Karanbir Chahal

The animation should be more pleasing to the eye.Right now it goes into starts and jumps

Broadcasting Support for N-Dimensional Array

1

In this project, we use a ND Array to represent the underlying data of a Tensor. The Matrix class represents the ND array. As of now, we have little to...

This pull request seeks to add building this project for the GPU. Currently, the kernel for the dot product is added (matrix multiplication). To build for the GPU, the cuda...

Memory Leaks in creating Tensors and Ops

1

Lot of times we are constructing objects on the heap and not explicitly deleting them. This leads to a ton of memory leaks. We need to debug this and solve...

This issue tracks the development of the Loss layer (MSE, Cross entropy et a)

This issue tracks the development of the dropout layer

This issue tracks the development of the batch normalisation layer.

Backward Propagation Pointer Bug

1

When we try to overload operations such that complex operations can be done in a single expression. Something like ```c++ Tensor = a; Tensor = b; Tensor = c; Tensor...

1cycle Policy. Unfamiliar results

1

Hey, I was implementing 1 cycle policy as an exercise. And I have a few observations from my experiments. I have a __Model__ : Resnet18. __Batch size for training__ =...

Training on a pretrained Bert language model ?

1

Do you want to train this thing on a BERT language model base ? I think you'll get really great results ? I wouldn't mind working on this if you...