def Img_transform(self, name, size, split='train'):
# if len(args.crop_size) == 1:
# crop_size = (args.crop_size[0] , args.crop_size[0]) ## W x H
# else:
# crop_size = (args.crop_size[1] , args.crop_size[0])
assert (isinstance(size, tuple) and len(size) == 2)
if name in ['CS', 'IDD']:
if split == 'train':
t = [
transforms.Resize(size),
transforms.RandomCrop((512, 512)),
transforms.RandomHorizontalFlip(),
transforms.ToTensor()
]
else:
t = [transforms.Resize(size), transforms.ToTensor()]
return transforms.Compose(t)
if split == 'train':
t = [
transforms.Resize(size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor()
]
else:
t = [transforms.Resize(size), transforms.ToTensor()]
return transforms.Compose(t)
def __init__(self, cfg):
self.cfg = cfg
if self.cfg.mode == 'train':
self.transform = transform.Compose( transform.Normalize(mean=cfg.mean, std=cfg.std),
transform.Resize(size=512),
transform.RandomRotate(-15, 15),
transform.RandomCrop(448, 448),
transform.RandomHorizontalFlip(),
transform.RandomMask(),
transform.ToTensor())
elif self.cfg.mode == 'val' or self.cfg.mode == 'test':
self.transform = transform.Compose( transform.Normalize(mean=cfg.mean, std=cfg.std),
transform.Resize(size=512),
transform.ToTensor())
else:
raise ValueError
def __init__(self, cfg):
with open(cfg.datapath + '/' + cfg.mode + '.txt', 'r') as lines:
self.samples = []
for line in lines:
imagepath = cfg.datapath + '/image/' + line.strip() + '.jpg'
maskpath = cfg.datapath + '/scribble/' + line.strip() + '.png'
self.samples.append([imagepath, maskpath])
if cfg.mode == 'train':
self.transform = transform.Compose(
transform.Normalize(mean=cfg.mean, std=cfg.std),
transform.Resize(320, 320), transform.RandomHorizontalFlip(),
transform.RandomCrop(320, 320), transform.ToTensor())
elif cfg.mode == 'test':
self.transform = transform.Compose(
transform.Normalize(mean=cfg.mean, std=cfg.std),
transform.Resize(320, 320), transform.ToTensor())
else:
raise ValueError
def __init__(self, cfg):
with open(os.path.join(cfg.datapath, cfg.mode + '.txt'), 'r') as lines:
self.samples = []
for line in lines:
imagepath = os.path.join(cfg.datapath, 'image',
line.strip() + '.jpg')
maskpath = os.path.join(cfg.datapath, 'mask',
line.strip() + '.png')
self.samples.append([imagepath, maskpath])
if cfg.mode == 'train':
self.transform = transform.Compose(
transform.Normalize(mean=cfg.mean, std=cfg.std),
transform.Resize(320, 320), transform.RandomHorizontalFlip(),
transform.RandomCrop(288, 288), transform.ToTensor())
elif cfg.mode == 'test':
self.transform = transform.Compose(
transform.Normalize(mean=cfg.mean, std=cfg.std),
transform.Resize(320, 320), transform.ToTensor())
else:
raise ValueError
import torchvision
import torch
print(torch.__version__)
print(torchvision.__version__)
normalize = T.Normalize(mean=[0.43216, 0.394666, 0.37645],
std=[0.22803, 0.22145, 0.216989])
# def normalize(tensor):
# # Subtract the mean, and scale to the interval [-1,1]
# tensor_minusmean = tensor - tensor.mean()
# return tensor_minusmean/tensor_minusmean.abs().max()
transform_video = torchvision.transforms.Compose([
T.ToFloatTensorInZeroOne(),
T.Resize((128, 171)),
T.RandomHorizontalFlip(), normalize,
T.RandomCrop((112, 112))
])
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
root = ET.parse(
'/root/yangsen-data/LIRIS-ACCEDE-movies/ACCEDEmovies.xml').getroot()
movie_length = {}
def get_sec(time_str: str) -> int:
"""Get Seconds from time."""
h, m, s = time_str.split(':')
return int(h) * 3600 + int(m) * 60 + int(s)
for i in root:
if args.distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend='nccl', init_method='env://')
synchronize()
img_mean = [0.485, 0.456, 0.406]
img_std = [0.229, 0.224, 0.225]
device = 'cuda'
# torch.backends.cudnn.deterministic = True
train_trans = transform.Compose(
[
transform.RandomScale(0.5, 2.0),
# transform.Resize(args.size, None),
transform.RandomHorizontalFlip(),
transform.RandomCrop(args.size),
transform.RandomBrightness(0.04),
transform.ToTensor(),
transform.Normalize(img_mean, img_std),
transform.Pad(args.size)
]
)
valid_trans = transform.Compose(
[transform.ToTensor(), transform.Normalize(img_mean, img_std)]
)
train_set = ADE20K(args.path, 'train', train_trans)
valid_set = ADE20K(args.path, 'valid', valid_trans)
arch_map = {'vovnet39': vovnet39, 'vovnet57': vovnet57}