loaders["train"] = train_loader loaders["valid"] = valid_loader return loaders data_transform = Compose([ Augmentor( dict_key="features", augment_fn=lambda x: torch.from_numpy(x.copy().astype(np.float32) / 255.0).unsqueeze_(0), ), Augmentor( dict_key="features", augment_fn=Normalize((0.5, ), (0.5, )), ), Augmentor( dict_key="targets", augment_fn=lambda x: torch.from_numpy(x.copy().astype(np.float32) / 255.0).unsqueeze_(0), ), ]) loaders = get_loaders(data_transform) # # Model # In[ ]: from catalyst.contrib.models.cv import Unet
def get_transforms(stage: str = None, mode: str = None): """ @TODO: Docs. Contribution is welcome """ return Compose([ToTensor(), Normalize((0.1307, ), (0.3081, ))])
# # Data # In[ ]: import collections import torch from catalyst.contrib.datasets import MNIST from catalyst.data.cv import ToTensor, Compose, Normalize bs = 32 num_workers = 0 data_transform = Compose([ToTensor(), Normalize((0.1307,), (0.3081,))]) loaders = collections.OrderedDict() trainset = MNIST( "./data", train=False, download=True, transform=data_transform ) trainloader = torch.utils.data.DataLoader( trainset, batch_size=bs, shuffle=True, num_workers=num_workers ) testset = MNIST("./data", train=False, download=True, transform=data_transform) testloader = torch.utils.data.DataLoader( testset, batch_size=bs, shuffle=False, num_workers=num_workers )