))
|
||||
x1 = x1 + F.interpolate(x1_, size=x1.shape[2:], mode='bilinear', align_corners=True)
|
||||
x2 = x2 + F.interpolate(x2_, size=x2.shape[2:], mode='bilinear', align_corners=True)
|
||||
x3 = x3 + F.interpolate(x3_, size=x3.shape[2:], mode='bilinear', align_corners=True)
|
||||
x4 = x4 + F.interpolate(x4_, size=x4.shape[2:], mode='bilinear', align_corners=True)
|
||||
class_preds = self.cls_head(self.avgpool(x4).view(x4.shape[0], -1)) if self.training and self.config.auxiliary_classification else None
|
||||
if self.config.cxt:
|
||||
x4 = torch.cat(
|
||||
(
|
||||
*[
|
||||
F.interpolate(x1, size=x4.shape[2:], mode='bilinear', align_corners=True),
|
||||
F.interpolate(x2, size=x4.shape[2:], mode='bilinear', align_corners=True),
|
||||
F.interpolate(x3, size=x4.shape[2:], mode='bilinear', align_corners=True),
|
||||
][-len(self.config.cxt):],
|
||||
x4
|
||||
),
|
||||
dim=1
|
||||
)
|
||||
return (x1, x2, x3, x4), class_preds
|
||||
|
||||
def forward_ori(self, x):
|
||||
########## Encoder ##########
|
||||
(x1, x2, x3, x4), class_preds = self.forward_enc(x)
|
||||
if self.config.squeeze_block:
|
||||
x4 = self.squeeze_module(x4)
|
||||
########## Decoder ##########
|
||||
features = [x, x1, x2, x3, x4]
|
||||
if self.config.out_ref:
|
||||
features.append(laplacian(torch.mean(x, dim=1).unsqueeze(1), kernel_size=5))
|
||||
scaled_preds = self.decoder(features)
|
||||
return scaled_preds, class_preds
|
||||
|
||||
def forward_ref(self, x, pred):
|
||||
# refine patch-level segmentation
|
||||
if pred.shape[2:] != x.shape[2:]:
|
||||
pred = F.interpolate(pred, size=x.shape[2:], mode='bilinear', align_corners=True)
|
||||
# pred = pred.sigmoid()
|
||||
if self.config.refine == 'itself':
|
||||
x = self.stem_layer(torch.cat([x, pred], dim=1))
|
||||
scaled_preds, class_preds = self.forward_ori(x)
|
||||
else:
|
||||
scaled_preds = self.refiner([x, pred])
|
||||
class_preds = None
|
||||
return scaled_preds, class_preds
|
||||
|
||||
def forward_ref_end(self, x):
|
||||
# remove the grids of concatenated preds
|
||||
return self.dec_end(x) if self.config.ender else x
|
||||
|
||||
|
||||
def forward(self, x):
|
||||
scaled_preds, class_preds = self.forward_ori(x)
|
||||
class_preds_lst = [class_preds]
|
||||
return [scaled_preds, class_preds_lst] if self.training else scaled_preds
|
||||
|
||||
|
||||
class Decoder(nn.Module):
|
||||
def __init__(self, channels):
|
||||
super(Decoder, self).__init__()
|
||||
self.config = Config()
|
||||
DecoderBlock = eval(self.config.dec_blk)
|
||||
LateralBlock = eval(self.config.lat_blk)
|
||||
|
||||
if self.config.dec_ipt:
|
||||
self.split = self.config.dec_ipt_split
|
||||
N_dec_ipt = 64
|
||||
DBlock = SimpleConvs
|
||||
ic = 64
|
||||
ipt_cha_opt = 1
|
||||
self.ipt_blk4 = DBlock(2**8*3 if self.split else 3, [N_dec_ipt, channels[0]//8][ipt_cha_opt], inter_channels=ic)
|
||||
self.ipt_blk3 = DBlock(2**6*3 if self.split else 3, [N_dec_ipt, channels[1]//8][ipt_cha_opt], inter_channels=ic)
|
||||
self.ipt_blk2 = DBlock(2**4*3 if self.split else 3, [N_dec_ipt, channels[2]//8][ipt_cha_opt], inter_channels=ic)
|
||||
self.ipt_blk1 = DBlock(2**0*3 if self.split else 3, [N_dec_ipt, channels[3]//8][ipt_cha_opt], inter_channels=ic)
|
||||
else:
|
||||
self.split = None
|
||||
|
||||
self.decoder_block4 = DecoderBlock(channels[0], channels[1])
|
||||
self.decoder_block3 = DecoderBlock(channels[1]+([N_dec_ipt, channels[0]//8][ipt_cha_opt] if self.config.dec_ipt else 0), channels[2])
|
||||
self.decoder_block2 = DecoderBlock(channels[2]+([N_dec_ipt, channels[1]//8][ipt_cha_opt] if self.config.dec_ipt else 0), channels[3])
|
||||
self.decoder_block1 = DecoderBlock(channels[3]+([N_dec_ipt, channels[2]//8][ipt_cha_opt] if self.config.dec_ipt else 0), channels[3]//2)
|
||||
self.conv_out1 = nn.Sequential(nn.Conv2d(channels[3]//2+([N_dec_ipt, channels[3]//8][ipt_cha_opt] if self.config.dec_ipt else 0), 1, 1, 1, 0))
|
||||
|
||||
self.lateral_block4 = LateralBlock(channels[1], channels[1])
|
||||
self.lateral_block3 = LateralBlock(channels[2], channels[2])
|
||||
self.lateral_block2 = LateralBlock(channels[3], channels[3])
|
||||
|
||||
if self.config.ms_supervision:
|
||||
self.conv_ms_spvn_4 = nn.Conv2d(channels[1], 1, 1, 1, 0)
|
||||
self.conv_ms_spvn_3 = nn.Conv2d(channels[2], 1, 1, 1, 0)
|
||||
self.conv_ms_spvn_2 = nn.Conv2d(channels[3], 1, 1, 1, 0)
|
||||
|
||||
if self.config.out_ref:
|
||||
_N = 16
|
||||
# self.gdt_convs_4 = nn.Sequential(nn.Conv2d(channels[1], _N, 3, 1, 1), nn.BatchNorm2d(_N), nn.ReLU(inplace=True))
|
||||
self.gdt_convs_3 = nn.Sequential(nn.Conv2d(channels[2], _N, 3, 1, 1), nn.BatchNorm2d(_N), nn.ReLU(inplace=True))
|
||||
self.gdt_convs_2 = nn.Sequential(nn.Conv2d(channels[3], _N, 3, 1, 1), nn.BatchNorm2d(_N), nn.ReLU(inplace=True))
|
||||
|
||||
# self.gdt_convs_pred_4 = nn.Sequential(nn.Conv2d(_N, 1, 1, 1, 0))
|
||||
self.gdt_convs_pred_3 = nn.Sequential(nn.Conv2d(_N, 1, 1, 1, 0))
|
||||
self.gdt_convs_pred_2 = nn.Sequential(nn.Conv2d(_N, 1, 1, 1, 0))
|
||||
|
||||
# self.gdt_convs_attn_4 = nn.Sequential(nn.Conv2d(_N, 1, 1, 1, 0))
|
||||
self.gdt_convs_attn_3 = nn.Sequential(nn.Conv2d(_N, 1, 1, 1, 0))
|
||||
self.gdt_convs_attn_2 = nn.Sequential(nn.Conv2d(_N, 1, 1, 1, 0))
|
||||
|
||||
|
||||
def get_patches_batch(self, x, p):
|
||||
_size_h, _size_w = p.shape[2:]
|
||||
patches_batch = []
|
||||
for idx in range(x.shape[0]):
|
||||
columns_x = torch.split(x[idx], split_size_or_sections=_size_w, dim=-1)
|
||||
patches_x = []
|
||||
for column_x in columns_x:
|
||||
patches_x += [p.unsqueeze(0) for p in torch.split(column_x, split_size_or_sections=_size_h, dim=-2)]
|
||||
patch_sample = torch.cat(patches_x, dim=1)
|
||||
patches_batch.append(patch_sample)
|
||||
return torch.cat(patches_batch, dim=0)
|
||||
|
||||
def forward(self, features):
|
||||
if self.config.out_ref:
|
||||
outs_gdt_pred = []
|
||||
outs_gdt_label = []
|
||||
x, x1, x2, x3, x4, gdt_gt = features
|
||||
else:
|
||||
x, x1, x2, x3, x4 = features
|
||||
outs = []
|
||||
