def transform_ts(self, sample):
composed_transforms = transforms.Compose([
# tr.FixedResize(size=self.args.crop_size),
tr.Normalize(mean=(0.279, 0.293, 0.290),
std=(0.197, 0.198, 0.201)),
tr.ToTensor()
])
return composed_transforms(sample)
def transform_val(self, sample):
composed_transforms = transforms.Compose([
tr.FixScaleCrop(crop_size=self.args.crop_size),
tr.Normalize(mean=(0.485, 0.456, 0.406),
std=(0.229, 0.224, 0.225)),
tr.ToTensor()
])
return composed_transforms(sample)
def transform_ts(self, sample):
composed_transforms = transforms.Compose([
tr.FixedResize(size=self.crop_size),
tr.Normalize(mean=(0.3416, 0.3416, 0.3416),
std=(0.1889, 0.1889, 0.1889)),
tr.ToTensor()
])
return composed_transforms(sample)
def transform_tr(self, sample: dict):
sample_transforms = transforms.Compose([
ctr.RandomCrop(size=self.settings['rnd_crop_size']),
ctr.RandomHorizontalFlip(p=0.5),
ctr.ToTensor(),
ctr.Normalize(**self.settings['normalize_params'],
apply_to=['image']),
ctr.Squeeze(apply_to=['label']),
])
return sample_transforms(sample)
def transform_val(self, sample):
composed_transforms = transforms.Compose([
tr.RandomHorizontalFlip(),
tr.RandomCrop(crop_size=(512, 512)),
tr.Normalize(mean=(0.485, 0.456, 0.406),
std=(0.229, 0.224, 0.225)),
tr.ToTensor()
])
return composed_transforms(sample)
def transform_tr(self, sample):
# composed_transforms = transforms.Compose([
# tr.RandomHorizontalFlip(),
# tr.RandomScaleCrop(base_size=self.args.base_size, crop_size=self.args.crop_size),
# tr.RandomGaussianBlur(),
# tr.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
# tr.ToTensor()])
composed_transforms = transforms.Compose([tr.ToTensor()])
return composed_transforms(sample)
def transform_tr(self, sample):
composed_transforms = transforms.Compose([
tr.FixedCrop(x1=280, x2=1000, y1=50, y2=562),
tr.RandomHorizontalFlip(),
tr.Normalize(mean=(0.485, 0.456, 0.406),
std=(0.229, 0.224, 0.225)),
tr.ToTensor()
])
return composed_transforms(sample)
def transform_tr(self, sample):
composed_transforms = transforms.Compose([
# tr.RandomHorizontalFlip(),
# tr.RandomScaleCrop(base_size=self.args.base_size, crop_size=self.args.crop_size, fill=255),
tr.RandomGaussianBlur(),
tr.Normalize(mean=(0.279, 0.293, 0.290),
std=(0.197, 0.198, 0.201)),
tr.ToTensor()
])
return composed_transforms(sample)
def transform(sample, cropsize=IMAGE_SIZE[1], offset=690):#####################此处更改IMAGE_SIZE选择
roi_image = sample['image'].crop((0,offset,3384,1710))
roi_label = sample['label'].crop((0,offset,3384,1710))
sample['image'] = roi_image.resize(cropsize, Image.BILINEAR)
sample['label'] = roi_label.resize(cropsize, Image.NEAREST)
composed_transform = transforms.Compose([
# tr.RandomHorizontalFlip(),
# tr.RandomGaussianBlur(),
tr.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
tr.ToTensor()])
return composed_transform(sample)
def transform_val(self, sample):
composed_transforms = transforms.Compose([
tr.FixScaleCrop(crop_size=self.crop_size),
tr.Normalize(mean=[0.4911], std=[0.1658]),
tr.ToTensor()
])
transformed = composed_transforms(sample)
transformed['image'] = transformed['image'].unsqueeze(0)
return transformed
def transform_tr(self, sample):
composed_transforms = transforms.Compose([
FixedResize(resize=self.args.resize),
RandomCrop(crop_size=self.args.crop_size),
#tr.RandomGaussianBlur(),
tr.Normalize(mean=(0.485, 0.456, 0.406),
std=(0.229, 0.224, 0.225)),
tr.ToTensor()
])
return composed_transforms(sample)
def transform_train(self, sample):
composed_transforms = transforms.Compose([
#tr.RandomHorizontalFlip(),
#tr.RandomRotate(10),
#tr.RandomScaleCrop(base_size=self.args.base_size, crop_size=self.args.crop_size),
#tr.RandomGaussianBlur(),
tr.AddAxis(),
tr.Normalize(),
