Emmanuel Benazera

dk, 10.1 is deprecated for us, and I don't believe we are using it anymore.

Hello, first thing is to study whether this might be due to cudnn. You need to try two things to find out about this : - create your services with...

Also FYI bear in mind that what is reported is memory that is allocated internally by CUDA/Cudnn, not what is not available anymore. Typically Cudnn does not fully deallocate it's...

Thanks. Look at the cudnn versions that come with every cuda flavor (i.e. from the original nvidia docker image)

Looks like a CUDNN/CUDA internal thing to me. I'd suggest you try the `tensorrt` backend instead, there's no reason not to use it actually.

You can look for yourself, it's basic cudnn calls: https://github.com/jolibrain/caffe/blob/master/src/caffe/layers/cudnn_conv_layer.cu and we recently updated for CUDNN8, https://github.com/jolibrain/caffe/pull/75 If you doubt the implementation you'll see ours (e.g. with cudnn8) is similar...

We don't have more info than what's in the code and CUDNN doc. The CUDNN memory issues are everywhere if you look for them. Your tests clearly indicate that it's...

There's no support for `test_split` is detection jobs yet, this is something we could add.

@cchadowitz-pf thanks, I've updated the scope to object detection at large, i.e. with more than a single class, since this is a demand we hear from several sources now. I'm...

Hi, you'd need to post your API calls, etc as requested in the issue template. Thanks!