pytorch-deep-learning icon indicating copy to clipboard operation
pytorch-deep-learning copied to clipboard

Incorrect Batch Indexing in FashionMNIST Batched Image: Displays 32 Instead of 31

Open ruzcko opened this issue 1 year ago • 0 comments

Description: The image illustrating the batching process for the FashionMNIST dataset appears to contain an error in the indexing of batch samples. Currently, the image displays the batch indices from 0 to 32, but it would be more accurate to display from 0 to 31, given that batch indices typically start at 0 and end at batch_size - 1.

Steps to Reproduce:

  1. Refer to the attached image illustrating the FashionMNIST batching process.
  2. Observe the batch sample indices listed at the top of the image samples, particularly the rightmost index.

Expected Behavior: The batch indices should be labeled from 0 to 31 to accurately reflect a batch size of 32.

Actual Behavior: The batch indices are labeled from 0 to 32.

Image:

image

Additional Information: Correcting this labeling will help avoid any potential confusion for users trying to understand the batching process and the indexing of samples within a batch.

Thank you for your attention to this detail.

ruzcko avatar Jun 03 '24 16:06 ruzcko