def getLoader(datasetName, dataroot, batchSize, workers, mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), split='train', shuffle=True, seed=None): if datasetName == 'pix2pix': from datasets.pix2pix import pix2pix as commonDataset import transforms.pix2pix as transforms if split == 'train': dataset = commonDataset(root=dataroot, transform=transforms.Compose([ transforms.RandomHorizontalFlip(), transforms.ToTensor(), transforms.Normalize(mean, std), ]), seed=seed) else: dataset = commonDataset(root=dataroot, transform=transforms.Compose([ transforms.ToTensor(), transforms.Normalize(mean, std), ]), seed=seed) dataloader = torch.utils.data.DataLoader(dataset, batch_size=batchSize, shuffle=shuffle, num_workers=int(workers)) return dataloader
def getLoader(datasetName, dataroot, originalSize, imageSize, batchSize=64, workers=4, mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), split='train', shuffle=True, seed=None): #import pdb; pdb.set_trace() if datasetName == 'pix2pix': # from datasets.pix2pix import pix2pix as commonDataset # import transforms.pix2pix as transforms from datasets.pix2pix import pix2pix as commonDataset import transforms.pix2pix as transforms elif datasetName == 'pix2pix_val': # from datasets.pix2pix_val import pix2pix_val as commonDataset # import transforms.pix2pix as transforms from datasets.pix2pix_val import pix2pix_val as commonDataset import transforms.pix2pix as transforms if datasetName == 'pix2pix_class': # from datasets.pix2pix import pix2pix as commonDataset # import transforms.pix2pix as transforms from datasets.pix2pix_class import pix2pix as commonDataset import transforms.pix2pix as transforms if split == 'train': dataset = commonDataset( root=dataroot, transform=transforms.Compose([ transforms.Scale(originalSize), #transforms.RandomCrop(imageSize), #transforms.CenterCrop(imageSize), #transforms.RandomHorizontalFlip(), transforms.ToTensor(), transforms.Normalize(mean, std), ]), seed=seed) else: dataset = commonDataset( root=dataroot, transform=transforms.Compose([ transforms.Scale(originalSize), #transforms.CenterCrop(imageSize), transforms.ToTensor(), transforms.Normalize(mean, std), ]), seed=seed) dataloader = torch.utils.data.DataLoader(dataset, batch_size=batchSize, shuffle=shuffle, num_workers=int(workers)) return dataloader
def getLoader(datasetName, dataroot, originalSize, imageSize, batchSize=64, workers=0, mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), split='train', shuffle=True, seed=None): #import pdb; pdb.set_trace() if datasetName == 'pix2pix': from datasets.pix2pix import pix2pix as commonDataset import transforms.pix2pix as transforms elif datasetName == 'folder': from datasets.folder import ImageFolder as commonDataset import torchvision.transforms as transforms if split == 'train': dataset = commonDataset(root=dataroot, transform=transforms.Compose([ transforms.ToTensor(), transforms.Normalize(mean, std), ]), seed=seed) else: dataset = commonDataset(root=dataroot, transform=transforms.Compose([ transforms.ToTensor(), transforms.Normalize(mean, std), ]), seed=seed) assert dataset dataloader = torch.utils.data.DataLoader(dataset, batch_size=batchSize, shuffle=shuffle, num_workers=int(workers)) return dataloader