liav
/
lut_reproduce
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

reset cache arg. hbdnet change.

Browse Source
main
protsenkovi 5 months ago
parent df56917042
commit 39f830d6e5
6 changed files with 71 additions and 61 deletions
Show Stats Download Patch File Download Diff File

16
src/common/data.py
Unescape Escape View File

@ -11,11 +11,11 @@ from pathlib import Path
from common.utils import PIL_CONVERT_COLOR, pil2numpy from common.utils import PIL_CONVERT_COLOR, pil2numpy
image_extensions = ['.jpg', '.png'] image_extensions = ['.jpg', '.png']
def load_images_cached(images_dir_path, color_model): def load_images_cached(images_dir_path, color_model, reset_cache):
image_paths = sorted([f for f in Path(images_dir_path).glob("*") if f.suffix.lower() in image_extensions]) image_paths = sorted([f for f in Path(images_dir_path).glob("*") if f.suffix.lower() in image_extensions])
cache_path = Path(images_dir_path).parent / f"{Path(images_dir_path).stem}_{color_model}_cache.npy" cache_path = Path(images_dir_path).parent / f"{Path(images_dir_path).stem}_{color_model}_cache.npy"
cache_path = cache_path.resolve() cache_path = cache_path.resolve()
if not Path(cache_path).exists(): if not Path(cache_path).exists() or reset_cache:
print("Caching to:", cache_path) print("Caching to:", cache_path)
value = {f:pil2numpy(PIL_CONVERT_COLOR[color_model](Image.open(f))) for f in image_paths} value = {f:pil2numpy(PIL_CONVERT_COLOR[color_model](Image.open(f))) for f in image_paths}
np.save(cache_path, value, allow_pickle=True) np.save(cache_path, value, allow_pickle=True)
@ -25,12 +25,12 @@ def load_images_cached(images_dir_path, color_model):
return list(value.keys()), list(value.values()) return list(value.keys()), list(value.values())
class SRTrainDataset(Dataset): class SRTrainDataset(Dataset):
def __init__(self, hr_dir_path, lr_dir_path, patch_size, color_model = "RGB", rigid_aug=True): def __init__(self, hr_dir_path, lr_dir_path, patch_size, color_model = "RGB", rigid_aug=True, reset_cache = False):
super(SRTrainDataset, self).__init__() super(SRTrainDataset, self).__init__()
self.sz = patch_size self.sz = patch_size
self.rigid_aug = rigid_aug self.rigid_aug = rigid_aug
self.hr_image_names, self.hr_images = load_images_cached(hr_dir_path, color_model=color_model) self.hr_image_names, self.hr_images = load_images_cached(hr_dir_path, color_model=color_model, reset_cache=reset_cache)
self.lr_image_names, self.lr_images = load_images_cached(lr_dir_path, color_model=color_model) self.lr_image_names, self.lr_images = load_images_cached(lr_dir_path, color_model=color_model, reset_cache=reset_cache)
assert len(self.hr_images) == len(self.lr_images) assert len(self.hr_images) == len(self.lr_images)
def __getitem__(self, idx): def __getitem__(self, idx):
@ -87,10 +87,10 @@ class SRTrainDataset(Dataset):
return len(self.hr_images) return len(self.hr_images)
class SRTestDataset(Dataset): class SRTestDataset(Dataset):
def __init__(self, hr_dir_path, lr_dir_path, color_model): def __init__(self, hr_dir_path, lr_dir_path, color_model, reset_cache):
super(SRTestDataset, self).__init__() super(SRTestDataset, self).__init__()
self.hr_image_paths, self.hr_images = load_images_cached(hr_dir_path, color_model=color_model) self.hr_image_paths, self.hr_images = load_images_cached(hr_dir_path, color_model=color_model, reset_cache=reset_cache)
self.lr_image_paths, self.lr_images = load_images_cached(lr_dir_path, color_model=color_model) self.lr_image_paths, self.lr_images = load_images_cached(lr_dir_path, color_model=color_model, reset_cache=reset_cache)
assert len(self.hr_images) == len(self.lr_images) assert len(self.hr_images) == len(self.lr_images)
def __getitem__(self, idx): def __getitem__(self, idx):

