Riptide
Riptide copied to clipboard
Simple Training and Deployment of Fast End-to-End Binary Networks
Results
2
Riptide issues
Sort by
recently updated
recently updated
newest added
In the corresponding paper it mentions about unipolar vs bipolar quantization methods. I wonder how can I train a bipolar network using the train_imagenet.py? Thanks!
Hello, So I have been able to train binary AlexNet (1A1W) to top-1 accuracy to 43.2%, top-5 accuracy to 66.0%, fairly close to the published result. But I have been...