SkimCaffe

SkimCaffe copied to clipboard

Hi， I'd like to use the skimcaffe to sparse the winograd layer，which branch should I use？because I found that there is a branch named intel_sparse_winograd, does it has some special...

FLNDTORRES

### Issue summary When I compile Caffe cloned from the official repository, the compilation is successful, but when trying to compile SkimCaffe, I don't get any errors while compiling (only...

nadir199

Performance issue of running a single convolutional layer with different sparsity

7

### Issue summary I’m measuring the performance of the inference of a single sparse convolutional layer using SkimCaffe. However, the results show that: 1. The effective flops achieved is only...

yushansu

sparse resnet model

1

### Issue summary I'd like to use the sparse resnet model. I have downloaded the model from "SkimCaffe/models/resnet/ResNet-50-model.caffemodel.bz2" and loaded it using caffe c++ interface. But when iterating the entry...

dongxiao92

Winograd Layer in Skim Caffe

17

Please use the [caffe-users list](https://groups.google.com/forum/#!forum/caffe-users) for usage, installation, or modeling questions, or other requests for help. _Do not post such requests to Issues._ Doing so interferes with the development of...

imniksha

winograd convolution (portable and fast in inference)

3

Dear developers, thanks for your contribution to this excellent program, here are parts of my work about winograd convolution for cpu inference. Three files are added for cpu inference based...

TaoHuUMD

make all error with intel compiler

1

Please use the [caffe-users list](https://groups.google.com/forum/#!forum/caffe-users) for usage, installation, or modeling questions, or other requests for help. _Do not post such requests to Issues._ Doing so interferes with the development of...

acad1234

error

1

Hi,when i run the ./models/bvlc_reference_caffenet/train_script.sh 0.001 5e-5 0.0001 10 0 0 0 0 0 template_l1_solver.prototxt caffenet_0.57368.caffemodel i encounted the following error: + template_file=template_solver.prototxt + template_file=0 + cat models/bvlc_reference_caffenet/0 cat: models/bvlc_reference_caffenet/0:...

fgxfxpfzzfcc

error occurs running on gpu when i transplant the code to windows

1

I parse models/resnet/caffenet_train_iter_2000000.caffemodel under the caffe. I only transplant the part of sparse matrix calculations to caffe(for example, the caffe_gpu_sparse_dense2csr function interface),but CUSPARSE_CHECK () reports error when running to the...

yeyuxmf

libxsmm and other frameworks

3

> our sparse convolution routine will be migrated to libxsmm library so that it can be also used by other frameworks like TensorFlow I suppose libxsmm is already used in...

cvasfi