Chaofan Tao

Why use centroids for training and generation

2

Hi, Thanks for your implementation of image-gpt. I wonder whether quantize the input to centroids is an optional processing for both training and generation, and the advantages of using centroids....

Thanks for your code! I wonder how do you compute the **latency** and **energy** in the paper?

## Environment info - Platform: Linux - Python version: 3.9.18 - PyTorch version (GPU?): 2.0.0+cu118 - Using GPU in script?: yes ## Information I use contextNet to train on the...

forward() got an unexpected keyword argument 'log_probs'

1

## Environment info - Platform: Linux - Python version: 3.9.18 - PyTorch version (GPU?): 2.0.0+cu118 - Using GPU in script?: yes ## Information I want to train context-net on the...

Comparison between ".data.clone()" and ".data.copy_()"

3

Thank you for your code! I have a question about LINE 26 and LINE33 in the `binaryconnect.py`. I wonder why you choose two different functions ".data.clone()" and ".data.copy_()" in these...