p4 = self.decoder_block4(x4)
|
||||
m4 = self.conv_ms_spvn_4(p4) if self.config.ms_supervision else None
|
||||
_p4 = F.interpolate(p4, size=x3.shape[2:], mode='bilinear', align_corners=True)
|
||||
_p3 = _p4 + self.lateral_block4(x3)
|
||||
if self.config.dec_ipt:
|
||||
patches_batch = self.get_patches_batch(x, _p3) if self.split else x
|
||||
_p3 = torch.cat((_p3, self.ipt_blk4(F.interpolate(patches_batch, size=x3.shape[2:], mode='bilinear', align_corners=True))), 1)
|
||||
|
||||
p3 = self.decoder_block3(_p3)
|
||||
m3 = self.conv_ms_spvn_3(p3) if self.config.ms_supervision else None
|
||||
if self.config.out_ref:
|
||||
# >> GT:
|
||||
# m3 --dilation--> m3_dia
|
||||
# G_3^gt * m3_dia --> G_3^m, which is the label of gradient
|
||||
m3_dia = m3
|
||||
gdt_label_main_3 = gdt_gt * F.interpolate(m3_dia, size=gdt_gt.shape[2:], mode='bilinear', align_corners=True)
|
||||
outs_gdt_label.append(gdt_label_main_3)
|
||||
# >> Pred:
|
||||
# p3 --conv--BN--> F_3^G, where F_3^G predicts the \hat{G_3} with xx
|
||||
# F_3^G --sigmoid--> A_3^G
|
||||
p3_gdt = self.gdt_convs_3(p3)
|
||||
gdt_pred_3 = self.gdt_convs_pred_3(p3_gdt)
|
||||
outs_gdt_pred.append(gdt_pred_3)
|
||||
gdt_attn_3 = self.gdt_convs_attn_3(p3_gdt).sigmoid()
|
||||
# >> Finally:
|
||||
# p3 = p3 * A_3^G
|
||||
p3 = p3 * gdt_attn_3
|
||||
_p3 = F.interpolate(p3, size=x2.shape[2:], mode='bilinear', align_corners=True)
|
||||
_p2 = _p3 + self.lateral_block3(x2)
|
||||
if self.config.dec_ipt:
|
||||
patches_batch = self.get_patches_batch(x, _p2) if self.split else x
|
||||
_p2 = torch.cat((_p2, self.ipt_blk3(F.interpolate(patches_batch, size=x2.shape[2:], mode='bilinear', align_corners=True))), 1)
|
||||
|
||||
p2 = self.decoder_block2(_p2)
|
||||
m2 = self.conv_ms_spvn_2(p2) if self.config.ms_supervision else None
|
||||
if self.config.out_ref:
|
||||
# >> GT:
|
||||
m2_dia = m2
|
||||
gdt_label_main_2 = gdt_gt * F.interpolate(m2_dia, size=gdt_gt.shape[2:], mode='bilinear', align_corners=True)
|
||||
outs_gdt_label.append(gdt_label_main_2)
|
||||
# >> Pred:
|
||||
p2_gdt = self.gdt_convs_2(p2)
|
||||
gdt_pred_2 = self.gdt_convs_pred_2(p2_gdt)
|
||||
outs_gdt_pred.append(gdt_pred_2)
|
||||
gdt_attn_2 = self.gdt_convs_attn_2(p2_gdt).sigmoid()
|
||||
# >> Finally:
|
||||
p2 = p2 * gdt_attn_2
|
||||
_p2 = F.interpolate(p2, size=x1.shape[2:], mode='bilinear', align_corners=True)
|
||||
_p1 = _p2 + self.lateral_block2(x1)
|
||||
if self.config.dec_ipt:
|
||||
patches_batch = self.get_patches_batch(x, _p1) if self.split else x
|
||||
_p1 = torch.cat((_p1, self.ipt_blk2(F.interpolate(patches_batch, size=x1.shape[2:], mode='bilinear', align_corners=True))), 1)
|
||||
|
||||
_p1 = self.decoder_block1(_p1)
|
||||
_p1 = F.interpolate(_p1, size=x.shape[2:], mode='bilinear', align_corners=True)
|
||||
if self.config.dec_ipt:
|
||||
patches_batch = self.get_patches_batch(x, _p1) if self.split else x
|
||||
_p1 = torch.cat((_p1, self.ipt_blk1(F.interpolate(patches_batch, size=x.shape[2:], mode='bilinear', align_corners=True))), 1)
|
||||
p1_out = self.conv_out1(_p1)
|
||||
|
||||
if self.config.ms_supervision:
|
||||
outs.append(m4)
|
||||
outs.append(m3)
|
||||
outs.append(m2)
|
||||
outs.append(p1_out)
|
||||
return outs if not (self.config.out_ref and self.training) else ([outs_gdt_pred, outs_gdt_label], outs)
|
||||
|
||||
|
||||
class SimpleConvs(nn.Module):
|
||||
def __init__(
|
||||
self, in_channels: int, out_channels: int, inter_channels=64
|
||||
) -> None:
|
||||
super().__init__()
|
||||
self.conv1 = nn.Conv2d(in_channels, inter_channels, 3, 1, 1)
|
||||
self.conv_out = nn.Conv2d(inter_channels, out_channels, 3, 1, 1)
|
||||
|
||||
def forward(self, x):
|
||||
return self.conv_out(self.conv1(x))
|
||||
@@ -0,0 +1,163 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
from ..modules.deform_conv import DeformableConv2d
|
||||
from ...config import Config
|
||||
|
||||
|
||||
config = Config()
|
||||
|
||||
|
||||
class ASPPComplex(nn.Module):
|
||||
def __init__(self, in_channels=64, out_channels=None, output_stride=16):
|
||||
super(ASPPComplex, self).__init__()
|
||||
self.down_scale = 1
|
||||
if out_channels is None:
|
||||
out_channels = in_channels
|
||||
self.in_channelster = 256 // self.down_scale
|
||||
if output_stride == 16:
|
||||
dilations = [1, 6, 12, 18]
|
||||
elif output_stride == 8:
|
||||
dilations = [1, 12, 24, 36]
|
||||
else:
|
||||
raise NotImplementedError
|
||||
|
||||
self.aspp1 = _ASPPModule(in_channels, self.in_channelster, 1, padding=0, dilation=dilations[0])
|
||||
self.aspp2 = _ASPPModule(in_channels, self.in_channelster, 3, padding=dilations[1], dilation=dilations[1])
|
||||
self.aspp3 = _ASPPModule(in_channels, self.in_channelster, 3, padding=dilations[2], dilation=dilations[2])
|
||||
self.aspp4 = _ASPPModule(in_channels, self.in_channelster, 3, padding=dilations[3], dilation=dilations[3])
|
||||
|
||||
self.global_avg_pool = nn.Sequential(nn.AdaptiveAvgPool2d((1, 1)),
|
||||
nn.Conv2d(in_channels, self.in_channelster, 1, stride=1, bias=False),
|
||||
nn.BatchNorm2d(self.in_channelster) if config.batch_size > 1 else nn.Identity(),
|
||||
nn.ReLU(inplace=True))
|
||||
self.conv1 = nn.Conv2d(self.in_channelster * 5, out_channels, 1, bias=False)
|
||||
self.bn1 = nn.BatchNorm2d(out_channels)
|
||||
self.relu = nn.ReLU(inplace=True)
|
||||
self.dropout = nn.Dropout(0.5)
|
||||
|
||||
def forward(self, x):
|
||||
x1 = self.aspp1(x)
|
||||
x2 = self.aspp2(x)
|
||||
x3 = self.aspp3(x)
|
||||
x4 = self.aspp4(x)
|
||||
x5 = self.global_avg_pool(x)
|
||||
x5 = F.interpolate(x5, size=x1.size()[2:], mode='bilinear', align_corners=True)
|
||||
x = torch.cat((x1, x2, x3, x4, x5), dim=1)
|
||||
|
||||
x = self.conv1(x)
|
||||
x = self.bn1(x)
|
||||
x = self.relu(x)
|
||||
|
||||
return self.dropout(x)
|
||||
|
||||
|
||||
class _ASPPModule(nn.Module):
|
||||
def __init__(self, in_channels, planes, kernel_size, padding, dilation):
|
||||
super(_ASPPModule, self).__init__()
|
||||
self.atrous_conv = nn.Conv2d(in_channels, planes, kernel_size=kernel_size,
