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.Randomswap((swap_num[0], swap_num[1])),
]),
'common_aug': 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,
}
return data_transforms
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
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')
val_list = osp.join(data_dir, 'val.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
print("------------Preparing Model...----------------")
net = ACCNN(n_classes=n_classes,
pre_trained=True,
dataset=dataset,
fold=fold,
virtualize=True,
using_fl=fl).to(DEVICE)
print("------------%s Model Already be Prepared------------" % net_name)
input_img_size = net.input_size
IMG_MEAN = [0.449]
IMG_STD = [0.226]
transform_train = transforms.Compose([
transforms.Resize(
input_img_size
), # 缩放将图片的最小边缩放为 input_img_size，因此如果输入是非正方形的，那么输出也不是正方形的
transforms.RandomHorizontalFlip(),
transforms.RandomRotation(30),
transforms.ToTensor(),
transforms.Normalize(IMG_MEAN, IMG_STD),
])
transform_test = transforms.Compose([
transforms.Resize(
input_img_size
), # 缩放将图片的最小边缩放为 input_img_size，因此如果输入是非正方形的，那么输出也不是正方形的
transforms.ToTensor(),
transforms.Normalize(IMG_MEAN, IMG_STD),
])
print("------------Preparing Data...----------------")
if dataset == "JAFFE":
test_data = JAFFE(is_train=False,
transform=transform_test,
help='learning rate',
default=0.01,
type=float)
return parser.parse_args()
args = parse_args()
data_dir = args.data_dir
save_dir = args.save_dir
channel = args.channel
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.RandomHorizontalFlip(0.5), T.Normalize()])
eval_transforms = T.Compose([T.Normalize()])
train_list = osp.join(data_dir, 'train.txt')
val_list = osp.join(data_dir, 'val.txt')
label_list = osp.join(data_dir, 'labels.txt')
# 定义数据读取器
train_reader = Reader(data_dir=data_dir,
file_list=train_list,
label_list=label_list,
transforms=train_transforms,
shuffle=True)
eval_reader = Reader(data_dir=data_dir,
IMG_MEAN = [0.449]
IMG_STD = [0.226]
# for RGB images
# IMG_MEAN = [0.485, 0.456, 0.406]
# IMG_STD = [0.229, 0.224, 0.225]
crop_img_size = int(net.input_size * 1.2)
input_img_size = net.input_size
transform_using_crop = opt.tr_using_crop
if transform_using_crop:
transform_train = transforms.Compose([
transforms.Resize(crop_img_size),
transforms.TenCrop(input_img_size),
transforms.Lambda(lambda crops: torch.stack([
transforms.Normalize(IMG_MEAN, IMG_STD)
(transforms.ToTensor()(transforms.RandomHorizontalFlip()(
transforms.RandomRotation(30)(crop)))) for crop in crops
])),
])
transform_test = transforms.Compose([
transforms.Resize(crop_img_size),
transforms.TenCrop(input_img_size),
transforms.Lambda(lambda crops: torch.stack([
transforms.Normalize(IMG_MEAN, IMG_STD)
(transforms.ToTensor()(crop)) for crop in crops
])),
])
else:
transform_train = transforms.Compose([
transforms.Resize(
input_img_size
), # 缩放将图片的最小边缩放为 input_img_size，因此如果输入是非正方形的，那么输出也不是正方形的
