Ziteng Gao
Ziteng Gao
We observe a consistent performance lag when training AdaMixer with `mmcv_full==1.3.5`, especially with the longer training scheme. This phenomenon may be also widespread with `mmcv_full>1.3.3`. For right reproduction, please use...
Hi! Thanks for the nice work. I'm quite confused about whether or not DPPs for ResNet-50 and ResNet-101 are inserted as pooling layers __after__ the bottleneck? That seems increase the...
Although the implementation of strided convolution is complete, pooling methods such as maxpool and avgpool are still problems.
Although `non_saturating_d_loss` and `non_saturating_gen_loss` are not default choices in this codebase, there seems a mistake of argument placement `label` and `input` in these two functions, which should be swapped (`input`...