You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When we define a lazy tensor and preprocess it, there should be a simple way to visualize the resulting tensors as images to check whether the preprocessing is applied correctly and yields sensible results.
torchvision has a function tensor_image_browse.
This should work for both the validation as well as the training data and it should either be interactive or just write the images to disk so they can then be explored.
The text was updated successfully, but these errors were encountered:
When we define a lazy tensor and preprocess it, there should be a simple way to visualize the resulting tensors as images to check whether the preprocessing is applied correctly and yields sensible results.
torchvision
has a functiontensor_image_browse
.This should work for both the validation as well as the training data and it should either be interactive or just write the images to disk so they can then be explored.
The text was updated successfully, but these errors were encountered: