Quoc Nhat

Thank you for your response. I've tried #20 . I choose to use the first solution ( rebuild project on old Ubuntu 18.04 gcc version 4.9.3, CentOS 7 uses gcc...

Hello, Have you successfully built and compiled ".so" libs cross different systems ( .,i,e: different gcc version) ? I investigated hard on this but failed at all. Which a lot...

Hello, Have you successfully built and compiled ".so" libs cross different systems ( .,i,e: different gcc version) ? I investigated hard on this but failed at all. Which a lot...

I have trained on rain removal but the result is not very good. However, it can compare with the others rain removal methods.

Sorry, it has been a long time and is deleted now. The dataset is collected by ourselves and is formatted as the valid other for training. Below are rain videos,...

@qidiso this "train_softmax.py" do not have mobilefacenet. I think this version works: https://github.com/deepinsight/insightface/blob/master/src/train_softmax.py

how do u get the pretrained model? I can not find it. thanks

the link is dead, please give me the pretrained model and the weight file.

@qidiso thank you so much. One more thing pls, I evaluated the above mxnet pretrained model and got some results. But it is slightly lower than yours. ([lfw] (mine) Accuracy-Flip...

> Maybe you can download here and replace the two git-lfs pointer file in dex/dex/pth. > [gender_sd.pth](https://drive.google.com/file/d/1ancMcq5b_0nppdIAav1UgBxdiaMnnQPe/view) > [age_sd.pth](https://drive.google.com/file/d/1KtzJBcGPMwjYdxbJkfEeRFzxNMaTVykH/view) solved the problem by either git-lfs installing and replacing 2 pretrained...