Mayank Daga
Mayank Daga
What is the reason for not incorporating/benchmarking `BackwardWeights` at least for NVIDIA? There is no use of `cudnnRNNBackwardWeights`.
I keep getting the above error on running this prototxt through caffe. Have you seen this before?
I came across your post on the Tensorflow thread that you are developing an OpenCL counterpart for cuDNN. I would like to help/contribute on that project. Let me know where...
Any small change requires manually deleting the `caffe` binary, a `make clean` and then `make all`. Ideally, just `make all` should be able to pick up the source changes and...
New feature request to add MIOpen's batch normalization support.