|
||||
stride=1, padding=padding, dilation=dilation, bias=False)
|
||||
self.bn = nn.BatchNorm2d(planes)
|
||||
self.relu = nn.ReLU(inplace=True)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.atrous_conv(x)
|
||||
x = self.bn(x)
|
||||
|
||||
return self.relu(x)
|
||||
|
||||
|
||||
class ASPP(nn.Module):
|
||||
def __init__(self, in_channels=64, out_channels=None, output_stride=16):
|
||||
super(ASPP, self).__init__()
|
||||
self.down_scale = 1
|
||||
if out_channels is None:
|
||||
out_channels = in_channels
|
||||
self.in_channelster = 256 // self.down_scale
|
||||
if output_stride == 16:
|
||||
dilations = [1, 6, 12, 18]
|
||||
elif output_stride == 8:
|
||||
dilations = [1, 12, 24, 36]
|
||||
else:
|
||||
raise NotImplementedError
|
||||
|
||||
self.aspp1 = _ASPPModule(in_channels, self.in_channelster, 1, padding=0, dilation=dilations[0])
|
||||
self.aspp2 = _ASPPModule(in_channels, self.in_channelster, 3, padding=dilations[1], dilation=dilations[1])
|
||||
self.aspp3 = _ASPPModule(in_channels, self.in_channelster, 3, padding=dilations[2], dilation=dilations[2])
|
||||
self.aspp4 = _ASPPModule(in_channels, self.in_channelster, 3, padding=dilations[3], dilation=dilations[3])
|
||||
|
||||
self.global_avg_pool = nn.Sequential(nn.AdaptiveAvgPool2d((1, 1)),
|
||||
nn.Conv2d(in_channels, self.in_channelster, 1, stride=1, bias=False),
|
||||
nn.BatchNorm2d(self.in_channelster) if config.batch_size > 1 else nn.Identity(),
|
||||
nn.ReLU(inplace=True))
|
||||
self.conv1 = nn.Conv2d(self.in_channelster * 5, out_channels, 1, bias=False)
|
||||
self.bn1 = nn.BatchNorm2d(out_channels)
|
||||
self.relu = nn.ReLU(inplace=True)
|
||||
self.dropout = nn.Dropout(0.5)
|
||||
|
||||
def forward(self, x):
|
||||
x1 = self.aspp1(x)
|
||||
x2 = self.aspp2(x)
|
||||
x3 = self.aspp3(x)
|
||||
x4 = self.aspp4(x)
|
||||
x5 = self.global_avg_pool(x)
|
||||
x5 = F.interpolate(x5, size=x1.size()[2:], mode='bilinear', align_corners=True)
|
||||
x = torch.cat((x1, x2, x3, x4, x5), dim=1)
|
||||
|
||||
x = self.conv1(x)
|
||||
x = self.bn1(x)
|
||||
x = self.relu(x)
|
||||
|
||||
return self.dropout(x)
|
||||
|
||||
|
||||
##################### Deformable
|
||||
class _ASPPModuleDeformable(nn.Module):
|
||||
def __init__(self, in_channels, planes, kernel_size, padding):
|
||||
super(_ASPPModuleDeformable, self).__init__()
|
||||
self.atrous_conv = DeformableConv2d(in_channels, planes, kernel_size=kernel_size,
|
||||
stride=1, padding=padding, bias=False)
|
||||
self.bn = nn.BatchNorm2d(planes)
|
||||
self.relu = nn.ReLU(inplace=True)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.atrous_conv(x)
|
||||
x = self.bn(x)
|
||||
|
||||
return self.relu(x)
|
||||
|
||||
|
||||
class ASPPDeformable(nn.Module):
|
||||
def __init__(self, in_channels, out_channels=None, num_parallel_block=1):
|
||||
super(ASPPDeformable, self).__init__()
|
||||
self.down_scale = 1
|
||||
if out_channels is None:
|
||||
out_channels = in_channels
|
||||
self.in_channelster = 256 // self.down_scale
|
||||
|
||||
self.aspp1 = _ASPPModuleDeformable(in_channels, self.in_channelster, 1, padding=0)
|
||||
self.aspp_deforms = nn.ModuleList([
|
||||
_ASPPModuleDeformable(in_channels, self.in_channelster, 3, padding=1) for _ in range(num_parallel_block)
|
||||
])
|
||||
|
||||
self.global_avg_pool = nn.Sequential(nn.AdaptiveAvgPool2d((1, 1)),
|
||||
nn.Conv2d(in_channels, self.in_channelster, 1, stride=1, bias=False),
|
||||
nn.BatchNorm2d(self.in_channelster) if config.batch_size > 1 else nn.Identity(),
|
||||
nn.ReLU(inplace=True))
|
||||
self.conv1 = nn.Conv2d(self.in_channelster * (2 + len(self.aspp_deforms)), out_channels, 1, bias=False)
|
||||
self.bn1 = nn.BatchNorm2d(out_channels)
|
||||
self.relu = nn.ReLU(inplace=True)
|
||||
self.dropout = nn.Dropout(0.5)
|
||||
|
||||
def forward(self, x):
|
||||
x1 = self.aspp1(x)
|
||||
x_aspp_deforms = [aspp_deform(x) for aspp_deform in self.aspp_deforms]
|
||||
x5 = self.global_avg_pool(x)
|
||||
x5 = F.interpolate(x5, size=x1.size()[2:], mode='bilinear', align_corners=True)
|
||||
x = torch.cat((x1, *x_aspp_deforms, x5), dim=1)
|
||||
|
||||
x = self.conv1(x)
|
||||
x = self.bn1(x)
|
||||
x = self.relu(x)
|
||||
|
||||
return self.dropout(x)
|
||||
@@ -0,0 +1,93 @@
|
||||
import numpy as np
|
||||
import torch
|
||||
from torch import nn
|
||||
from torch.nn import init
|
||||
|
||||
|
||||
class SEWeightModule(nn.Module):
|
||||
def __init__(self, channels, reduction=16):
|
||||
super(SEWeightModule, self).__init__()
|
||||
self.avg_pool = nn.AdaptiveAvgPool2d(1)
|
||||
self.fc1 = nn.Conv2d(channels, channels//reduction, kernel_size=1, padding=0)
|
||||
self.relu = nn.ReLU(inplace=True)
|
||||
self.fc2 = nn.Conv2d(channels//reduction, channels, kernel_size=1, padding=0)
|
||||
self.sigmoid = nn.Sigmoid()
|
||||
|
||||
def forward(self, x):
|
||||
out = self.avg_pool(x)
|
||||
out = self.fc1(out)
|
||||
out = self.relu(out)
|
||||
out = self.fc2(out)
|
||||
weight = self.sigmoid(out)
|
||||
return weight
|
||||
|
||||
|
||||
class PSA(nn.Module):
|
||||
|
||||
def __init__(self, in_channels, S=4, reduction=4):
|
||||
super().__init__()
|
||||
self.S = S
|
||||
|
||||
_convs = []
|
||||
for i in range(S):
|
||||
_convs.append(nn.Conv2d(in_channels//S, in_channels//S, kernel_size=2*(i+1)+1, padding=i+1))
|
||||
self.convs = nn.ModuleList(_convs)
|
||||
|
||||
self.se_block = SEWeightModule(in_channels//S, reduction=S*reduction)
|
||||
|
||||
self.softmax = nn.Softmax(dim=1)
|
||||
|
||||
def forward(self, x):
|
||||
b, c, h, w = x.size()
|
||||
|
||||
# Step1: SPC module
|
||||
SPC_out = x.view(b, self.S, c//self.S, h, w) #bs,s,ci,h,w
|
||||
for idx, conv in enumerate(self.convs):
|
||||
SPC_out[:,idx,:,:,:] = conv(SPC_out[:,idx,:,:,:].clone())
|
||||
|
||||
# Step2: SE weight
|
||||
se_out=[]
|
||||
for idx in range(self.S):
|
||||
se_out.append(self.se_block(SPC_out[:, idx, :, :, :]))
|
||||
SE_out = torch.stack(se_out, dim=1)
|
||||
SE_out = SE_out.expand_as(SPC_out)
