search

ayooshkathuria / pytorch-yolo-v3

A PyTorch implementation of the YOLO v3 object detection algorithm
3.3k stars 1.06k forks source link

Refactor for usability & maintainability #9

Open abagshaw opened 6 years ago

abagshaw commented 6 years ago

Love what you've done here (and especially the in-depth tutorial on the Paperspace blog!). I've been looking for a performant pytorch implementation of YOLOv3 and this seems to be the closest thing that fits the bill.

One suggestion: Right now the repo feels more like a proof of concept than a well organized library (one example: the simple task of figuring out how to plug in an image and get a list of predictions out to use in another python app isn't super straightforward).

Would love to see this progress towards a more refined library (and if I have some time I'll certainly try to help out with any refactoring I can).

Thanks for all your work on this!

ayooshkathuria commented 6 years ago

Thanks for the suggestion. I've been pretty busy this month, but a more refined library is certainly on my list. More or less a library that will allow you to train your custom data sets with YOLO. I'm leaving this issue open and ping you for suggestions when I make appropriate pull requests so you can review it if you have time.

renderedSafe commented 6 years ago

I concur. I'll be looking into submitting a pull request if I can put together something that I can stand to let others see. I really appreciate what you've done here. I need something similar to you, @abagshaw. I'm trying to filter out the trash motion alerts from my security cameras and only send me the ones with things I care about. I'm not happy with the state of the deployability of these tools. Tensorflow's object detection is a giant pain to deploy, so here I am.