How to perform the same crop augmentation on both the image and its corresponding mask?

Question

My code is:

randomScale = random.uniform(0.08, 1.0)
        CPtransform = transforms.RandomResizedCrop((self.height, self.width), scale=(randomScale, randomScale), ratio=(1,1), interpolation=2)
        toImage = T.ToPILImage()
        padImage= CPtransform(toImage(image).convert("L"))
        padMask = CPtransform(toImage(mask).convert("L"))
        return TF.to_tensor(padImage), TF.to_tensor(padMask)

But the mask are not correspond to its image after augmentation as the graph shows. The function that I used on them are all the same but the result are different.

Can anybody help? Thanks!

Answer 1

You can concat image and mask and convert it to a single tensor and do the transformation.

image = T.PILToTensor()(pil_image)
mask = T.PILToTensor()(pil_mask)

# concatenate the images and apply transform:
both_images = torch.cat((image, mask),0)

# Apply the transformations to both images simultaneously
transformed_images = CPtransform(both_images)

#get transformed image and mask separately
image_trans = transformed_images[:image.shape[0]]
mask_trans = transformed_images[image.shape[0]:]