|
||||
|
||||
# Step3: Softmax
|
||||
softmax_out = self.softmax(SE_out)
|
||||
|
||||
# Step4: SPA
|
||||
PSA_out = SPC_out * softmax_out
|
||||
PSA_out = PSA_out.view(b, -1, h, w)
|
||||
|
||||
return PSA_out
|
||||
|
||||
|
||||
class SGE(nn.Module):
|
||||
|
||||
def __init__(self, groups):
|
||||
super().__init__()
|
||||
self.groups=groups
|
||||
self.avg_pool = nn.AdaptiveAvgPool2d(1)
|
||||
self.weight=nn.Parameter(torch.zeros(1,groups,1,1))
|
||||
self.bias=nn.Parameter(torch.zeros(1,groups,1,1))
|
||||
self.sig=nn.Sigmoid()
|
||||
|
||||
def forward(self, x):
|
||||
b, c, h,w=x.shape
|
||||
x=x.view(b*self.groups,-1,h,w) #bs*g,dim//g,h,w
|
||||
xn=x*self.avg_pool(x) #bs*g,dim//g,h,w
|
||||
xn=xn.sum(dim=1,keepdim=True) #bs*g,1,h,w
|
||||
t=xn.view(b*self.groups,-1) #bs*g,h*w
|
||||
|
||||
t=t-t.mean(dim=1,keepdim=True) #bs*g,h*w
|
||||
std=t.std(dim=1,keepdim=True)+1e-5
|
||||
t=t/std #bs*g,h*w
|
||||
t=t.view(b,self.groups,h,w) #bs,g,h*w
|
||||
|
||||
t=t*self.weight+self.bias #bs,g,h*w
|
||||
t=t.view(b*self.groups,1,h,w) #bs*g,1,h*w
|
||||
x=x*self.sig(t)
|
||||
x=x.view(b,c,h,w)
|
||||
|
||||
return x
|
||||
|
||||
@@ -0,0 +1,101 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from ..modules.aspp import ASPP, ASPPDeformable
|
||||
from ..modules.attentions import PSA, SGE
|
||||
from ...config import Config
|
||||
|
||||
|
||||
config = Config()
|
||||
|
||||
|
||||
class BasicDecBlk(nn.Module):
|
||||
def __init__(self, in_channels=64, out_channels=64, inter_channels=64):
|
||||
super(BasicDecBlk, self).__init__()
|
||||
inter_channels = in_channels // 4 if config.dec_channels_inter == 'adap' else 64
|
||||
self.conv_in = nn.Conv2d(in_channels, inter_channels, 3, 1, padding=1)
|
||||
self.relu_in = nn.ReLU(inplace=True)
|
||||
if config.dec_att == 'ASPP':
|
||||
self.dec_att = ASPP(in_channels=inter_channels)
|
||||
elif config.dec_att == 'ASPPDeformable':
|
||||
self.dec_att = ASPPDeformable(in_channels=inter_channels)
|
||||
self.conv_out = nn.Conv2d(inter_channels, out_channels, 3, 1, padding=1)
|
||||
self.bn_in = nn.BatchNorm2d(inter_channels)
|
||||
self.bn_out = nn.BatchNorm2d(out_channels)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.conv_in(x)
|
||||
x = self.bn_in(x)
|
||||
x = self.relu_in(x)
|
||||
if hasattr(self, 'dec_att'):
|
||||
x = self.dec_att(x)
|
||||
x = self.conv_out(x)
|
||||
x = self.bn_out(x)
|
||||
return x
|
||||
|
||||
|
||||
class ResBlk(nn.Module):
|
||||
def __init__(self, in_channels=64, out_channels=None, inter_channels=64):
|
||||
super(ResBlk, self).__init__()
|
||||
if out_channels is None:
|
||||
out_channels = in_channels
|
||||
inter_channels = in_channels // 4 if config.dec_channels_inter == 'adap' else 64
|
||||
|
||||
self.conv_in = nn.Conv2d(in_channels, inter_channels, 3, 1, padding=1)
|
||||
self.bn_in = nn.BatchNorm2d(inter_channels)
|
||||
self.relu_in = nn.ReLU(inplace=True)
|
||||
|
||||
if config.dec_att == 'ASPP':
|
||||
self.dec_att = ASPP(in_channels=inter_channels)
|
||||
elif config.dec_att == 'ASPPDeformable':
|
||||
self.dec_att = ASPPDeformable(in_channels=inter_channels)
|
||||
|
||||
self.conv_out = nn.Conv2d(inter_channels, out_channels, 3, 1, padding=1)
|
||||
self.bn_out = nn.BatchNorm2d(out_channels)
|
||||
|
||||
self.conv_resi = nn.Conv2d(in_channels, out_channels, 1, 1, 0)
|
||||
|
||||
def forward(self, x):
|
||||
_x = self.conv_resi(x)
|
||||
x = self.conv_in(x)
|
||||
x = self.bn_in(x)
|
||||
x = self.relu_in(x)
|
||||
if hasattr(self, 'dec_att'):
|
||||
x = self.dec_att(x)
|
||||
x = self.conv_out(x)
|
||||
x = self.bn_out(x)
|
||||
return x + _x
|
||||
|
||||
|
||||
class HierarAttDecBlk(nn.Module):
|
||||
def __init__(self, in_channels=64, out_channels=None, inter_channels=64):
|
||||
super(HierarAttDecBlk, self).__init__()
|
||||
if out_channels is None:
|
||||
out_channels = in_channels
|
||||
inter_channels = in_channels // 4 if config.dec_channels_inter == 'adap' else 64
|
||||
self.split_y = 8 # must be divided by channels of all intermediate features
|
||||
self.split_x = 8
|
||||
|
||||
self.conv_in = nn.Conv2d(in_channels, inter_channels, 3, 1, 1)
|
||||
|
||||
self.psa = PSA(inter_channels*self.split_y*self.split_x, S=config.batch_size)
|
||||
self.sge = SGE(groups=config.batch_size)
|
||||
|
||||
if config.dec_att == 'ASPP':
|
||||
self.dec_att = ASPP(in_channels=inter_channels)
|
||||
elif config.dec_att == 'ASPPDeformable':
|
||||
self.dec_att = ASPPDeformable(in_channels=inter_channels)
|
||||
self.conv_out = nn.Conv2d(inter_channels, out_channels, 3, 1, 1)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.conv_in(x)
|
||||
N, C, H, W = x.shape
|
||||
x_patchs = x.reshape(N, -1, H//self.split_y, W//self.split_x)
|
||||
|
||||
# Hierarchical attention: group attention X patch spatial attention
|
||||
x_patchs = self.psa(x_patchs) # Group Channel Attention -- each group is a single image
|
||||
x_patchs = self.sge(x_patchs) # Patch Spatial Attention
|
||||
x = x.reshape(N, C, H, W)
|
||||
if hasattr(self, 'dec_att'):
|
||||
x = self.dec_att(x)
|
||||
x = self.conv_out(x)
|
||||
return x
|
||||
@@ -0,0 +1,66 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from torchvision.ops import deform_conv2d
|
||||
|
||||
|
||||
class DeformableConv2d(nn.Module):
|
||||
def __init__(self,
|
||||
in_channels,
|
||||
out_channels,
|
||||
kernel_size=3,
|
||||
stride=1,
|
||||
padding=1,
|
||||
bias=False):
|
||||
|
||||
super(DeformableConv2d, self).__init__()
|
||||
|
||||
assert type(kernel_size) == tuple or type(kernel_size) == int
|
||||
|
||||
kernel_size = kernel_size if type(kernel_size) == tuple else (kernel_size, kernel_size)
|
||||
self.stride = stride if type(stride) == tuple else (stride, stride)
|
||||
self.padding = padding
|
||||
|
||||
self.offset_conv = nn.Conv2d(in_channels,
|
||||
2 * kernel_size[0] * kernel_size[1],
|
||||
kernel_size=kernel_size,
|
||||
stride=stride,
|
||||
padding=self.padding,
|
||||
bias=True)
|
||||
|
||||
nn.init.constant_(self.offset_conv.weight, 0.)
