Karanbir Chahal

Prelim broadcasting support will come through the pull request for the Softmax layer.

Support for matrix is now live on develop via #11 . Refer to that to know more. What's left is backprop for dot product operation. This will include getting the...

Back Prop of matrix multiplication is handled via #21 . GPU support is still not pushed into main branch. So holding on that to close this issue

Handled via #23

We have two options to handle memory leaks: 1. We remove all dependencies, all tensors and operations by using a DFS like call when the destructor of a Tensor is...

Update on this is as follows: 1. Added another way to perform operations on tensors by just taking the pointer of two tensors and adding them. This approach removes a...

Hello, I was wondering what is the average time to get a good policy for creating classification models using Darts on a Google colab server (which has a 16 GB...

Yes ! We would welcome PR's that help this repo. It could be anything, some ideas are: 1. New Distillation techniques 2. Clean up on code. The lightning code is...

Hello, @scott-gray I would like to try to port it to pytorch. I know the procedure of incorporating c++ and cuda extension in pytorch through setuptools. Any advice on what...

Thanks ! I'll look into it