larenzhang

The paper reported the model parameters is 3.1M if α and w are jointly optimized over the union of the training and validation sets using coordinate descent. I want to...

About the results in the DynamicReLU paper

1

Hi, have you ever reimplemented the results as the paper reported, such as MobileNet or ResNet?

关于OREPA+RepVGG的实验结果

1

你好： 我看文章里OREPA和RepVGG结合时，是直接在conv_3*3上加OREPA， 而不是直接将conv_3*3/conv_1*1/identity三个分支换成OREPA的形式。请问这样做的是因为直接将conv_3*3/conv_1*1/identity三个分支换成OREPA进行训练效果不好么？

Caffe : Segmentation fault

3

I have executed the command： make all ,make test and there are no errors when I install caffe on ubuntu 16.04(cuda 8.0+Nvida Titan X).However,it occurs "Segmentation fault" when I excute...