There are no reviews yet. Be the first to send feedback to the community and the maintainers!
Repository Details
This is a convolutional neural network build to identify Amharic letters. Currently it has an accuracy of about 86% on the test data. I will be improving the dataset as well as the algorithm to build better products. If you are interested, send pull requests. A huge thanks to @Fetulhak for opensourcing his dataset.