A classifier trained on over 1 million digits on the EMNIST dataset.
Uses PyTorch and a combination of layers to create a fairly simple network.
Check the GitHub for the training code.
Cohen, G., Afshar, S., Tapson, J., & van Schaik, A. (2017). EMNIST: an extension of MNIST to handwritten letters. Retrieved from http://arxiv.org/abs/1702.05373
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the HF Inference API does not support pytorch models with pipeline type image-classification