|
||||
nn.init.constant_(self.offset_conv.bias, 0.)
|
||||
|
||||
self.modulator_conv = nn.Conv2d(in_channels,
|
||||
1 * kernel_size[0] * kernel_size[1],
|
||||
kernel_size=kernel_size,
|
||||
stride=stride,
|
||||
padding=self.padding,
|
||||
bias=True)
|
||||
|
||||
nn.init.constant_(self.modulator_conv.weight, 0.)
|
||||
nn.init.constant_(self.modulator_conv.bias, 0.)
|
||||
|
||||
self.regular_conv = nn.Conv2d(in_channels,
|
||||
out_channels=out_channels,
|
||||
kernel_size=kernel_size,
|
||||
stride=stride,
|
||||
padding=self.padding,
|
||||
bias=bias)
|
||||
|
||||
def forward(self, x):
|
||||
#h, w = x.shape[2:]
|
||||
#max_offset = max(h, w)/4.
|
||||
|
||||
offset = self.offset_conv(x)#.clamp(-max_offset, max_offset)
|
||||
modulator = 2. * torch.sigmoid(self.modulator_conv(x))
|
||||
|
||||
x = deform_conv2d(
|
||||
input=x,
|
||||
offset=offset,
|
||||
weight=self.regular_conv.weight,
|
||||
bias=self.regular_conv.bias,
|
||||
padding=self.padding,
|
||||
mask=modulator,
|
||||
stride=self.stride,
|
||||
)
|
||||
return x
|
||||
@@ -0,0 +1,29 @@
|
||||
import torch.nn as nn
|
||||
from ..modules.mlp import MLPLayer
|
||||
|
||||
|
||||
class BlockA(nn.Module):
|
||||
def __init__(self, in_channels=64, out_channels=64, inter_channels=64, mlp_ratio=4.):
|
||||
super(BlockA, self).__init__()
|
||||
inter_channels = in_channels
|
||||
self.conv = nn.Conv2d(in_channels, inter_channels, 3, 1, 1)
|
||||
self.norm1 = nn.LayerNorm(inter_channels)
|
||||
self.ffn = MLPLayer(in_features=inter_channels,
|
||||
hidden_features=int(inter_channels * mlp_ratio),
|
||||
act_layer=nn.GELU,
|
||||
drop=0.)
|
||||
self.norm2 = nn.LayerNorm(inter_channels)
|
||||
|
||||
def forward(self, x):
|
||||
B, C, H, W = x.shape
|
||||
_x = self.conv(x)
|
||||
_x = _x.flatten(2).transpose(1, 2)
|
||||
_x = self.norm1(_x)
|
||||
x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
|
||||
|
||||
x = x + _x
|
||||
_x1 = self.ffn(x)
|
||||
_x1 = self.norm2(_x1)
|
||||
_x1 = _x1.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
|
||||
x = x + _x1
|
||||
return x
|
||||
@@ -0,0 +1,21 @@
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
from functools import partial
|
||||
|
||||
from ...config import Config
|
||||
|
||||
|
||||
config = Config()
|
||||
|
||||
|
||||
class BasicLatBlk(nn.Module):
|
||||
def __init__(self, in_channels=64, out_channels=64, inter_channels=64):
|
||||
super(BasicLatBlk, self).__init__()
|
||||
inter_channels = in_channels // 4 if config.dec_channels_inter == 'adap' else 64
|
||||
self.conv = nn.Conv2d(in_channels, out_channels, 1, 1, 0)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.conv(x)
|
||||
return x
|
||||
@@ -0,0 +1,121 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from functools import partial
|
||||
|
||||
try:
|
||||
# version > 0.6.13
|
||||
from timm.layers import DropPath, to_2tuple, trunc_normal_
|
||||
except Exception:
|
||||
from timm.models.layers import DropPath, to_2tuple, trunc_normal_
|
||||
|
||||
import math
|
||||
|
||||
|
||||
class MLPLayer(nn.Module):
|
||||
def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
|
||||
super().__init__()
|
||||
out_features = out_features or in_features
|
||||
hidden_features = hidden_features or in_features
|
||||
self.fc1 = nn.Linear(in_features, hidden_features)
|
||||
self.act = act_layer()
|
||||
self.fc2 = nn.Linear(hidden_features, out_features)
|
||||
self.drop = nn.Dropout(drop)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.fc1(x)
|
||||
x = self.act(x)
|
||||
x = self.drop(x)
|
||||
x = self.fc2(x)
|
||||
x = self.drop(x)
|
||||
return x
|
||||
|
||||
|
||||
class Attention(nn.Module):
|
||||
def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0., sr_ratio=1):
|
||||
super().__init__()
|
||||
assert dim % num_heads == 0, f"dim {dim} should be divided by num_heads {num_heads}."
|
||||
|
||||
self.dim = dim
|
||||
self.num_heads = num_heads
|
||||
head_dim = dim // num_heads
|
||||
self.scale = qk_scale or head_dim ** -0.5
|
||||
|
||||
self.q = nn.Linear(dim, dim, bias=qkv_bias)
|
||||
self.kv = nn.Linear(dim, dim * 2, bias=qkv_bias)
|
||||
self.attn_drop = nn.Dropout(attn_drop)
|
||||
self.proj = nn.Linear(dim, dim)
|
||||
self.proj_drop = nn.Dropout(proj_drop)
|
||||
|
||||
self.sr_ratio = sr_ratio
|
||||
if sr_ratio > 1:
|
||||
self.sr = nn.Conv2d(dim, dim, kernel_size=sr_ratio, stride=sr_ratio)
|
||||
self.norm = nn.LayerNorm(dim)
|
||||
|
||||
def forward(self, x, H, W):
|
||||
B, N, C = x.shape
|
||||
q = self.q(x).reshape(B, N, self.num_heads, C // self.num_heads).permute(0, 2, 1, 3)
|
||||
|
||||
if self.sr_ratio > 1:
|
||||
x_ = x.permute(0, 2, 1).reshape(B, C, H, W)
|
||||
x_ = self.sr(x_).reshape(B, C, -1).permute(0, 2, 1)
|
||||
x_ = self.norm(x_)
|
||||
kv = self.kv(x_).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
|
||||
else:
|
||||
kv = self.kv(x).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
|
||||
k, v = kv[0], kv[1]
|
||||
|
||||
attn = (q @ k.transpose(-2, -1)) * self.scale
|
||||
attn = attn.softmax(dim=-1)
|
||||
attn = self.attn_drop(attn)
|
||||
|
||||
x = (attn @ v).transpose(1, 2).reshape(B, N, C)
|
||||
x = self.proj(x)
|
||||
x = self.proj_drop(x)
|
||||
return x
|
||||
|
||||
|
||||
class Block(nn.Module):
|
||||
def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0.,
|
||||
drop_path=0., act_layer=nn.GELU, norm_layer=nn.LayerNorm, sr_ratio=1):
|
||||
super().__init__()
|
||||
self.norm1 = norm_layer(dim)
|
||||
self.attn = Attention(
|
||||
dim,
|
||||
num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale,
|
||||
attn_drop=attn_drop, proj_drop=drop, sr_ratio=sr_ratio)
|
||||
# NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
|
||||
self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
|
||||
self.norm2 = norm_layer(dim)
|
||||
mlp_hidden_dim = int(dim * mlp_ratio)
|
||||
self.mlp = MLPLayer(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
|
||||
|
||||
def forward(self, x, H, W):
|
||||
x = x + self.drop_path(self.attn(self.norm1(x), H, W))
|
||||
x = x + self.drop_path(self.mlp(self.norm2(x), H, W))
|
||||
return x
|
||||
|
||||
|
||||
class OverlapPatchEmbed(nn.Module):
|
||||
""" Image to Patch Embedding
|
||||
"""
|
||||
|
||||
def __init__(self, img_size=224, patch_size=7, stride=4, in_channels=3, embed_dim=768):
|
||||
super().__init__()
