def dense_process_data(index):
images = list()
for ind in indices['dense']:
ptr = int(ind)
if ptr <= record.num_frames:
imgs = self._load_image(record.path, ptr)
else:
imgs = self._load_image(record.path, record.num_frames)
images.extend(imgs)
if self.phase == 'Fntest':
images = [np.asarray(im) for im in images]
clip_input = np.concatenate(images, axis=2)
self.t = transforms.Compose([
transforms.Resize(256)])
clip_input = self.t(clip_input)
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
if record.crop_pos == 0:
self.transform = transforms.Compose([
transforms.CenterCrop((256, 256)),
transforms.ToTensor(),
normalize,
])
elif record.crop_pos == 1:
self.transform = transforms.Compose([
transforms.CornerCrop2((256, 256),),
transforms.ToTensor(),
normalize,
])
elif record.crop_pos == 2:
self.transform = transforms.Compose([
transforms.CornerCrop1((256, 256)),
transforms.ToTensor(),
normalize,
])
return self.transform(clip_input)
return self.transform(images)
cuda_available = torch.cuda.is_available()
# directory results
if not os.path.exists(RESULTS_PATH):
os.makedirs(RESULTS_PATH)
# Load dataset
mean = m
std_dev = s
transform_train = transforms.Compose([
transforms.RandomApply([transforms.ColorJitter(0.1, 0.1, 0.1, 0.1)],
p=0.5),
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize(mean, std_dev)
])
transform_test = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize(mean, std_dev)
])
training_set = LocalDataset(IMAGES_PATH,
TRAINING_PATH,
transform=transform_train)
validation_set = LocalDataset(IMAGES_PATH,
VALIDATION_PATH,
transform=transform_test)
# valloader = torch.utils.data.DataLoader(CSDataSet(args.data_dir, './dataset/list/cityscapes/val.lst', crop_size=(1024, 2048), mean=IMG_MEAN, scale=False, mirror=False),
# batch_size=2, shuffle=False, pin_memory=True)
value_scale = 255
mean = [0.485, 0.456, 0.406]
mean = [item * 255 for item in mean]
std = [0.229, 0.224, 0.225]
std = [item * 255 for item in std]
train_transform = my_trans.Compose([
# my_trans.Resize((args.height, args.width)),
# my_trans.RandScale([0.5, 2.0]),
# my_trans.RandomGaussianBlur(),
my_trans.RandomHorizontalFlip(),
# my_trans.Crop([args.height, args.width],crop_type='rand', padding=mean, ignore_label=255),
my_trans.ToTensor(), # without div 255
my_trans.Normalize(mean=mean, std=std)
])
val_transform = my_trans.Compose([
# my_trans.Resize((args.height, args.width)),
my_trans.ToTensor(), # without div 255
my_trans.Normalize(mean=mean, std=std)
])
data_dir = '/data/zzg/CamVid/'
train_dataset = CamVid(data_dir,
mode='train',
p=None,
transform=train_transform)
trainloader = torch.utils.data.DataLoader(train_dataset,
batch_size=args.batch_size,
shuffle=True,
def main():
global args, best_record
args = parser.parse_args()
if args.augment:
transform_train = joint_transforms.Compose([
joint_transforms.RandomCrop(256),
joint_transforms.Normalize(),
joint_transforms.ToTensor(),
])
else:
transform_train = None
dataset_train = Data.WData(args.data_root, transform_train)
dataloader_train = data.DataLoader(dataset_train,
batch_size=args.batch_size,
shuffle=True,
num_workers=16)
dataset_val = Data.WData(args.val_root, transform_train)
dataloader_val = data.DataLoader(dataset_val,
batch_size=args.batch_size,
shuffle=None,
num_workers=16)
model = SFNet(input_channels=37, dilations=[2, 4, 8], num_class=2)
# multi gpu
model = torch.nn.DataParallel(model)
print('Number of model parameters: {}'.format(
sum([p.data.nelement() for p in model.parameters()])))
model = model.cuda()
cudnn.benchmark = True
# define loss function (criterion) and pptimizer
criterion = torch.nn.CrossEntropyLoss(ignore_index=-1).cuda()
optimizer = torch.optim.SGD([{
'params': get_1x_lr_params(model)
}, {
'params': get_10x_lr_params(model),
'lr': 10 * args.learning_rate
}],
lr=args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay)
for epoch in range(args.start_epoch, args.epochs):
adjust_learning_rate(optimizer, epoch)
# train for one epoch
train(dataloader_train, model, criterion, optimizer, epoch)
# evaluate on validation set
acc, mean_iou, val_loss = validate(dataloader_val, model, criterion,
epoch)
is_best = mean_iou > best_record['miou']
if is_best:
best_record['epoch'] = epoch
best_record['val_loss'] = val_loss.avg
best_record['acc'] = acc
best_record['miou'] = mean_iou
save_checkpoint(
{
'epoch': epoch + 1,
'val_loss': val_loss.avg,
'accuracy': acc,
'miou': mean_iou,
'model': model,
}, is_best)
print(
'------------------------------------------------------------------------------------------------------'
)
print('[epoch: %d], [val_loss: %5f], [acc: %.5f], [miou: %.5f]' %
(epoch, val_loss.avg, acc, mean_iou))
print(
'best record: [epoch: {epoch}], [val_loss: {val_loss:.5f}], [acc: {acc:.5f}], [miou: {miou:.5f}]'
.format(**best_record))
print(
'------------------------------------------------------------------------------------------------------'
)
parser.add_argument("--batch_size",
type=int,
default=1,
help="Size of the batches")
parser.add_argument("--lr",
type=float,
default=0.0002,
help="Adams learning rate")
args = parser.parse_args()
device = ('cuda:0' if torch.cuda.is_available() else 'cpu')
transforms = T.Compose([
T.Resize((256, 256)),
T.ToTensor(),
T.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
])
# models
print('Defining models!')
