def transform_val(self, sample): composed_transforms = transforms.Compose([ tr.FixScaleCrop(crop_size=self.args.crop_size), tr.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)), tr.ToTensor()]) return composed_transforms(sample)
def transform_val(self, sample): composed_transforms = transforms.Compose([ # tr.Resize(size=(64, 64)), tr.PaddingSurround(), tr.UpperThreshold(0), tr.Normalize(), tr.ToTensor() ]) return composed_transforms(sample)
def transform_tr(self, sample): composed_transforms = transforms.Compose([ tr.RandomHorizontalFlip(), tr.RandomScaleCrop(base_size=self.args.image_size, crop_size=self.args.crop_size), tr.RandomGaussianBlur(), tr.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)), tr.ToTensor()]) return composed_transforms(sample)
def transform_val(self, sample): composed_transforms = transforms.Compose([ tr.FixScaleCrop(crop_size=self.args.crop_size), tr.Normalize(mean=(0.656963, 0.621670, 0.550278), std=(0.300198, 0.303201, 0.334976)), tr.ToTensor() ]) return composed_transforms(sample)
def __init__(self, data_root, num_sample=3, Training=False): self.Training = Training self.augment_transform = None self._single_object = False self.num_sample = num_sample if Training: self.data_dir = os.path.join(data_root, 'Train') self.augment_transform = transforms.Compose([ tr.Resize(scales=(512, 512)), tr.Crop(scale=0.5), tr.ToTensor() ]) else: self.data_dir = os.path.join(data_root, 'Test') self.augment_transform = transforms.Compose( [tr.Resize(scales=(512, 512)), tr.ToTensor()]) # Load Videos self.videos = [] for seq in sorted(os.listdir(self.data_dir)): self.videos.append(seq) if Training: random.shuffle(self.videos) self.videoindex = {} self.imagefiles = [] self.videofiles = [] offset = 0 for _video in self.videos: imagefiles = sorted( glob.glob(os.path.join(self.data_dir, _video, '*.jpg'))) self.imagefiles.extend(imagefiles) self.videofiles.extend([_video] * len(imagefiles)) self.videoindex[_video] = [offset, offset + len(imagefiles)] offset += len(imagefiles) print('total video: ', len(self.videos)) print('total image: ', len(self.imagefiles))
def transform_val(self, sample): """ You can change transforms with <dataloader.custom_transforms>. """ composed_transforms = transforms.Compose([ tr.Resize(size=(64, 64)), tr.Normalize(mean=(0.30273438, 0.30273438, 0.30273438), std=(0.44050565, 0.44050565, 0.44050565)), tr.ToTensor() ]) return composed_transforms(sample)
def transform_tr(self, sample): composed_transforms = transforms.Compose([ tr.RandomHorizontalFlip(), tr.RandomVerticalFlip(), tr.RandomScaleCrop(base_size=self.args.base_size, crop_size=self.args.crop_size, fill=255), tr.RandomRotate(), tr.RandomGaussianBlur(), tr.RandomNoise(), # mean and std calculated by calculateMeanStd.py tr.Normalize(mean=(0.656963, 0.621670, 0.550278), std=(0.300198, 0.303201, 0.334976)), tr.ToTensor() ]) return composed_transforms(sample)
joint_transforms.ImageResize(520), joint_transforms.RandomCrop(473), joint_transforms.RandomHorizontallyFlip(), joint_transforms.RandomRotate(10) ]) img_transform = transforms.Compose([ transforms.ToTensor(), transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) ]) target_transform = transforms.ToTensor() davis_transforms = transforms.Compose([ tr.RandomHorizontalFlip(), tr.ScaleNRotate(rots=(-30, 30), scales=(.75, 1.25)), tr.ToTensor()] ) # train_set = ImageFolder(msra10k_path, joint_transform, img_transform, target_transform) if args['train_loader'] == 'video_sequence': train_set = VideoSequenceFolder(video_seq_path, video_seq_gt_path, imgs_file, joint_transform, img_transform, target_transform) else: # train_set = DAVIS2016(db_root_dir='/home/ty/data/davis', train=True, transform=None) train_set = DAVIS_Single(db_image_dir='/home/ty/data/Pre-train', train=True, transform=None) # train_set = VideoImageFolder(video_train_path, imgs_file, joint_transform, img_transform, target_transform) train_loader = DataLoader(train_set, batch_size=args['train_batch_size'], num_workers=4, shuffle=True) criterion = nn.BCEWithLogitsLoss().cuda()
}, { 'params': [param for name, param in net.named_parameters() if name[-4:] != 'bias'], 'lr': lr, 'weight_decay': wd }], momentum=0.9) # Preparation of the data loaders # Define augmentation transformations as a composition composed_transforms = transforms.Compose([ tr.RandomHorizontalFlip(), # tr.ScaleNRotate(rots=(-30, 30), scales=(.75, 1.25)), tr.ToTensor() ]) # Training dataset and its iterator db_train = db.DAVIS2016(train=True, db_root_dir=db_root_dir, transform=composed_transforms, seq_name=seq_name) trainloader = DataLoader(db_train, batch_size=p['trainBatch'], shuffle=True, num_workers=1) # Testing dataset and its iterator db_test = db.DAVIS2016(train=False, db_root_dir=db_root_dir, transform=tr.ToTensor(),