1
src/common/utils.py
Unescape Escape View File

@ -10,6 +10,7 @@ PIL_CONVERT_COLOR = {
'RGB': lambda pil_image: pil_image.convert("RGB") if pil_image.mode != 'RGB' else pil_image, 'RGB': lambda pil_image: pil_image.convert("RGB") if pil_image.mode != 'RGB' else pil_image,
'YCbCr': lambda pil_image: pil_image.convert("YCbCr") if pil_image.mode != 'YCbCr' else pil_image, 'YCbCr': lambda pil_image: pil_image.convert("YCbCr") if pil_image.mode != 'YCbCr' else pil_image,
'Y': lambda pil_image: pil_image.convert("YCbCr").getchannel(0) if pil_image.mode != 'YCbCr' else pil_image.getchannel(0), 'Y': lambda pil_image: pil_image.convert("YCbCr").getchannel(0) if pil_image.mode != 'YCbCr' else pil_image.getchannel(0),
# 'Y': lambda pil_image: _rgb2ycbcr(np.array(pil_image))[:,:,0],# if pil_image.mode != 'YCbCr' else pil_image.getchannel(0),
'L': lambda pil_image: pil_image.convert("L") if pil_image.mode != 'L' else pil_image, 'L': lambda pil_image: pil_image.convert("L") if pil_image.mode != 'L' else pil_image,
} }

2
src/common/validation.py
Unescape Escape View File

@ -74,7 +74,7 @@ def valid_steps(model, datasets, config, log_prefix="", print_progress = False):
task = val_image_pair(model, hr_image, lr_image, color_model=config.color_model, output_image_path=output_image_path, device=config.device) task = val_image_pair(model, hr_image, lr_image, color_model=config.color_model, output_image_path=output_image_path, device=config.device)
tasks.append(task) tasks.append(task)
if print_progress: if print_progress:
print(f"\r{datetime.now()-start_datetime} {idx}/{len(test_dataset)} {hr_image_path}", end=" "*25) print(f"\r{datetime.now()-start_datetime} {idx+1}/{len(test_dataset)} {hr_image_path}", end=" "*25)
if print_progress: if print_progress:
print() print()
total_time = time.time() - start_time total_time = time.time() - start_time