generator = UnetGenerator().to(device)
discriminator = ConditionalDiscriminator().to(device)
# optimizers
g_optimizer = torch.optim.Adam(generator.parameters(),
lr=args.lr,
betas=(0.5, 0.999))
d_optimizer = torch.optim.Adam(discriminator.parameters(),
lr=args.lr,
betas=(0.5, 0.999))
# loss functions
g_criterion = GeneratorLoss(alpha=100)
d_criterion = DiscriminatorLoss()
if __name__=='__main__':
args = parse_args()
wandb.init(config=args,
project=f'dlcv_naive_{args.source}2{args.target}')
size = 64
t0 = transforms.Compose([
transforms.Resize(size),
transforms.ColorJitter(),
transforms.RandomRotation(15, fill=(0,)),
transforms.Grayscale(3),
transforms.ToTensor(),
transforms.Normalize((0.5,0.5,0.5),(0.5,0.5,0.5))
])
t1 = transforms.Compose([
transforms.Resize(size),
transforms.Grayscale(3),
transforms.ToTensor(),
transforms.Normalize((0.5,0.5,0.5),(0.5,0.5,0.5))
])
root = '../hw3_data/digits/'
# dataset
source, target = args.source, args.target
train_source_dataset = Digits_Dataset(root+f'{source}/train', source, t0)
train_target_dataset = Digits_Dataset(root+f'{target}/train', target, t0)
valid_source_dataset = Digits_Dataset(root+f'{source}/test', source, t1)
valid_target_dataset = Digits_Dataset(root+f'{target}/test', target, t1)
def inference(args):
if args.target=='mnistm':
args.source = 'usps'
elif args.target=='usps':
args.source = 'svhn'
elif args.target=='svhn':
args.source = 'mnistm'
else:
raise NotImplementedError(f"{args.target}: not implemented!")
size = args.img_size
t1 = transforms.Compose([
transforms.Resize(size),
transforms.Grayscale(3),
transforms.ToTensor(),
transforms.Normalize((0.5,0.5,0.5),(0.5,0.5,0.5))
])
valid_target_dataset = Digits_Dataset_Test(args.dataset_path, t1)
valid_target_dataloader = DataLoader(valid_target_dataset,
batch_size=512,
num_workers=6)
load = torch.load(
f"./p3/result/3_2/{args.source}2{args.target}/best_model.pth",
map_location='cpu')
feature_extractor = FeatureExtractor()
feature_extractor.load_state_dict(load['F'])
feature_extractor.cuda()
feature_extractor.eval()
label_predictor = LabelPredictor()
label_predictor.load_state_dict(load['C'])
label_predictor.cuda()
label_predictor.eval()
out_preds = []
out_fnames = []
count=0
for i,(imgs, fnames) in enumerate(valid_target_dataloader):
bsize = imgs.size(0)
imgs = imgs.cuda()
features = feature_extractor(imgs)
class_output = label_predictor(features)
_, preds = class_output.max(1)
preds = preds.detach().cpu()
out_preds.append(preds)
out_fnames += fnames
count+=bsize
print(f"\t [{count}/{len(valid_target_dataloader.dataset)}]",
end=" \r")
out_preds = torch.cat(out_preds)
out_preds = out_preds.cpu().numpy()
d = {'image_name':out_fnames, 'label':out_preds}
df = pd.DataFrame(data=d)
df = df.sort_values('image_name')
df.to_csv(args.out_csv, index=False)
print(f' [Info] finish predicting {args.dataset_path}')
default='cuda:0',
help='cpu or cuda:0 or cuda:1')
args = parser.parse_args() if string is None else parser.parse_args(string)
return args
if __name__ == '__main__':
args = parse_args()
wandb.init(config=args, project='dlcv_gan_face')
transform = transforms.Compose([
transforms.Resize(args.img_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.5] * 3, [0.5] * 3)
])
train_dataset = Face_Dataset('../hw3_data/face/train', transform)
valid_dataset = Face_Dataset('../hw3_data/face/test', transform)
train_dataloader = DataLoader(train_dataset,
batch_size=args.batch,
shuffle=True,
num_workers=args.num_workers)
valid_dataloader = DataLoader(valid_dataset,
batch_size=args.batch,
num_workers=args.num_workers)
train(args, train_dataloader, valid_dataloader)
