automan

@niuhaoyu16 .The optional parameter 'allow_extra=allow_extra' is recently introduced to mxnet. This FCIS implementation is based on an older version of mxnet. I think you could simply add 'allow_extra=True' to the...

Hi. Thanks for your question. Momentum = None is not equivalent to Momentum = 0.0. Momentum = None is a unique feature of PyTorch, it calculates the cumulative moving average....

I did not test momentum=0.1. I think the simple average is a better choice since it is robust to the order of mini-batch, although it is slightly different from what...

Hi, Thanks for the update. FYI, to reproduce the results in our paper, each experiment should be conducted 10 times. I will leave this issue open so that more people...

@justopit Please give more information about your training sets and testing sets. For Market, Duke, and MSMT, I have the same results as @HeliosZhao: momentum=None is better than momentum=0.1. This...