Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Is this actively maintained? #1778

Open
bc-arl opened this issue May 29, 2024 · 8 comments
Open

Is this actively maintained? #1778

bc-arl opened this issue May 29, 2024 · 8 comments

Comments

@bc-arl
Copy link

bc-arl commented May 29, 2024

Trying to train some object detectors for a business.
We need to be able to use a repo with a commercial license
Just wondering if this is still state of the art open source yolo trainer as the repo hasn't been committed to in a year...
We had been using MMDetection but it is a pain and we're looking to move off of it.

@Subhankhan41
Copy link

@bc-arl Hi, any success finding an answer? We are also on the same boat and looking for a better alternate to MMDetection. Any success finding a better alternative?

@cravies
Copy link

cravies commented Jul 10, 2024

I'm the guy above and no, I haven't managed to find anything better than MMDetection

@cravies
Copy link

cravies commented Jul 10, 2024

MMdetection can be a bit cleaner if you mainly use it for training, and try to avoid their runtime as much as possible. I.e export to onnx and try to stick to vanilla onnxruntime. Does require writing preprocessing / postprocessing code though to mimic what the model is expecting as input and make sense of the outputs, theres some examples of people doing this on github for both mmpose and mmdetection

@cravies
Copy link

cravies commented Jul 10, 2024

Here's an example for rtmpose
https://github.com/Tau-J/rtmlib

@cravies
Copy link

cravies commented Jul 10, 2024

P.S this approach can be a bit of a timesink initially, so I wouldn't do it if you just need to get something working quickly. But for a long term project, probably worth it.

@Subhankhan41
Copy link

@cravies Hey, thanks for the response and sharing some useful information. I am trying some luck with detectron2 as follows:
https://github.com/facebookresearch/detectron2

Currently, it looks good. Regarding YoloX, It's still Apache 2.0 License so maybe it could be used for commercial use.

@Rares926
Copy link

Out of curiosity, what do you think about the SuperGradients repository? I've used it for a while, and it seems well-structured, similar to MMDetection, where all training-related configurations can be specified in a single file. However, unlike MMDetection, it doesn’t require several large, intertwined repositories to work. However the downside is that Deci was bought by Nvidia some months ago and for now it is unclear if the repo will be updated in the future or if it will retain it's apache licence.

@cravies
Copy link

cravies commented Oct 1, 2024

SuperGradients looks good but don't want to use anything that's not actively maintained.
After looking around on the internet, people are saying keras-cv is an option. It's apache licensed, actively maintained, and has a yolov8 implementation.
Haven't tried it yet but will be exploring using it in the future. openmmlab is a pain and is no longer maintained.
https://keras.io/api/keras_cv/models/backbones/yolo_v8/

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants