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

[Add] Yolov5 trt HRNet inference on video #99

Merged
merged 3 commits into from
Nov 27, 2022
Merged

[Add] Yolov5 trt HRNet inference on video #99

merged 3 commits into from
Nov 27, 2022

Conversation

gpastal24
Copy link
Contributor

Added yolov5 and HRNet tensorRT inference.

The yolov5 trt engine can be generated via either the cache torch hub directory or by cloning the yolov5 repo, exporting the yolov5 into trt engine and moving it into the simpleHRNet folder.

Also added padding instead of bbox enlargement

@stefanopini
Copy link
Owner

Thanks @gpastal24 , great contribution again! I'm going to have a look at this PR later this week or the next week.

I'll probably follow the same approach used for simple-HigherHRNet: merge into tensorrt branch, clean up the code and add colab notebook, ask your review, merge into master.

@stefanopini stefanopini changed the base branch from master to tensorrt November 27, 2022 16:44
@stefanopini stefanopini merged commit 276290f into stefanopini:tensorrt Nov 27, 2022
@stefanopini stefanopini mentioned this pull request Nov 27, 2022
7 tasks
stefanopini added a commit that referenced this pull request Dec 29, 2022
* [Add] Yolov5 trt HRNet inference on video (#99)

* [Add] Yolov5 trt HRNet inference on video

* Fixed a bug with int overflow on tracking

* Revisions before review

Co-authored-by: Giannis Pastaltzidis <gpastal@iti.gr>

* Restore submodule

* Rename models folder and remove pycache

* Add .gitignore

* Fix models imports

* Refactor code, Update docstring

* Fix YOLOv5 sizes and loading

* Rename models to fix issue with YOLOv5 from torch hub

* Fix issues with yolov5 and tensorrt, Update extract-keypoints script

* Fix bug in yolov5.engine detections

Fix bug in detection locations when tensorrt-converted yolov5 is used

* Add Google Colab notebook

* Update README.md

* Update notebook

Co-authored-by: gpastal24 <104021640+gpastal24@users.noreply.github.com>
Co-authored-by: Giannis Pastaltzidis <gpastal@iti.gr>
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

Successfully merging this pull request may close these issues.

3 participants