CODEWITHSUNDEEP
pytorchconv-neural-networkalbumentations
AJW
AJW

Reputation: 5873

using ImageFolder with albumentations in pytorch

I have a situation where I need to use ImageFolder with the albumentations lib to make the augmentations in pytorch - custom dataloader is not an option.

To this end, I am stumped and I am not able to get ImageFolder to work with albumenations. I have tried something along these lines:

class Transforms:
    def __init__(self, transforms: A.Compose):
        self.transforms = transforms

    def __call__(self, img, *args, **kwargs):
        return self.transforms(image=np.array(img))['image']

and then:

    trainset = datasets.ImageFolder(traindir,transform=Transforms(transforms=A.Resize(32 , 32)))

where traindir is some dir with images. I however get thrown a weird error:

RuntimeError: Given groups=1, weight of size [16, 3, 3, 3], expected input[1024, 32, 32, 3] to have 3 channels, but got 32 channels instead

and I cant seem to find a reproducible example to make a simple aug pipleline work with imagefolder.

UPDATE On the recommendation of @Shai, I have done this now:

class Transforms:
    def __init__(self):
        self.transforms = A.Compose([A.Resize(224,224),ToTensorV2()])

    def __call__(self, img, *args, **kwargs):
        return self.transforms(image=np.array(img))['image']

trainset = datasets.ImageFolder(traindir,transform=Transforms())

but I get thrown:

    self.padding, self.dilation, self.groups)
RuntimeError: Input type (torch.cuda.ByteTensor) and weight type (torch.cuda.FloatTensor) should be the same

Upvotes: 3

Views: 2469

Answers (3)

sudhanshu rastogi
sudhanshu rastogi

Reputation: 1

Albumentations library utilizes opencv that represents images as numpy array, therefore you have to provide a callable loader function that returns img as numpy array, which can be passed to albumentation transformation.

train_transform=A.Compose([A.HorizontalFlip(),
                           A.ShiftScaleRotate(rotate_limit=5,value=0,
                                              border_mode=cv2.BORDER_CONSTANT),

                           A.OneOf(
                                   [A.CLAHE(),
                                    A.RandomBrightnessContrast(),
                                    A.HueSaturationValue()],p=1),
                           A.GaussNoise(),
                           A.RandomResizedCrop(height=480,width=480),
                           A.Normalize(),
                           ToTensorV2()])


 def open_img(img_path):
     img=Image.open(img_path)
     return np.array(img)

 class Transform():
     def __init__(self,transform):
        self.transform=transform
     def __call__(self,image):
        return self.transform(image=image)["image"]



train_ds=ImageFolder(train_dir,transform=Transform(train_transform),loader=open_img)

Upvotes: 0

Mohamed Elawady
Mohamed Elawady

Reputation: 11

By looking into ImageFolder implementation on PyTorch[link] and some proposed work in Kaggle [link]. I propose the following solution (which is successfully tested from my side):

import numpy as np
from typing import Any, Callable, Optional, Tuple
from torchvision.datasets.folder import DatasetFolder, default_loader, IMG_EXTENSIONS
class CustomImageFolder(DatasetFolder):
def __init__(
    self,
    root: str,
    transform: Optional[Callable] = None,
    target_transform: Optional[Callable] = None,
    loader: Callable[[str], Any] = default_loader,
    is_valid_file: Optional[Callable[[str], bool]] = None,
):
    super().__init__(
        root,
        loader,
        IMG_EXTENSIONS if is_valid_file is None else None,
        transform=transform,
        target_transform=target_transform,
        is_valid_file=is_valid_file,
    )
    self.imgs = self.samples

def __getitem__(self, index: int) -> Tuple[Any, Any]:
    """
    Args:
        index (int): Index

    Returns:
        tuple: (sample, target) where target is class_index of the target class.
    """
    path, target = self.samples[index]
    sample = self.loader(path)
    if self.transform is not None:
        try:
            sample = self.transform(sample)
        except Exception:
            sample = self.transform(image=np.array(sample))["image"]
    if self.target_transform is not None:
        target = self.target_transform(target)

    return sample, target

def __len__(self) -> int:
    return len(self.samples)

Now you can run the code as follows:

trainset = CustomImageFolder(traindir,transform=Transforms(transforms=A.Resize(32 , 32)))

Upvotes: 1

Shai
Shai

Reputation: 114926

You need to use ToTensorV2 transformation as the final one:

trainset = datasets.ImageFolder(traindir,transform=Transforms(transforms=A.Compose([A.Resize(32 , 32), ToTensorV2()]))

Upvotes: 2

Related Questions