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

Anyone tried yolo v4 or v5? #51

Closed
esgnn opened this issue Apr 26, 2020 · 7 comments
Closed

Anyone tried yolo v4 or v5? #51

esgnn opened this issue Apr 26, 2020 · 7 comments
Labels
enhancement New feature or request

Comments

@esgnn
Copy link

esgnn commented Apr 26, 2020

Hi,
I tried to replace yolov3.weights and yolov3.cfg with new yolov4.weights and yolov4.cfg but it took forever to predict with yolo detection. Actually I am on colab and it terminated the runtime because of memory, so no prediction occurred.

Has anyone else tried it?

@stefanopini
Copy link
Owner

Hi!
I guess you're talking about this version of YOLO and the weights they have released there:
YOLOv4 (v3/v2) - Windows and Linux version of Darknet ... - https://github.com/AlexeyAB/darknet

I've had a quick look at it and the script seems to be stuck in this loop
YOLOv3/utils/utils.py#L251-L260
when using the new checkpoint with the old detector.

It could be due to wrong thresholds or to a different ordering of the output, but I still haven't found the time to investigate it.

@azuryl
Copy link

azuryl commented Sep 26, 2020

@stefanopini do you tires yolov5?

@stefanopini
Copy link
Owner

Do you mean https://github.com/ultralytics/yolov5 ?
No, I didn't, but I think it'll require major changes because it is a completely different repository w.r.t. the current YOLOv3.
May you have a look at that?

@stefanopini stefanopini changed the title Anyone tried yolov4? Anyone tried yolo v4 or v5? Sep 26, 2020
@stefanopini stefanopini added the enhancement New feature or request label Sep 26, 2020
@gpastal24
Copy link
Contributor

#99 yolov5 for single image/video inference. Maybe it should be added in a different branch rather than the master branch since I didn't take a look into the _predict_batch method.
Also I have added trt for HRNet

@stefanopini
Copy link
Owner

Thanks @gpastal24 ! I'll take a look at your PR in the following days.

@gpastal24
Copy link
Contributor

Hi @stefanopini , thank you. I have made some revisions based on your comments on HigherHRNet PR.

@stefanopini
Copy link
Owner

stefanopini commented Dec 29, 2022

Support for YOLOv5 added to the master branch! (See #100 )

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

No branches or pull requests

4 participants