def __init__(self, mode='train'):
"""
初始化函数
"""
assert mode in ['train', 'test',
'valid'], 'mode is one of train, test, valid.'
self.data = []
with open('signs/{}.txt'.format(mode)) as f:
for line in f.readlines():
info = line.strip().split('\t')
if len(info) > 0:
self.data.append([info[0].strip(), info[1].strip()])
if mode == 'train':
self.transforms = T.Compose([
T.RandomResizedCrop(IMAGE_SIZE), # 随机裁剪大小
T.RandomHorizontalFlip(0.5), # 随机水平翻转
T.ToTensor(), # 数据的格式转换和标准化 HWC => CHW
T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]) # 图像归一化
])
else:
self.transforms = T.Compose([
T.Resize(256), # 图像大小修改
T.RandomCrop(IMAGE_SIZE), # 随机裁剪
T.ToTensor(), # 数据的格式转换和标准化 HWC => CHW
T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]) # 图像归一化
])
def __init__(self, noise_path, size, keys=None):
self.noise_path = noise_path
self.noise_imgs = sorted(glob.glob(noise_path + '*.png'))
self.size = size
self.keys = keys
self.transform = T.Compose([
T.RandomCrop(size),
T.Transpose(),
T.Normalize([0., 0., 0.], [255., 255., 255.])
])
def load_train_test_datasets(dataset_root):
mean = [0.485, 0.456, 0.406]
std = [0.229, 0.224, 0.225]
resize = transforms.Resize(256)
rcrop = transforms.RandomCrop((224, 224))
ccrop = transforms.CenterCrop((224, 224))
tot = transforms.ToTensor()
normalize = transforms.Normalize(mean, std)
train_transforms = transforms.Compose([resize, rcrop, tot, normalize])
test_transforms = transforms.Compose([resize, ccrop, tot, normalize])
train_set = DatasetFolder(osp.join(dataset_root, 'train'),
transform=train_transforms)
test_set = DatasetFolder(osp.join(dataset_root, 'test'),
transform=test_transforms)
return train_set, test_set
NUM_WORKERS = cfg['NUM_WORKERS']
USE_PRETRAINED = cfg['USE_PRETRAINED']
logger.info("=" * 60)
logger.info("Overall Configurations:")
for cfg_, value in cfg.items():
logger.info(cfg_ + ":" + str(value))
logger.info("=" * 60)
fleet.init(is_collective=True)
train_transform = transforms.Compose([
# refer to https://pytorch.org/docs/stable/torchvision/transforms.html for more build-in online data augmentation
transforms.Resize(
[int(128 * INPUT_SIZE[0] / 112),
int(128 * INPUT_SIZE[0] / 112)]), # smaller side resized
transforms.RandomCrop([INPUT_SIZE[0], INPUT_SIZE[1]]),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(mean=RGB_MEAN, std=RGB_STD),
])
logger.info('loading data form file:{}'.format(DATA_ROOT))
train_dataset = LFWDataset(os.path.join(DATA_ROOT), train_transform)
num_classes = train_dataset.num_classes
train_loader = paddle.io.DataLoader(train_dataset,
places=[paddle.CPUPlace()],
batch_size=BATCH_SIZE,
shuffle=True,
drop_last=DROP_LAST,
num_workers=NUM_WORKERS)
NUM_CLASS = train_dataset.num_classes
CUDA = True
if CUDA:
paddle.set_device('gpu')
place = paddle.CUDAPlace(0) if CUDA else paddle.CPUPlace()
mean, std = ([0.4914, 0.4822, 0.4465], [0.2023, 0.1994, 0.2010])
mean = list(map(lambda x: x * 255, mean))
std = list(map(lambda x: x * 255, std))
train_loader = paddle.io.DataLoader(
paddle.vision.datasets.Cifar10(
mode='train',
transform=transforms.Compose([
# transforms.Resize(size=64),
transforms.RandomHorizontalFlip(),
transforms.RandomCrop(32, 4),
transforms.Transpose(order=(2, 0, 1)),
transforms.Normalize(mean=mean, std=std),
]),
download=True),
places=place,
batch_size=128,
shuffle=True,
num_workers=0,
use_shared_memory=True)
val_loader = paddle.io.DataLoader(paddle.vision.datasets.Cifar10(
mode='test',
transform=transforms.Compose([
transforms.Transpose(order=(2, 0, 1)),
transforms.Normalize(mean=mean, std=std),
parser.add_argument('--bottleneck', default=False, type=bool,
help='whether to use bottleneck')
parser.add_argument('--weights', default='no', type=str,
help='the path for pretrained model')
parser.add_argument('--pretrained', default=False, type=bool,
help='whether to load pretrained weights')
parser.add_argument('--batch_size', default=config_parameters['batch_size'], type=int,
help='batch_size')
parser.add_argument('--lr', default=config_parameters['lr'], type=float)
parser.add_argument('--weight_decay', type=float, default=0.0001)
parser.add_argument('--epochs', type = int, default = config_parameters['epochs'])
parser.add_argument('--warmup', type = int, default = 10)
args = parser.parse_args()
train_transforms = T.Compose([
T.RandomCrop(32, padding=4),
T.RandomHorizontalFlip(),
T.ToTensor(),
T.Normalize(mean=[x/255.0 for x in [125.3, 123.0, 113.9]],
std=[x/255.0 for x in [63.0, 62.1, 66.7]])
])
eval_transforms = T.Compose([
T.ToTensor(),
T.Normalize(mean=[x/255.0 for x in [125.3, 123.0, 113.9]],
std=[x/255.0 for x in [63.0, 62.1, 66.7]])
])
if args.dataset == 'cifar10':
train_dataset = paddle.vision.datasets.Cifar10(mode='train', transform=train_transforms)
eval_dataset = paddle.vision.datasets.Cifar10(mode='test', transform=eval_transforms)