I'm using pytorch and downloading the EMNIST dataset using training_data = datasets.EMNIST(root="./resources", split="letters", download=True, train=True, transform=ToTensor()) and it works fine I manage to get the images and show them but I don't know what the labels refers to, in other words what label is 34 letter "q" or "b"? I can manually show the image and the label and manually create the labels but there must be a better way.

Also I might decide to use a different split so I don't want to create the labels again.

I read the EMNIST paper and it's really cool how they adapted the NIST dataset to create EMNIST but I'm still clueless about the labels. paper


You can see some labels at https://www.tensorflow.org/datasets/catalog/emnist. It goes like this:

  • ‘0’-‘9’ are 0-9
  • ‘A’-‘Z’ are 10-35
  • ‘a’-‘z’ are 36-61

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.