94
src/models/hdbnet.py
Unescape Escape View File

@ -8,23 +8,24 @@ from pathlib import Path
from . import hdblut from . import hdblut
from common import layers from common import layers
from itertools import cycle from itertools import cycle
from models.base import SRNetBase
class HDBNet(nn.Module): class HDBNet(SRNetBase):
def __init__(self, hidden_dim = 64, layers_count = 4, scale = 4): def __init__(self, hidden_dim = 64, layers_count = 4, scale = 4):
super(HDBNet, self).__init__() super(HDBNet, self).__init__()
assert scale == 4 assert scale == 4
self.scale = scale self.scale = scale
self.stage1_3H = layers.UpscaleBlock(in_features=3, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2*2) self.stage1_3H = layers.UpscaleBlock(in_features=3, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2, input_max_value=255, output_max_value=255)
self.stage1_3D = layers.UpscaleBlock(in_features=3, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2*2) self.stage1_3D = layers.UpscaleBlock(in_features=3, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2, input_max_value=255, output_max_value=255)
self.stage1_3B = layers.UpscaleBlock(in_features=3, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2*2) self.stage1_3B = layers.UpscaleBlock(in_features=3, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2, input_max_value=255, output_max_value=255)
self.stage1_2H = layers.UpscaleBlock(in_features=2, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2*2) self.stage1_2H = layers.UpscaleBlock(in_features=2, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2, input_max_value=15, output_max_value=255)
self.stage1_2D = layers.UpscaleBlock(in_features=2, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2*2) self.stage1_2D = layers.UpscaleBlock(in_features=2, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2, input_max_value=15, output_max_value=255)
# self.stage2_3H = layers.UpscaleBlock(in_features=3, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2) self.stage2_3H = layers.UpscaleBlock(in_features=3, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2, input_max_value=255, output_max_value=255)
# self.stage2_3D = layers.UpscaleBlock(in_features=3, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2) self.stage2_3D = layers.UpscaleBlock(in_features=3, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2, input_max_value=255, output_max_value=255)
# self.stage2_3B = layers.UpscaleBlock(in_features=3, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2) self.stage2_3B = layers.UpscaleBlock(in_features=3, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2, input_max_value=255, output_max_value=255)
# self.stage2_2H = layers.UpscaleBlock(in_features=2, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2) self.stage2_2H = layers.UpscaleBlock(in_features=2, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2, input_max_value=15, output_max_value=255)
# self.stage2_2D = layers.UpscaleBlock(in_features=2, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2) self.stage2_2D = layers.UpscaleBlock(in_features=2, hidden_dim=hidden_dim, layers_count=layers_count, upscale_factor=2, input_max_value=15, output_max_value=255)
self._extract_pattern_3H = layers.PercievePattern(receptive_field_idxes=[[0,0],[0,1],[0,2]], center=[0,0], window_size=3) self._extract_pattern_3H = layers.PercievePattern(receptive_field_idxes=[[0,0],[0,1],[0,2]], center=[0,0], window_size=3)
self._extract_pattern_3D = layers.PercievePattern(receptive_field_idxes=[[0,0],[1,1],[2,2]], center=[0,0], window_size=3) self._extract_pattern_3D = layers.PercievePattern(receptive_field_idxes=[[0,0],[1,1],[2,2]], center=[0,0], window_size=3)
@ -32,6 +33,8 @@ class HDBNet(nn.Module):
self._extract_pattern_2H = layers.PercievePattern(receptive_field_idxes=[[0,0],[0,1]], center=[0,0], window_size=2) self._extract_pattern_2H = layers.PercievePattern(receptive_field_idxes=[[0,0],[0,1]], center=[0,0], window_size=2)
self._extract_pattern_2D = layers.PercievePattern(receptive_field_idxes=[[0,0],[1,1]], center=[0,0], window_size=2) self._extract_pattern_2D = layers.PercievePattern(receptive_field_idxes=[[0,0],[1,1]], center=[0,0], window_size=2)
self.rotations = 4
def forward_stage(self, x, scale, percieve_pattern, stage): def forward_stage(self, x, scale, percieve_pattern, stage):
b,c,h,w = x.shape b,c,h,w = x.shape
x = percieve_pattern(x) x = percieve_pattern(x)
@ -47,41 +50,42 @@ class HDBNet(nn.Module):
x = x.reshape(b*c, 1, h, w) x = x.reshape(b*c, 1, h, w)
lsb = x % 16 lsb = x % 16
msb = x - lsb msb = x - lsb
output_msb = torch.zeros([b*c, 1, h*2*2, w*2*2], dtype=x.dtype, device=x.device) output = torch.zeros([b*c, 1, h*2, w*2], dtype=x.dtype, device=x.device)
