Closed smilesun closed 10 months ago
Docstring for class torchvision.transforms.transforms.RandomGrayscale
=====================================================================
RandomGrayscale(p=0.1)
Randomly convert image to grayscale with a probability of p (default 0.1).
If the image is torch Tensor, it is expected
to have [..., 3, H, W] shape, where ... means an arbitrary number of leading dimensions
Args:
p (float): probability that image should be converted to grayscale.
Returns:
PIL Image or Tensor: Grayscale version of the input image with probability p and unchanged
with probability (1-p).
- If input image is 1 channel: grayscale version is 1 channel
- If input image is 3 channel: grayscale version is 3 channel with r == g == b
Here it says that this error ("Unable to find a valid cuDNN algorithm to run convolution") can occur when you run out of GPU memory. Could you maybe try to reduce the batch size and see if you still get the error?
it looks like you are right, it depends on batch size