tr.ToTensor()])
return composed_transforms(sample)
def transform_ts(self, sample):
"""Image transformations for testing"""
targs = self.transform
method = targs["method"]
pars = targs["parameters"]
composed_transforms = transforms.Compose([
tr.FixedResize(size=pars["outSize"]),
tr.Normalize(mean=pars["mean"], std=pars["std"]),
tr.ToTensor()])
return composed_transforms(sample)
def transform_tr(self, sample):
composed_transforms = transforms.Compose([
tr.FixedResize(size=(1024, 2048)),
tr.ColorJitter(),
tr.RandomGaussianBlur(),
tr.RandomMotionBlur(),
tr.RandomHorizontalFlip(),
tr.RandomScaleCrop(base_size=self.args.base_size, crop_size=self.args.crop_size, fill=255),
tr.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
tr.ToTensor()])
return composed_transforms(sample)
def __init__(self, inputRes=None, samples_list_file='/home/xk/PycharmProjects/Pred_Seg/data/DAVIS16_samples_list.txt', transform=None, num_frame=4): f = open(samples_list_file, "r") lines = f.readlines() self.samples_list = lines self.transform = transform self.inputRes = inputRes self.toTensor = tr.ToTensor() self.num_frame = num_frame
def transform_val(self, sample):
"""Image transformations for validation"""
targs = self.transform
method = targs["method"]
pars = targs["parameters"]
composed_transforms = transforms.Compose([
tr.FixedResize(size=pars["outSize"]),
tr.FixScaleCrop(cropSize=pars["outSize"]),
tr.Normalize(mean=pars["mean"], std=(pars["std"])),
tr.ToTensor()])
return composed_transforms(sample)
def transform_train(self, sample):
composed_transforms = transforms.Compose([
tr.FixScaleCrop(crop_size=self.crop_size),
tr.RandomHorizontalFlip(),
tr.RandomGaussianBlur(),
tr.Normalize(mean=[0.4911], std=[0.1658]),
tr.ToTensor()
])
transformed = composed_transforms(sample)
transformed['image'] = transformed['image'].unsqueeze(0)
return transformed
def transform_tr(self, sample):
composed_transforms = transforms.Compose([
tr.ColorJitter(brightness=0.5, contrast=0.5, saturation=0.5),
#tr.RandomGaussianBlur(),
tr.HorizontalFlip(),
tr.RandomScale(),
tr.RandomCrop(size=(self.args.crop_size, self.args.crop_size)),
tr.Normalize(mean=(0.485, 0.456, 0.406),
std=(0.229, 0.224, 0.225)),
tr.ToTensor()
])
return composed_transforms(sample)
def transform_tr(self, sample):
composed_transforms = transforms.Compose([
tr.RandomHorizontalFlip(),
#tr.FixScaleCrop(crop_size=self.args['crop_size']),
tr.FixedResize(size=self.args['crop_size']),
#tr.RandomScaleCrop(base_size=self.args['base_size'], crop_size=self.args['crop_size'], min_scale = 1.0, max_scale = 1.5),
#tr.RandomGaussianBlur(),
tr.Normalize(mean=self.mean, std=self.std),
tr.ToTensor()
])
return composed_transforms(sample)
def transform_train(self, sample):
composed_transforms = transforms.Compose([
self.scalecrop,
tr.RandomHorizontalFlip(),
#tr.RandomScaleCrop(base_size=self.base_size, crop_size=self.crop_size, fill=255),
tr.RandomGaussianBlur(),
tr.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
tr.ToTensor()
])
return composed_transforms(sample)
def transform_tr(self, sample):
composed_transforms = transforms.Compose([
tr.RandomHorizontalFlip(),
tr.RandomScaleCrop(base_size=self.cfg.DATASET.BASE_SIZE,
crop_size=self.cfg.DATASET.CROP_SIZE),
tr.RandomGaussianBlur(),
tr.Normalize(mean=(0.485, 0.456, 0.406),
std=(0.229, 0.224, 0.225)),
tr.ToTensor()
])
return composed_transforms(sample)
def transform_tr(self, sample):
composed_transforms = transforms.Compose([
tr.scaleNorm(),
tr.RandomScale((1.0, 1.4)),
tr.RandomHSV((0.9, 1.1), (0.9, 1.1), (25, 25)),
tr.RandomCrop(image_h, image_w),
tr.RandomFlip(),
tr.ToTensor(),
tr.Normalize()
])
return composed_transforms(sample)
def transform_val(self, sample):
composed_transforms = transforms.Compose([
