Daniil Pakhomov
Daniil Pakhomov
@ahkarami I am glad you liked it :) Yes, the project is alive an developing -- our focus is just directed towards 2d data so far. We will add support...
@qwliu So far only these layers are supported: https://github.com/warmspringwinds/pytorch-cpp#implemented-layers
Sorry for the late reply @jjn037 This piece of code is slow because you transfer the data from gpu to cpu -- this is usually an expensive operation and should...
FYI, I have just added a file with a speed benchmark: https://github.com/warmspringwinds/pytorch-cpp/blob/master/examples/resnet_18_8s_benchmark.cpp
@samhodge It's already converted here: https://github.com/warmspringwinds/pytorch-cpp#segmentation-pascal-voc
Hi @samhodge -- I didn't really test it on macos yet but I will have a look at this Thank you for letting me know about these problems 👍
@samhodge Yay, You are welcome :) For the future, try to get a linux machine -- a lot of open source projects are having issues with clang
Hi, @kirill-pinigin , we use 1.8 We have more information here: https://github.com/warmspringwinds/pytorch-cpp#hdf5
Hi @pharrellyhy Did you check it using the last cell here: https://github.com/warmspringwinds/pytorch-cpp/blob/master/convert_weights.ipynb It will be different a bit. also make sure that you have switched your pytorch code into test...
@pharrellyhy Could you please provide me with code that you use to benchmark both pytorch and pytorch-cpp versions? It's really important to do it right.