def _train_image_transform(self):
transform = transforms.Compose([
transforms.Resize(256),
transforms.RandomCrop(224),
transforms.RandomHorizontalFlip(),
transforms.RandomVerticalFlip(),
transforms.RandomRotation(0.2),
transforms.ColorJitter(0.1, 0, 0, 0),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
])
return transform
args = parse_args()
data_dir = args.data_dir
save_dir = args.save_dir
num_classes = args.num_classes
channel = args.channel
clip_min_value = args.clip_min_value
clip_max_value = args.clip_max_value
mean = args.mean
std = args.std
num_epochs = args.num_epochs
train_batch_size = args.train_batch_size
lr = args.lr
# 定义训练和验证时的transforms
train_transforms = T.Compose([
T.RandomVerticalFlip(0.5),
T.RandomHorizontalFlip(0.5),
T.ResizeStepScaling(0.5, 2.0, 0.25),
T.RandomPaddingCrop(1000),
T.Clip(min_val=clip_min_value, max_val=clip_max_value),
T.Normalize(
min_val=clip_min_value, max_val=clip_max_value, mean=mean, std=std),
])
eval_transforms = T.Compose([
T.Clip(min_val=clip_min_value, max_val=clip_max_value),
T.Normalize(
min_val=clip_min_value, max_val=clip_max_value, mean=mean, std=std),
])
train_list = osp.join(data_dir, 'train.txt')
def load_data_transformers(resize_reso=512, crop_reso=448, swap_num=[7, 7]):
center_resize = 600
Normalize = transforms.Normalize([0.485, 0.456, 0.406],
[0.229, 0.224, 0.225])
data_transforms = {
'swap':
transforms.Compose([
transforms.Resize((resize_reso, resize_reso)),
transforms.RandomRotation(degrees=15),
transforms.RandomCrop((crop_reso, crop_reso)),
transforms.RandomHorizontalFlip(),
transforms.Randomswap((swap_num[0], swap_num[1])),
]),
'food_swap':
transforms.Compose([
transforms.Resize((resize_reso, resize_reso)),
transforms.RandomRotation(degrees=90),
#transforms.RandomCrop((crop_reso, crop_reso)),
transforms.RandomHorizontalFlip(),
transforms.RandomVerticalFlip(),
transforms.RandomResizedCrop(size=crop_reso, scale=(0.75, 1)),
transforms.Randomswap((swap_num[0], swap_num[1])),
]),
'food_unswap':
transforms.Compose([
transforms.Resize((resize_reso, resize_reso)),
transforms.RandomRotation(degrees=90),
#transforms.RandomCrop((crop_reso, crop_reso)),
transforms.RandomHorizontalFlip(),
transforms.RandomVerticalFlip(),
transforms.RandomResizedCrop(size=crop_reso, scale=(0.75, 1)),
]),
'unswap':
transforms.Compose([
transforms.Resize((resize_reso, resize_reso)),
transforms.RandomRotation(degrees=15),
transforms.RandomCrop((crop_reso, crop_reso)),
transforms.RandomHorizontalFlip(),
]),
'train_totensor':
transforms.Compose([
transforms.Resize((crop_reso, crop_reso)),
#ImageNetPolicy(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
]),
'val_totensor':
transforms.Compose([
transforms.Resize((crop_reso, crop_reso)),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
]),
'test_totensor':
transforms.Compose([
transforms.Resize((resize_reso, resize_reso)),
transforms.CenterCrop((crop_reso, crop_reso)),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
]),
'None':
None,
'Centered_swap':
transforms.Compose([
transforms.CenterCrop((center_resize, center_resize)),
transforms.Resize((resize_reso, resize_reso)),
transforms.RandomRotation(degrees=15),
transforms.RandomCrop((crop_reso, crop_reso)),
transforms.RandomHorizontalFlip(),
transforms.Randomswap((swap_num[0], swap_num[1])),
]),
'Centered_unswap':
transforms.Compose([
transforms.CenterCrop((center_resize, center_resize)),
transforms.Resize((resize_reso, resize_reso)),
transforms.RandomRotation(degrees=15),
transforms.RandomCrop((crop_reso, crop_reso)),
transforms.RandomHorizontalFlip(),
]),
'Tencrop':
transforms.Compose([
transforms.Resize((resize_reso, resize_reso)),
transforms.TenCrop((crop_reso, crop_reso)),
transforms.Lambda(lambda crops: torch.stack(
[transforms.ToTensor()(crop) for crop in crops])),
])
}
return data_transforms
# Load image
dataset = SLAM('data/SLAM')
data, target = dataset[1]
# Add grid lines (https://stackoverflow.com/a/20473192/5828163)
dx, dy = 80, 80
data[:, ::dy, :] = [0, 0, 0, 0]
data[::dx, :, :] = [0, 0, 0, 0]
target[:, ::dy] = 1
target[::dx, :] = 1
# Plot transformations
plot_data_target(data, target, 'Original')
transform_list = [
transforms.RandomHorizontalFlip(p=1),
transforms.RandomVerticalFlip(p=1),
transforms.MinMaxScaling(),
transforms.RandomElasticDeformation(alpha=200, sigma=10, alpha_affine=40),
transforms.Pad(92, padding_mode='reflect'),
transforms.RandomRotation(180),
transforms.RandomCrop(572, 388),
transforms.ToTensor(),
]
for transform in transform_list:
data, target = transform(data, target)
plot_data_target(data, target, transform.__class__.__name__)