CGrad MNIST

A small MNIST classifier trained from scratch with CGrad, my own neural-network library written in C.

The model uses a 16-filter convolutional layer, max pooling, and a linear classifier. It reached 96.79% accuracy on the MNIST test set.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support