output_lsb = torch.zeros([b*c, 1, h*2*2, w*2*2], dtype=x.dtype, device=x.device) for rotations_count in range(self.rotations):
for rotations_count in range(4):
rotated_msb = torch.rot90(msb, k=rotations_count, dims=[2, 3]) rotated_msb = torch.rot90(msb, k=rotations_count, dims=[2, 3])
rotated_lsb = torch.rot90(lsb, k=rotations_count, dims=[2, 3]) rotated_lsb = torch.rot90(lsb, k=rotations_count, dims=[2, 3])
output_msb += torch.rot90(self.forward_stage(rotated_msb, 2*2, self._extract_pattern_3H, self.stage1_3H), k=-rotations_count, dims=[2, 3]) output_msb = self.forward_stage(rotated_msb, 2, self._extract_pattern_3H, self.stage1_3H) + \
output_msb += torch.rot90(self.forward_stage(rotated_msb, 2*2, self._extract_pattern_3D, self.stage1_3D), k=-rotations_count, dims=[2, 3]) self.forward_stage(rotated_msb, 2, self._extract_pattern_3D, self.stage1_3D) + \
output_msb += torch.rot90(self.forward_stage(rotated_msb, 2*2, self._extract_pattern_3B, self.stage1_3B), k=-rotations_count, dims=[2, 3]) self.forward_stage(rotated_msb, 2, self._extract_pattern_3B, self.stage1_3B)
output_lsb += torch.rot90(self.forward_stage(rotated_lsb, 2*2, self._extract_pattern_2H, self.stage1_2H), k=-rotations_count, dims=[2, 3]) output_msb /= 3
output_lsb += torch.rot90(self.forward_stage(rotated_lsb, 2*2, self._extract_pattern_2D, self.stage1_2D), k=-rotations_count, dims=[2, 3]) output_lsb = self.forward_stage(rotated_lsb, 2, self._extract_pattern_2H, self.stage1_2H) + \
output_msb /= 4*3 self.forward_stage(rotated_lsb, 2, self._extract_pattern_2D, self.stage1_2D)
output_lsb /= 4*2 output_lsb /= 2
output_msb = round_func((output_msb / 255) * 16) * 15 if not config is None and config.current_iter % config.display_step == 0:
output_lsb = (output_lsb / 255) * 15 config.writer.add_histogram('s1_output_lsb', output_lsb.detach().cpu().numpy(), config.current_iter)
# print(output_msb.min(), output_msb.max(), output_lsb.min(), output_lsb.max()) config.writer.add_histogram('s1_output_msb', output_msb.detach().cpu().numpy(), config.current_iter)
x = output_msb + output_lsb output += torch.rot90(output_msb + output_lsb, k=-rotations_count, dims=[2, 3]).clamp(0, 255)
# lsb = x % 16 output /= self.rotations
# msb = x - lsb x = output
lsb = x % 16
# output_msb = torch.zeros([b*c, 1, h*4, w*4], dtype=x.dtype, device=x.device) msb = x - lsb
# output_lsb = torch.zeros([b*c, 1, h*4, w*4], dtype=x.dtype, device=x.device) output = torch.zeros([b*c, 1, h*4, w*4], dtype=x.dtype, device=x.device)
# for rotations_count in range(4): for rotations_count in range(self.rotations):
# rotated_msb = torch.rot90(msb, k=rotations_count, dims=[2, 3]) rotated_msb = torch.rot90(msb, k=rotations_count, dims=[2, 3])
# rotated_lsb = torch.rot90(lsb, k=rotations_count, dims=[2, 3]) rotated_lsb = torch.rot90(lsb, k=rotations_count, dims=[2, 3])
# output_msb += torch.rot90(self.forward_stage(rotated_msb, 2, self._extract_pattern_3H, self.stage2_3H), k=-rotations_count, dims=[2, 3]) output_msb = self.forward_stage(rotated_msb, 2, self._extract_pattern_3H, self.stage2_3H) + \
# output_msb += torch.rot90(self.forward_stage(rotated_msb, 2, self._extract_pattern_3D, self.stage2_3D), k=-rotations_count, dims=[2, 3]) self.forward_stage(rotated_msb, 2, self._extract_pattern_3D, self.stage2_3D) + \
# output_msb += torch.rot90(self.forward_stage(rotated_msb, 2, self._extract_pattern_3B, self.stage2_3B), k=-rotations_count, dims=[2, 3]) self.forward_stage(rotated_msb, 2, self._extract_pattern_3B, self.stage2_3B)
# output_lsb += torch.rot90(self.forward_stage(rotated_lsb, 2, self._extract_pattern_2H, self.stage2_2H), k=-rotations_count, dims=[2, 3]) output_msb /= 3
# output_lsb += torch.rot90(self.forward_stage(rotated_lsb, 2, self._extract_pattern_2D, self.stage2_2D), k=-rotations_count, dims=[2, 3]) output_lsb = self.forward_stage(rotated_lsb, 2, self._extract_pattern_2H, self.stage2_2H) + \
# output_msb /= 4*3 self.forward_stage(rotated_lsb, 2, self._extract_pattern_2D, self.stage2_2D)
# output_lsb /= 4*2 output_lsb /= 2
# output_msb = round_func((output_msb / 255) * 16) * 15 if not config is None and config.current_iter % config.display_step == 0:
# output_lsb = (output_lsb / 255) * 15 config.writer.add_histogram('s2_output_lsb', output_lsb.detach().cpu().numpy(), config.current_iter)
# # print(output_msb.min(), output_msb.max(), output_lsb.min(), output_lsb.max()) config.writer.add_histogram('s2_output_msb', output_msb.detach().cpu().numpy(), config.current_iter)
# x = output_msb + output_lsb output += torch.rot90(output_msb + output_lsb, k=-rotations_count, dims=[2, 3]).clamp(0, 255)
output /= self.rotations
x = output
x = x.reshape(b, c, h*self.scale, w*self.scale) x = x.reshape(b, c, h*self.scale, w*self.scale)
return x return x