|
||||
img_size = to_2tuple(img_size)
|
||||
patch_size = to_2tuple(patch_size)
|
||||
|
||||
self.img_size = img_size
|
||||
self.patch_size = patch_size
|
||||
self.H, self.W = img_size[0] // patch_size[0], img_size[1] // patch_size[1]
|
||||
self.num_patches = self.H * self.W
|
||||
self.proj = nn.Conv2d(in_channels, embed_dim, kernel_size=patch_size, stride=stride,
|
||||
padding=(patch_size[0] // 2, patch_size[1] // 2))
|
||||
self.norm = nn.LayerNorm(embed_dim)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.proj(x)
|
||||
_, _, H, W = x.shape
|
||||
x = x.flatten(2).transpose(1, 2)
|
||||
x = self.norm(x)
|
||||
return x, H, W
|
||||
|
||||
@@ -0,0 +1,54 @@
|
||||
import torch.nn as nn
|
||||
|
||||
|
||||
def build_act_layer(act_layer):
|
||||
if act_layer == 'ReLU':
|
||||
return nn.ReLU(inplace=True)
|
||||
elif act_layer == 'SiLU':
|
||||
return nn.SiLU(inplace=True)
|
||||
elif act_layer == 'GELU':
|
||||
return nn.GELU()
|
||||
|
||||
raise NotImplementedError(f'build_act_layer does not support {act_layer}')
|
||||
|
||||
|
||||
def build_norm_layer(dim,
|
||||
norm_layer,
|
||||
in_format='channels_last',
|
||||
out_format='channels_last',
|
||||
eps=1e-6):
|
||||
layers = []
|
||||
if norm_layer == 'BN':
|
||||
if in_format == 'channels_last':
|
||||
layers.append(to_channels_first())
|
||||
layers.append(nn.BatchNorm2d(dim))
|
||||
if out_format == 'channels_last':
|
||||
layers.append(to_channels_last())
|
||||
elif norm_layer == 'LN':
|
||||
if in_format == 'channels_first':
|
||||
layers.append(to_channels_last())
|
||||
layers.append(nn.LayerNorm(dim, eps=eps))
|
||||
if out_format == 'channels_first':
|
||||
layers.append(to_channels_first())
|
||||
else:
|
||||
raise NotImplementedError(
|
||||
f'build_norm_layer does not support {norm_layer}')
|
||||
return nn.Sequential(*layers)
|
||||
|
||||
|
||||
class to_channels_first(nn.Module):
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
|
||||
def forward(self, x):
|
||||
return x.permute(0, 3, 1, 2)
|
||||
|
||||
|
||||
class to_channels_last(nn.Module):
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
|
||||
def forward(self, x):
|
||||
return x.permute(0, 2, 3, 1)
|
||||
@@ -0,0 +1,253 @@
|
||||
# import torch
|
||||
# import torch.nn as nn
|
||||
# from collections import OrderedDict
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
# from torchvision.models import vgg16, vgg16_bn
|
||||
# from torchvision.models import resnet50
|
||||
|
||||
from birefnet_old.config import Config
|
||||
from birefnet_old.dataset import class_labels_TR_sorted
|
||||
from birefnet_old.models.backbones.build_backbone import build_backbone
|
||||
from birefnet_old.models.modules.decoder_blocks import BasicDecBlk
|
||||
from birefnet_old.models.modules.lateral_blocks import BasicLatBlk
|
||||
from birefnet_old.models.modules.ing import *
|
||||
from birefnet_old.models.refinement.stem_layer import StemLayer
|
||||
|
||||
|
||||
class RefinerPVTInChannels4(nn.Module):
|
||||
def __init__(self, in_channels=3+1):
|
||||
super(RefinerPVTInChannels4, self).__init__()
|
||||
self.config = Config()
|
||||
self.epoch = 1
|
||||
self.bb = build_backbone(self.config.bb, params_settings='in_channels=4')
|
||||
|
||||
lateral_channels_in_collection = {
|
||||
'vgg16': [512, 256, 128, 64], 'vgg16bn': [512, 256, 128, 64], 'resnet50': [1024, 512, 256, 64],
|
||||
'pvt_v2_b2': [512, 320, 128, 64], 'pvt_v2_b5': [512, 320, 128, 64],
|
||||
'swin_v1_b': [1024, 512, 256, 128], 'swin_v1_l': [1536, 768, 384, 192],
|
||||
}
|
||||
channels = lateral_channels_in_collection[self.config.bb]
|
||||
self.squeeze_module = BasicDecBlk(channels[0], channels[0])
|
||||
|
||||
self.decoder = Decoder(channels)
|
||||
|
||||
if 0:
|
||||
for key, value in self.named_parameters():
|
||||
if 'bb.' in key:
|
||||
value.requires_grad = False
|
||||
|
||||
def forward(self, x):
|
||||
if isinstance(x, list):
|
||||
x = torch.cat(x, dim=1)
|
||||
########## Encoder ##########
|
||||
if self.config.bb in ['vgg16', 'vgg16bn', 'resnet50']:
|
||||
x1 = self.bb.conv1(x)
|
||||
x2 = self.bb.conv2(x1)
|
||||
x3 = self.bb.conv3(x2)
|
||||
x4 = self.bb.conv4(x3)
|
||||
else:
|
||||
x1, x2, x3, x4 = self.bb(x)
|
||||
|
||||
x4 = self.squeeze_module(x4)
|
||||
|
||||
########## Decoder ##########
|
||||
|
||||
features = [x, x1, x2, x3, x4]
|
||||
scaled_preds = self.decoder(features)
|
||||
|
||||
return scaled_preds
|
||||
|
||||
|
||||
class Refiner(nn.Module):
|
||||
def __init__(self, in_channels=3+1):
|
||||
super(Refiner, self).__init__()
|
||||
self.config = Config()
|
||||
self.epoch = 1
|
||||
self.stem_layer = StemLayer(in_channels=in_channels, inter_channels=48, out_channels=3)
|
||||
self.bb = build_backbone(self.config.bb)
|
||||
|
||||
lateral_channels_in_collection = {
|
||||
'vgg16': [512, 256, 128, 64], 'vgg16bn': [512, 256, 128, 64], 'resnet50': [1024, 512, 256, 64],
|
||||
'pvt_v2_b2': [512, 320, 128, 64], 'pvt_v2_b5': [512, 320, 128, 64],
|
||||
'swin_v1_b': [1024, 512, 256, 128], 'swin_v1_l': [1536, 768, 384, 192],
|
||||
}
|
||||
channels = lateral_channels_in_collection[self.config.bb]
|
||||
self.squeeze_module = BasicDecBlk(channels[0], channels[0])
|
||||
|
||||
self.decoder = Decoder(channels)
|
||||
|
||||
if 0:
|
||||
for key, value in self.named_parameters():
|
||||
if 'bb.' in key:
|
||||
value.requires_grad = False
|
||||
|
||||
def forward(self, x):
|
||||
if isinstance(x, list):
|
||||
x = torch.cat(x, dim=1)
|
||||
x = self.stem_layer(x)
|
||||
########## Encoder ##########
|
||||
if self.config.bb in ['vgg16', 'vgg16bn', 'resnet50']:
|
||||
x1 = self.bb.conv1(x)
|
||||
x2 = self.bb.conv2(x1)
|
||||
x3 = self.bb.conv3(x2)
|
||||
x4 = self.bb.conv4(x3)
|
||||
else:
|
||||
x1, x2, x3, x4 = self.bb(x)
|
||||
|
||||
x4 = self.squeeze_module(x4)
|
||||
|
||||
########## Decoder ##########
|
||||
|
||||
features = [x, x1, x2, x3, x4]
|
||||
scaled_preds = self.decoder(features)
|
||||
|
||||
return scaled_preds
|
||||
|
||||
|
||||
class Decoder(nn.Module):
|
||||
def __init__(self, channels):
|
||||
super(Decoder, self).__init__()
|
||||
self.config = Config()
|
||||
DecoderBlock = eval('BasicDecBlk')
|
||||
LateralBlock = eval('BasicLatBlk')
|
||||
|
||||
self.decoder_block4 = DecoderBlock(channels[0], channels[1])
|
||||
self.decoder_block3 = DecoderBlock(channels[1], channels[2])
