AojunZhou

@MaKiTann Hi， how about the imagenet result ？

@jaxony Thanks, Do you know how to replicate the paper result about 1x with group 3 in Pytroch.

@gngdb thanks for your kind reply, I try to implement the groups=3 and multiplier 1x, I got only 59.8% validation accuracy after 60 epochs

@gngdb Hi , I forgot to remind you that the the original paper have updated at 7 Dec 2017, https://arxiv.org/abs/1707.01083 , you can find better accuracy in new version, maybe...

@windid Hi, Thanks, do you use @jaxony 's code directly? what about weight decay?

@windid ok, I will try your first implementation, with init learning rate: 0.5, batch size: 1024, 4 GPU.

Yes, My single GPU with 24G memory.

@fantexibaba we don't save the model with low-precision in training process.

@fantexibaba can you share your training setting?

@power0341 Hi, thank for your attention 1. about detection task， I'm sorry, I am not familiar with detection task, If I have time to do detection task quantization, I will...