#tr.FixedResize(768,1536),
#tr.FixScaleCrop(crop_size=self.args.crop_size),
#tr.RandomScaleCrop(base_size=768, crop_size=768),
tr.Normalize(mean=(0.485, 0.456, 0.406),
std=(0.229, 0.224, 0.225)),
tr.ToTensor()
])
return composed_transforms(sample)
def transforms_train_esp(self, sample):
composed_transforms = transforms.Compose([
tr.RandomVerticalFlip(),
tr.RandomHorizontalFlip(),
tr.RandomAffine(degrees=40, scale=(.9, 1.1), shear=30),
tr.ColorJitter(brightness=0.5, contrast=0.5, saturation=0.5),
tr.FixedResize(size=self.input_size),
tr.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224,
0.225]),
tr.ToTensor()
])
return composed_transforms(sample)
def __init__(self,
args,
split='train',
):
super().__init__()
self._dataset = ic.get_dataset('ilabs.vision', 'scarlet300')
files = list(self._dataset[split])
images = sorted(f for f in files if f.endswith('.png'))
masks_filename = self.CACHE_BOX % split
if not os.path.exists(masks_filename):
print('Generating CACHE for split', split)
masks = [generate_first_box(fname) for fname in tqdm(images)]
torch.save(masks, masks_filename)
else:
masks = torch.load(masks_filename)
assert len(images) == len(masks)
self._images = images
self._masks = masks
self.split = split
self.args = args
if split == 'train':
self._transform = transforms.Compose([
# tr.RandomHorizontalFlip(),
# tr.RandomScaleCrop(base_size=self.args.base_size, crop_size=self.args.crop_size, fill=0xffffff),
tr.RandomGaussianBlur(),
tr.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
tr.ToTensor()
])
elif split == 'test':
self._transform = transforms.Compose([
# tr.FixScaleCrop(crop_size=self.args.crop_size),
tr.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
tr.ToTensor()
])
else:
raise ValueError('Unknown split: ' + split)
def transform_val(self, sample):
"""Transformations for images
sample: {image:img, annotation:ann}
Note: the mean and std is from imagenet
"""
composed_transforms = transforms.Compose([
tr.FixScaleCrop(crop_size=self.args.crop_size, fill=0),
tr.Normalize(mean=(0.485, 0.456, 0.406),
std=(0.229, 0.224, 0.225)),
tr.ToTensor()
])
return composed_transforms(sample)
def transform_tr(self, sample):
composed_transforms = transforms.Compose([
tr.RandomHorizontalFlip(
), # given PIL image randomly with a given probability
tr.RandomScaleCrop(base_size=self.args.base_size,
crop_size=self.args.crop_size),
tr.RandomGaussianBlur(),
tr.Normalize(mean=(0.485, 0.456, 0.406),
std=(0.229, 0.224, 0.225)),
tr.ToTensor()
])
return composed_transforms(sample)
def transform_tr(self, sample):
composed_transforms = transforms.Compose([
tr.RandomHorizontalFlip(),
tr.RandomScaleCrop(base_size=self.base_size,
crop_size=self.crop_size,
fill=255),
tr.RandomDarken(self.cfg, self.darken),
#tr.RandomGaussianBlur(), #TODO Not working for depth channel
tr.Normalize(mean=self.data_mean, std=self.data_std),
tr.ToTensor()
])
return composed_transforms(sample)
def transform_val(self, sample):
composed_transforms = transforms.Compose([
tr.FixScaleCrop(crop_size=self.args.crop_size),
tr.Normalize(mean=(0.485, 0.456, 0.406),
std=(0.229, 0.224, 0.225)),
tr.ToTensor()
])
transformed = composed_transforms(sample)
transformed['imgId'] = sample['imgId']
transformed['resolution'] = sample['image'].size
return transformed
def transform_tr(self, sample):
"""Image transformations for training"""
targs = self.transform
method = targs["method"]
pars = targs["parameters"]
composed_transforms = transforms.Compose([
tr.FixedResize(size=pars["outSize"]),
tr.RandomRotate(degree=(90)),
tr.RandomScaleCrop(baseSize=pars["baseSize"], cropSize=pars["outSize"], fill=255),
tr.Normalize(mean=pars["mean"], std=pars["std"]),
tr.ToTensor()])
return composed_transforms(sample)