|
||||
self.decoder_block2 = DecoderBlock(channels[2], channels[3])
|
||||
self.decoder_block1 = DecoderBlock(channels[3], channels[3]//2)
|
||||
|
||||
self.lateral_block4 = LateralBlock(channels[1], channels[1])
|
||||
self.lateral_block3 = LateralBlock(channels[2], channels[2])
|
||||
self.lateral_block2 = LateralBlock(channels[3], channels[3])
|
||||
|
||||
if self.config.ms_supervision:
|
||||
self.conv_ms_spvn_4 = nn.Conv2d(channels[1], 1, 1, 1, 0)
|
||||
self.conv_ms_spvn_3 = nn.Conv2d(channels[2], 1, 1, 1, 0)
|
||||
self.conv_ms_spvn_2 = nn.Conv2d(channels[3], 1, 1, 1, 0)
|
||||
self.conv_out1 = nn.Sequential(nn.Conv2d(channels[3]//2, 1, 1, 1, 0))
|
||||
|
||||
def forward(self, features):
|
||||
x, x1, x2, x3, x4 = features
|
||||
outs = []
|
||||
p4 = self.decoder_block4(x4)
|
||||
_p4 = F.interpolate(p4, size=x3.shape[2:], mode='bilinear', align_corners=True)
|
||||
_p3 = _p4 + self.lateral_block4(x3)
|
||||
|
||||
p3 = self.decoder_block3(_p3)
|
||||
_p3 = F.interpolate(p3, size=x2.shape[2:], mode='bilinear', align_corners=True)
|
||||
_p2 = _p3 + self.lateral_block3(x2)
|
||||
|
||||
p2 = self.decoder_block2(_p2)
|
||||
_p2 = F.interpolate(p2, size=x1.shape[2:], mode='bilinear', align_corners=True)
|
||||
_p1 = _p2 + self.lateral_block2(x1)
|
||||
|
||||
_p1 = self.decoder_block1(_p1)
|
||||
_p1 = F.interpolate(_p1, size=x.shape[2:], mode='bilinear', align_corners=True)
|
||||
p1_out = self.conv_out1(_p1)
|
||||
|
||||
if self.config.ms_supervision:
|
||||
outs.append(self.conv_ms_spvn_4(p4))
|
||||
outs.append(self.conv_ms_spvn_3(p3))
|
||||
outs.append(self.conv_ms_spvn_2(p2))
|
||||
outs.append(p1_out)
|
||||
return outs
|
||||
|
||||
|
||||
class RefUNet(nn.Module):
|
||||
# Refinement
|
||||
def __init__(self, in_channels=3+1):
|
||||
super(RefUNet, self).__init__()
|
||||
self.encoder_1 = nn.Sequential(
|
||||
nn.Conv2d(in_channels, 64, 3, 1, 1),
|
||||
nn.Conv2d(64, 64, 3, 1, 1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True)
|
||||
)
|
||||
|
||||
self.encoder_2 = nn.Sequential(
|
||||
nn.MaxPool2d(2, 2, ceil_mode=True),
|
||||
nn.Conv2d(64, 64, 3, 1, 1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True)
|
||||
)
|
||||
|
||||
self.encoder_3 = nn.Sequential(
|
||||
nn.MaxPool2d(2, 2, ceil_mode=True),
|
||||
nn.Conv2d(64, 64, 3, 1, 1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True)
|
||||
)
|
||||
|
||||
self.encoder_4 = nn.Sequential(
|
||||
nn.MaxPool2d(2, 2, ceil_mode=True),
|
||||
nn.Conv2d(64, 64, 3, 1, 1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True)
|
||||
)
|
||||
|
||||
self.pool4 = nn.MaxPool2d(2, 2, ceil_mode=True)
|
||||
#####
|
||||
self.decoder_5 = nn.Sequential(
|
||||
nn.Conv2d(64, 64, 3, 1, 1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True)
|
||||
)
|
||||
#####
|
||||
self.decoder_4 = nn.Sequential(
|
||||
nn.Conv2d(128, 64, 3, 1, 1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True)
|
||||
)
|
||||
|
||||
self.decoder_3 = nn.Sequential(
|
||||
nn.Conv2d(128, 64, 3, 1, 1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True)
|
||||
)
|
||||
|
||||
self.decoder_2 = nn.Sequential(
|
||||
nn.Conv2d(128, 64, 3, 1, 1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True)
|
||||
)
|
||||
|
||||
self.decoder_1 = nn.Sequential(
|
||||
nn.Conv2d(128, 64, 3, 1, 1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True)
|
||||
)
|
||||
|
||||
self.conv_d0 = nn.Conv2d(64, 1, 3, 1, 1)
|
||||
|
||||
self.upscore2 = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
|
||||
|
||||
def forward(self, x):
|
||||
outs = []
|
||||
if isinstance(x, list):
|
||||
x = torch.cat(x, dim=1)
|
||||
hx = x
|
||||
|
||||
hx1 = self.encoder_1(hx)
|
||||
hx2 = self.encoder_2(hx1)
|
||||
hx3 = self.encoder_3(hx2)
|
||||
hx4 = self.encoder_4(hx3)
|
||||
|
||||
hx = self.decoder_5(self.pool4(hx4))
|
||||
hx = torch.cat((self.upscore2(hx), hx4), 1)
|
||||
|
||||
d4 = self.decoder_4(hx)
|
||||
hx = torch.cat((self.upscore2(d4), hx3), 1)
|
||||
|
||||
d3 = self.decoder_3(hx)
|
||||
hx = torch.cat((self.upscore2(d3), hx2), 1)
|
||||
|
||||
d2 = self.decoder_2(hx)
|
||||
hx = torch.cat((self.upscore2(d2), hx1), 1)
|
||||
|
||||
d1 = self.decoder_1(hx)
|
||||
|
||||
x = self.conv_d0(d1)
|
||||
outs.append(x)
|
||||
return outs
|
||||
@@ -0,0 +1,45 @@
|
||||
import torch.nn as nn
|
||||
from birefnet_old.models.modules.utils import build_act_layer, build_norm_layer
|
||||
|
||||
|
||||
class StemLayer(nn.Module):
|
||||
r""" Stem layer of InternImage
|
||||
Args:
|
||||
in_channels (int): number of input channels
|
||||
out_channels (int): number of output channels
|
||||
act_layer (str): activation layer
|
||||
norm_layer (str): normalization layer
|
||||
"""
|
||||
|
||||
def __init__(self,
|
||||
in_channels=3+1,
|
||||
inter_channels=48,
|
||||
out_channels=96,
|
||||
act_layer='GELU',
|
||||
norm_layer='BN'):
|
||||
super().__init__()
|
||||
self.conv1 = nn.Conv2d(in_channels,
|
||||
inter_channels,
|
||||
kernel_size=3,
|
||||
stride=1,
|
||||
padding=1)
|
||||
self.norm1 = build_norm_layer(
|
||||
inter_channels, norm_layer, 'channels_first', 'channels_first'
|
||||
)
|
||||
self.act = build_act_layer(act_layer)
|
||||
self.conv2 = nn.Conv2d(inter_channels,
|
||||
out_channels,
|
||||
kernel_size=3,
|
||||
stride=1,
|
||||
padding=1)
|
||||
self.norm2 = build_norm_layer(
|
||||
out_channels, norm_layer, 'channels_first', 'channels_first'
|
||||
)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.conv1(x)
|
||||
x = self.norm1(x)
|
||||
x = self.act(x)
|
||||
x = self.conv2(x)
|
||||
x = self.norm2(x)
|
||||
return x
|
||||
@@ -0,0 +1,85 @@
|
||||
from PIL import Image, ImageEnhance
|
||||
import random
|
||||
import numpy as np
|
||||
import random
|
||||
|
||||
|
||||
def preproc(image, label, preproc_methods=['flip']):
|
||||
if 'flip' in preproc_methods:
|
||||
image, label = cv_random_flip(image, label)
|
||||
if 'crop' in preproc_methods:
|
||||
image, label = random_crop(image, label)
|
||||
if 'rotate' in preproc_methods:
|
||||
image, label = random_rotate(image, label)
|
||||
if 'enhance' in preproc_methods:
|
||||
image = color_enhance(image)
|
||||
if 'pepper' in preproc_methods:
|
||||
label = random_pepper(label)
|
||||
return image, label
|
||||
|
||||
|
||||
def cv_random_flip(img, label):
|
||||
if random.random() > 0.5:
|