4
src/test.py
Unescape Escape View File

@ -30,6 +30,7 @@ class ValOptions():
self.parser.add_argument('--device', type=str, default='cuda', help='Device of the model') self.parser.add_argument('--device', type=str, default='cuda', help='Device of the model')
self.parser.add_argument('--color_model', type=str, default="RGB", help="Color model for train and test dataset.") self.parser.add_argument('--color_model', type=str, default="RGB", help="Color model for train and test dataset.")
self.parser.add_argument('--progress', type=bool, default=True, help='Show progres bar') self.parser.add_argument('--progress', type=bool, default=True, help='Show progres bar')
self.parser.add_argument('--reset_cache', action='store_true', default=False, help='Discard datasets cache')
def parse_args(self): def parse_args(self):
args = self.parser.parse_args() args = self.parser.parse_args()
@ -84,7 +85,8 @@ if __name__ == "__main__":
test_datasets[test_dataset_name] = SRTestDataset( test_datasets[test_dataset_name] = SRTestDataset(
hr_dir_path = Path(config.datasets_dir) / test_dataset_name / "HR", hr_dir_path = Path(config.datasets_dir) / test_dataset_name / "HR",
lr_dir_path = Path(config.datasets_dir) / test_dataset_name / "LR" / f"X{model.scale}", lr_dir_path = Path(config.datasets_dir) / test_dataset_name / "LR" / f"X{model.scale}",
color_model=config.color_model color_model=config.color_model,
reset_cache=config.reset_cache,
) )
results = valid_steps(model=model, datasets=test_datasets, config=config, log_prefix=f"Model {config.model_name}", print_progress=config.progress) results = valid_steps(model=model, datasets=test_datasets, config=config, log_prefix=f"Model {config.model_name}", print_progress=config.progress)

7
src/train.py
Unescape Escape View File

@ -49,6 +49,7 @@ class TrainOptions:
parser.add_argument('--device', default='cuda', help='Device of the model') parser.add_argument('--device', default='cuda', help='Device of the model')
parser.add_argument('--quantization_bits', '-q', type=int, default=4, help="Used when model is LUT. Number of 4DLUT buckets defined as 2**bits. Value is in range [1, 8].") parser.add_argument('--quantization_bits', '-q', type=int, default=4, help="Used when model is LUT. Number of 4DLUT buckets defined as 2**bits. Value is in range [1, 8].")
parser.add_argument('--color_model', type=str, default="RGB", help="Color model for train and test dataset.") parser.add_argument('--color_model', type=str, default="RGB", help="Color model for train and test dataset.")
parser.add_argument('--reset_cache', action='store_true', default=False, help='Discard datasets cache')
self.parser = parser self.parser = parser
@ -137,7 +138,8 @@ if __name__ == "__main__":
hr_dir_path = Path(config.datasets_dir) / train_dataset_name / "HR", hr_dir_path = Path(config.datasets_dir) / train_dataset_name / "HR",
lr_dir_path = Path(config.datasets_dir) / train_dataset_name / "LR" / f"X{config.scale}", lr_dir_path = Path(config.datasets_dir) / train_dataset_name / "LR" / f"X{config.scale}",
patch_size = config.crop_size, patch_size = config.crop_size,
color_model = config.color_model color_model = config.color_model,
reset_cache=config.reset_cache
)) ))
train_dataset = torch.utils.data.ConcatDataset(train_datasets) train_dataset = torch.utils.data.ConcatDataset(train_datasets)
train_loader = DataLoader( train_loader = DataLoader(
@ -156,7 +158,8 @@ if __name__ == "__main__":
test_datasets[test_dataset_name] = SRTestDataset( test_datasets[test_dataset_name] = SRTestDataset(
hr_dir_path = Path(config.datasets_dir) / test_dataset_name / "HR", hr_dir_path = Path(config.datasets_dir) / test_dataset_name / "HR",
lr_dir_path = Path(config.datasets_dir) / test_dataset_name / "LR" / f"X{config.scale}", lr_dir_path = Path(config.datasets_dir) / test_dataset_name / "LR" / f"X{config.scale}",
color_model = config.color_model color_model = config.color_model,
reset_cache=config.reset_cache
) )
l_accum = [0., 0., 0.] l_accum = [0., 0., 0.]
prepare_data_time = 0. prepare_data_time = 0.

Write Preview
Loading…
Cancel
Save