Wei Wen

cmake errors

1

Currently `cmake` is not supported. Please copy `Makefile.config.example` and `make all` at this stage. ``` cp Makefile.config.example Makefile.config # Adjust Makefile.config (for example, if using Anaconda Python, or if cuDNN...

low rank deep neural networks

7

### Issue summary I am working on low rank deep neural networks, to speedup the testing for better deployability. Anyone is working on similar stuff? ### Steps to reproduce Code...

In [GPU mode](https://github.com/wenwei202/caffe/blob/0900e113196068d5b0f12048463e8046f38f34dd/src/caffe/layers/base_conv_layer.cpp#L752) with `conv_mode: LOWERED_CCNMM` , we need to first [remove](https://github.com/wenwei202/caffe/blob/0900e113196068d5b0f12048463e8046f38f34dd/src/caffe/layers/base_conv_layer.cpp#L759) all-zero columns and rows in the feature map matrix `col_buffer_ `. This concatenation process is temporally using the...

I organize the issues regarding `make runtest` here. Please see some of them reported in https://github.com/BVLC/caffe/issues/4328 by searching `make runtest`. Code branch: https://github.com/wenwei202/caffe/tree/scnn

Is there any problem that makes the implementation of GPU version difficult? I tried to get a linear combination of SB weights and LB weights in GPU mode, and got...

I run `python plot_parametric_plot.py -n C1`, and get following error: ``` Traceback (most recent call last): File "plot_parametric_plot.py", line 64, in model = network_zoo.shallownet(nb_classes) File "/home//github/users/wenwei202/large-batch-training/network_zoo.py", line 37, in shallownet...

@eladhoffer What is the difference between `main_gbn.py` and `main_normal.py`? Thanks.

This is weird that cifar-10 is missing in https://github.com/pytorch/examples, why not create a pull request to them?

Variational RHN + WT (depth=10) with 517 units per layer is enough vs original 830

3

The homogeneity of RHNs ease us to learn sparse structures within RHNs. In our recent work of ISS (https://arxiv.org/pdf/1709.05027.pdf), we find that the we can reduce "#Units/Layer" of "Variational RHN...

Lack of cuDNN 5 and WINOGRAD algorithm support

1

I tried to run ` ./scripts/exp_case_alexnet_scalability.sh ` and raised a butch of Warning and got no profiling results: > WARNING build/bdist.linux-x86_64/egg/paleo/profilers/flops_profiler.py:192] Unsupported algorithm: CUDNN_CONVOLUTION_FWD_ALGO_WINOGRAD > WARNING build/bdist.linux-x86_64/egg/paleo/profilers/flops_profiler.py:192] Unsupported algorithm: CUDNN_CONVOLUTION_FWD_ALGO_WINOGRAD...