Utsav Garg
/home/torch/install/bin/luajit: /home/torch/install/share/lua/5.1/nn/Linear.lua:66: size mismatch at /home/torch/extra/cutorch/lib/THC/THCTensorMathBlas.cu:90 stack traceback: [C]: in function 'addmm' /home/babu/torch/install/share/lua/5.1/nn/Linear.lua:66: in function 'func' /home/babu/torch/install/share/lua/5.1/nngraph/gmodule.lua:345: in function 'neteval' /home/babu/torch/install/share/lua/5.1/nngraph/gmodule.lua:380: in function 'forward' ./misc_new/LanguageModel.lua:277: in function 'sample' eval_new.lua:135: in...
PyTorch is a recent deep learning framework which has become quite popular for researchers and we want to add support for it in Fabrik. The backend for PyTorch should be...
The [tested models](https://github.com/Cloud-CV/Fabrik/blob/master/tutorials/tested_models.md) list holds all models for which import and export has been tested. But, export is not always possible to all three frameworks currently supported (Caffe, Keras, Tensorflow)....
The model zoo currently opens up as a modal, and therefore cannot hold all models that have been [tested with Fabrik](https://github.com/Cloud-CV/Fabrik/blob/master/tutorials/tested_models.md) as it will get too cluttered. Even without all...
For Tensorflow, the import feature currently only supports a few layers (~10), we want to extend this to support as many layers as are available in our Keras backend (~60)....