ayooshkathuria / YOLO_v3_tutorial_from_scratch

Accompanying code for Paperspace tutorial series "How to Implement YOLO v3 Object Detector from Scratch"
https://blog.paperspace.com/how-to-implement-a-yolo-object-detector-in-pytorch/
2.32k stars 725 forks source link

Optimize computation of intersection area #11

Closed e-sha closed 6 years ago

e-sha commented 6 years ago

This commit simplifies computation of bounding box intersection area. It uses torch.clamp instead of torch.max and memory allocation

e-sha commented 6 years ago

Sory, the second commit does not correspond to the original problem. I wonder why it was added to the original pull request.

ayooshkathuria commented 6 years ago

Can't seem to get what the refactoring part is doing. Just getting rid of stray whitespace? Or anything particular you could point me towards?

e-sha commented 6 years ago

You are right. Refactoring just remove stray whitespaces. It does not correspond to the pull request and I don't understand why it was automatically added to it.

I'd like to detach the last commit from this pull request, but I don't understand how to do it.

e-sha commented 6 years ago

I've found a way to remove the second commit from pull request.

ayooshkathuria commented 6 years ago

Thanks. Merged.