Stochastic-Quantization
Stochastic-Quantization copied to clipboard
Training Low-bits DNNs with Stochastic Quantization
Results
2
Stochastic-Quantization issues
Sort by
recently updated
recently updated
newest added
我最近在研究量化相关的方向,看到了您的论文。注意到您使用ResNet-56在cifar100上取得了35.01的错误率,但我自己实现时最高只有43。 我去看了您的resnet56的代码,但因为我没学过caffe所以看不懂。 想请教您一下,您选取的optimizer、学习率退火方式以及相应的超参数是什么? 还有,我看您在别的issue里提到您只量化了weight,请问这里的weight包括bn层及bias吗? 十分感谢
Hi . Thank you for provide your great code! I have a two question.! 1. In paper, vgg9 model(cifar10) don't use data augmentation. But , this code use data augmentation...