Haozhe Zhu

Ahh, Thanks you for using it. I tested ResNet18 twice in December last year, it can achieve the same accuracy. I am busy on other affairs recently, and I will...

The authors quantized the first & last layers to 8b integers, while I left them floating-pointed. I guess that's why I got a slightly better accuracy than the authors. I...

Sorry for that I cannot find your email address on your GitHub page. haozhe_zhu @ foxmail dot com, this is my email. I will reply you with my WeChat qrcode.

@cometonf, ResNet18 with act 2b and weight 3b, the top5 is about 86~87%. If approved, I can share a trained model with its config yaml. I am still working to...

@cometonf, I have released a quantized model as well as its corresponding configuration YAML file. You can find it in the README. Its quantized bit width is a2/w3, and the...

I have tried it on ResNet/ImageNet, but I found the initial value selection of the hyperparameter s is very tricky. I an not sure how I should modify the original...

> > I have tried it on ResNet/ImageNet, but I found the initial value selection of the hyperparameter s is very tricky. > > I an not sure how I...

Ahhh, I cannot obtain better acc with cos decay, and I used step decay but fixed decay. And the `config.yaml` is just a template. Please refer the configuration file in...

Sorry not yet.

Please read the existing issues. We have discussed it yet. Some hyper parameters in the paper only work for ImageNet. So you need to adjust them manually for CIFAR10. The...