BENCHMARK again gpu conv paper
for the articles, we should benchmark ourself again this papers for conv net on gpu.
http://cas.ee.ic.ac.uk/people/btc00/index_files/Convolution_filter.pdf
http://cas.ee.ic.ac.uk/people/btc00/index_files/Convolution_filter.pdf
Leave a comment
James finding:
Convolutional NNET
=================
http://www.codeproject.com/KB/graphics/GPUNN.aspx - a LeNet5 - like
implementation if I understand correctly.
http://leenissen.dk/fann/html_latest/files2/gpu-txt.html - FANN's GPU support
http://code.google.com/p/standardmodelgpu/ (HMAX Model on GPU) - looks
like something from MIT, may have interesting convolution kernels
inside.
Dense NNET
===========
http://sourceforge.net/projects/cudann/
http://sourceforge.net/projects/cuda-nn/
http://sourceforge.net/projects/mbp/
Convolutional NNET
=================
http://www.codeproject.com/KB/graphics/GPUNN.aspx - a LeNet5 - like
implementation if I understand correctly.
http://leenissen.dk/fann/html_latest/files2/gpu-txt.html - FANN's GPU support
http://code.google.com/p/standardmodelgpu/ (HMAX Model on GPU) - looks
like something from MIT, may have interesting convolution kernels
inside.
Dense NNET
===========
http://sourceforge.net/projects/cudann/
http://sourceforge.net/projects/cuda-nn/
http://sourceforge.net/projects/mbp/
James finding:
Convolutional NNET
=================
http://www.codeproject.com/KB/graphics/GPUNN.aspx - a LeNet5 - like
implementation if I understand correctly.
http://leenissen.dk/fann/html_latest/files2/gpu-txt.html - FANN's GPU support
http://code.google.com/p/standardmodelgpu/ (HMAX Model on GPU) - looks
like something from MIT, may have interesting convolution kernels
inside.
Dense NNET
===========
http://sourceforge.net/projects/cudann/
http://sourceforge.net/projects/cuda-nn/
http://sourceforge.net/projects/mbp/
Convolutional NNET
=================
http://www.codeproject.com/KB/graphics/GPUNN.aspx - a LeNet5 - like
implementation if I understand correctly.
http://leenissen.dk/fann/html_latest/files2/gpu-txt.html - FANN's GPU support
http://code.google.com/p/standardmodelgpu/ (HMAX Model on GPU) - looks
like something from MIT, may have interesting convolution kernels
inside.
Dense NNET
===========
http://sourceforge.net/projects/cudann/
http://sourceforge.net/projects/cuda-nn/
http://sourceforge.net/projects/mbp/