thnets
thnets copied to clipboard
Basic library that can run networks created with Torch
testing this on a raspberry pi https://github.com/mvitez/thnets/blob/1e4adc7c1cf0020f73520edc58cc084fe7e6cf34/thnets.py#L29 for me it should be: result = as_array(presult, (n,1))
hello, When I try sample code (in README) to export PyTorch model, like ``` out = net.forward(torch.autograd.Variable(torch.FloatTensor(1,3,227,227))) thexport.save('pymodel.net', out) ``` I got the following error. ``` File "...... /python3.6/site-packages/torch/autograd/variable.py", line...
Hello! Very nice work! Do you have a plan to support Sigmoid activation? or if I would like to add it by myself, can you roughly let me know steps...
Hi Marko, Is it possible to build this to run on Windows 10? I have some troubles with OpenBlas, when I am trying to make it.
> Not all thnets supported layers have been implemented is the LSTM layer supported? I use thexport on my model,It seems the LSTM with embedding layer have been decomposed to...
There are a couple of problems that prevent it from compiling for AArch64, but they pretty much all revolve around the ARM assembly found in `thvector.h` and in `OpenBLAS-stripped/arm`. ARM...
According to @culurciello, it should be easy to build this to run on Android. Any document/example as to how it could be done? Could it be really as easy as...
I think in order to use the low precision library, I get gemmlowp, compile with LOWP=1, and then run with -a 7. All that seems to work great, and I...