||||
img = img.transpose(Image.FLIP_LEFT_RIGHT)
|
||||
label = label.transpose(Image.FLIP_LEFT_RIGHT)
|
||||
return img, label
|
||||
|
||||
|
||||
def random_crop(image, label):
|
||||
border = 30
|
||||
image_width = image.size[0]
|
||||
image_height = image.size[1]
|
||||
border = int(min(image_width, image_height) * 0.1)
|
||||
crop_win_width = np.random.randint(image_width - border, image_width)
|
||||
crop_win_height = np.random.randint(image_height - border, image_height)
|
||||
random_region = (
|
||||
(image_width - crop_win_width) >> 1, (image_height - crop_win_height) >> 1, (image_width + crop_win_width) >> 1,
|
||||
(image_height + crop_win_height) >> 1)
|
||||
return image.crop(random_region), label.crop(random_region)
|
||||
|
||||
|
||||
def random_rotate(image, label, angle=15):
|
||||
mode = Image.BICUBIC
|
||||
if random.random() > 0.8:
|
||||
random_angle = np.random.randint(-angle, angle)
|
||||
image = image.rotate(random_angle, mode)
|
||||
label = label.rotate(random_angle, mode)
|
||||
return image, label
|
||||
|
||||
|
||||
def color_enhance(image):
|
||||
bright_intensity = random.randint(5, 15) / 10.0
|
||||
image = ImageEnhance.Brightness(image).enhance(bright_intensity)
|
||||
contrast_intensity = random.randint(5, 15) / 10.0
|
||||
image = ImageEnhance.Contrast(image).enhance(contrast_intensity)
|
||||
color_intensity = random.randint(0, 20) / 10.0
|
||||
image = ImageEnhance.Color(image).enhance(color_intensity)
|
||||
sharp_intensity = random.randint(0, 30) / 10.0
|
||||
image = ImageEnhance.Sharpness(image).enhance(sharp_intensity)
|
||||
return image
|
||||
|
||||
|
||||
def random_gaussian(image, mean=0.1, sigma=0.35):
|
||||
def gaussianNoisy(im, mean=mean, sigma=sigma):
|
||||
for _i in range(len(im)):
|
||||
im[_i] += random.gauss(mean, sigma)
|
||||
return im
|
||||
|
||||
img = np.asarray(image)
|
||||
width, height = img.shape
|
||||
img = gaussianNoisy(img[:].flatten(), mean, sigma)
|
||||
img = img.reshape([width, height])
|
||||
return Image.fromarray(np.uint8(img))
|
||||
|
||||
|
||||
def random_pepper(img, N=0.0015):
|
||||
img = np.array(img)
|
||||
noiseNum = int(N * img.shape[0] * img.shape[1])
|
||||
for i in range(noiseNum):
|
||||
randX = random.randint(0, img.shape[0] - 1)
|
||||
randY = random.randint(0, img.shape[1] - 1)
|
||||
if random.randint(0, 1) == 0:
|
||||
img[randX, randY] = 0
|
||||
else:
|
||||
img[randX, randY] = 255
|
||||
return Image.fromarray(img)
|
||||
@@ -0,0 +1,97 @@
|
||||
import logging
|
||||
import os
|
||||
import torch
|
||||
from torchvision import transforms
|
||||
import numpy as np
|
||||
import random
|
||||
import cv2
|
||||
from PIL import Image
|
||||
|
||||
|
||||
def path_to_image(path, size=(1024, 1024), color_type=['rgb', 'gray'][0]):
|
||||
if color_type.lower() == 'rgb':
|
||||
image = cv2.imread(path)
|
||||
elif color_type.lower() == 'gray':
|
||||
image = cv2.imread(path, cv2.IMREAD_GRAYSCALE)
|
||||
else:
|
||||
print('Select the color_type to return, either to RGB or gray image.')
|
||||
return
|
||||
if size:
|
||||
image = cv2.resize(image, size, interpolation=cv2.INTER_LINEAR)
|
||||
if color_type.lower() == 'rgb':
|
||||
image = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB)).convert('RGB')
|
||||
else:
|
||||
image = Image.fromarray(image).convert('L')
|
||||
return image
|
||||
|
||||
|
||||
|
||||
def check_state_dict(state_dict, unwanted_prefix='_orig_mod.'):
|
||||
for k, v in list(state_dict.items()):
|
||||
if k.startswith(unwanted_prefix):
|
||||
state_dict[k[len(unwanted_prefix):]] = state_dict.pop(k)
|
||||
return state_dict
|
||||
|
||||
|
||||
def generate_smoothed_gt(gts):
|
||||
epsilon = 0.001
|
||||
new_gts = (1-epsilon)*gts+epsilon/2
|
||||
return new_gts
|
||||
|
||||
|
||||
class Logger():
|
||||
def __init__(self, path="log.txt"):
|
||||
self.logger = logging.getLogger('BiRefNet')
|
||||
self.file_handler = logging.FileHandler(path, "w")
|
||||
self.stdout_handler = logging.StreamHandler()
|
||||
self.stdout_handler.setFormatter(logging.Formatter('%(asctime)s %(levelname)s %(message)s'))
|
||||
self.file_handler.setFormatter(logging.Formatter('%(asctime)s %(levelname)s %(message)s'))
|
||||
self.logger.addHandler(self.file_handler)
|
||||
self.logger.addHandler(self.stdout_handler)
|
||||
self.logger.setLevel(logging.INFO)
|
||||
self.logger.propagate = False
|
||||
|
||||
def info(self, txt):
|
||||
self.logger.info(txt)
|
||||
|
||||
def close(self):
|
||||
self.file_handler.close()
|
||||
self.stdout_handler.close()
|
||||
|
||||
|
||||
class AverageMeter(object):
|
||||
"""Computes and stores the average and current value"""
|
||||
def __init__(self):
|
||||
self.reset()
|
||||
|
||||
def reset(self):
|
||||
self.val = 0.0
|
||||
self.avg = 0.0
|
||||
self.sum = 0.0
|
||||
self.count = 0.0
|
||||
|
||||
def update(self, val, n=1):
|
||||
self.val = val
|
||||
self.sum += val * n
|
||||
self.count += n
|
||||
self.avg = self.sum / self.count
|
||||
|
||||
|
||||
def save_checkpoint(state, path, filename="latest.pth"):
|
||||
torch.save(state, os.path.join(path, filename))
|
||||
|
||||
|
||||
def save_tensor_img(tenor_im, path):
|
||||
im = tenor_im.cpu().clone()
|
||||
im = im.squeeze(0)
|
||||
tensor2pil = transforms.ToPILImage()
|
||||
im = tensor2pil(im)
|
||||
im.save(path)
|
||||
|
||||
|
||||
def set_seed(seed):
|
||||
torch.manual_seed(seed)
|
||||
torch.cuda.manual_seed_all(seed)
|
||||
np.random.seed(seed)
|
||||
random.seed(seed)
|
||||
torch.backends.cudnn.deterministic = True
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
[project]
|
||||
name = "comfyui_birefnet_ll"
|
||||
description = "Sync with version of BiRefNet. NODES:AutoDownloadBiRefNetModel, LoadRembgByBiRefNetModel, RembgByBiRefNet, RembgByBiRefNetAdvanced, GetMaskByBiRefNet, BlurFusionForegroundEstimation."
|
||||
version = "1.1.4"
|
||||
license = {file = "LICENSE"}
|
||||
dependencies = ["numpy", "opencv-python", "timm"]
|
||||
|
||||
[project.urls]
|
||||
Repository = "https://github.com/lldacing/ComfyUI_BiRefNet_ll"
|
||||
# Used by Comfy Registry https://comfyregistry.org
|
||||
|
||||
[tool.comfy]
|
||||
PublisherId = "lldacing"
|
||||
DisplayName = "ComfyUI_BiRefNet_ll"
|
||||
Icon = ""
|
||||
+3
@@ -0,0 +1,3 @@
|
||||
numpy
|
||||
opencv-python
|
||||
timm
|
||||
Reference in New Issue
Block a user