evi-Genius

Results 8 comments of evi-Genius

I get the same issus, have you solve the problem?

I have the same question.

************************* Settings ************************* eval_per_calib : False use_gpu : 2 batch_norm : False use_gn : False input_bits_width : 8 exclude_first_conv : true dataset : imagenet batch_size : 64 use_se : False...

会不会是因为weight量化方案采用max对称量化的关系?我看depth wise convulation上面权重的异常值比较多,导致max对称量化后信息损失太大?

明白了,感谢回复!