How do image resize/crop transformations handle small images?

vision
1

i have a dataset of large images (i.e. the parameters i pass to transforms.resize or resized crop are smaller than the image dimensions and it works fine. i added small images to the dataset (i.e. smaller than the parameters). how are they handled by the transformations? also, is it/what is the best way to handle them?

2

I would start with the TorchVision documentation of Resize. It explains

  • If size is a sequence like (h, w), output size will be matched to this.
  • If size is an int, smaller edge of the image will be matched to this number. i.e, if height width, then image will be rescaled to (size * height / width, size)

So then crop will do its thing on the (upscaled) image.

Best regards

Thomas

3

I have same problem .but, i can not understand this solution. can you explain more ?