Changmao Cheng

MultiGPU efficient densenets are slow

14

I just want to benchmark the new implementation of efficient densenet with the code [here](https://gist.github.com/wandering007/d7f3db11285f382fefa39a9cda99ad0d). However, it seems that the used checkpointed modules are not broadcast to multiple GPUs as...

I want to manually delete/free/release an `at::Tensor` variable or its storage in a function for reducing memory usage. What should I do? Thanks!

Since `cv2.imread` loaded images are already in `BGR` format, which is the correct input format for caffe models, why change it [here](https://github.com/isht7/pytorch-deeplab-resnet/blob/master/convert_deeplab_resnet.py#L58)?

How to get 10-fold split lists for CALFW and CPLFW?

6

Hi, thanks for providing this awesome project. After I downloaded CALFW and CPLFW datasets from the official websites, I found that there are no off-the-shelf 10-fold cross-validation lists among the...