Finetuned yolov5 for trucks #476
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
BillMousta
requested review from
passalis,
omichel and
stefaniapedrazzi
as code owners
|
This PR has many conflicts. Could you please fix them before requesting a review? |
|
I changed the target to |
…gin/develop' into finetuned-yolov5-for-trucks
…o finetuned-yolov5-for-trucks
yolov5_learner.py documentation for download method
…o finetuned-yolov5-for-trucks
passalis
reviewed
Nov 8, 2023
src/opendr/perception/object_detection_2d/yolov5/yolov5_learner.py
Outdated
Show resolved
Hide resolved
src/opendr/perception/object_detection_2d/yolov5/yolov5_learner.py
Outdated
Show resolved
Hide resolved
|
If this PR is ready for review, please let us know. |
passalis
reviewed
Nov 13, 2023
Co-authored-by: Nikolaos Passalis <passalis@users.noreply.github.com>
omichel
approved these changes
Nov 15, 2023
tsampazk
requested changes
Nov 15, 2023
There was a problem hiding this comment.
Thank you @BillMousta for the new feature! I have added some comments, most are minor.
One general comment: I am not sure about the naming of the new feature. We use the word trucks which is not really accurate since the model is trained on tractors, so it could be misleading. Reading trucks i would intuitively expect pickup trucks or semis. Let me know if i misunderstand something regarding the naming.
projects/python/perception/object_detection_2d/yolov5/inference_demo_agriculture_vehicles.py
Show resolved
Hide resolved
|
Hmm it seems that you beat me to it. There are several stuff that need some polishing with this PR. I will implement the changes i commented on and open a new PR. |
Merged
Pavlos-Tosidis
added a commit
that referenced
this pull request
Nov 20, 2023
* Finetuned yolov5 for trucks (#476) * Yolov5 learner truck updates * Yolov5 create an inference demo for the finetuned model * Update object-detection-2d-yolov5.md yolov5_learner.py documentation for download method * Update object-detection-2d-yolov5.md * Refactor yolov5_learner.py download process in constructor for efficiency * Update docs/reference/object-detection-2d-yolov5.md Co-authored-by: Nikolaos Passalis <passalis@users.noreply.github.com> --------- Co-authored-by: Nikolaos Passalis <passalis@users.noreply.github.com> Co-authored-by: Olivier Michel <Olivier.Michel@cyberbotics.com> * Yolov5 trucks fixes (#487) * Some fixes and additions on the yolov5 download method doc * Minor addition for model name yolov5 trucks * Some fixes for the yolov5 download method docstring --------- Co-authored-by: Vasilis Moustakidis <45403400+BillMousta@users.noreply.github.com> Co-authored-by: Nikolaos Passalis <passalis@users.noreply.github.com> Co-authored-by: Olivier Michel <Olivier.Michel@cyberbotics.com> Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com>
passalis
added a commit
that referenced
this pull request
Nov 29, 2023
* Changed Face Recognition inference return. Now class is 0/1 if not found/found Added feature_extraction method to get access to features from a face image Added active_demo in which features in database get updated with new features of the same person. * Added final carriage return * Develop (#489) * Finetuned yolov5 for trucks (#476) * Yolov5 learner truck updates * Yolov5 create an inference demo for the finetuned model * Update object-detection-2d-yolov5.md yolov5_learner.py documentation for download method * Update object-detection-2d-yolov5.md * Refactor yolov5_learner.py download process in constructor for efficiency * Update docs/reference/object-detection-2d-yolov5.md Co-authored-by: Nikolaos Passalis <passalis@users.noreply.github.com> --------- Co-authored-by: Nikolaos Passalis <passalis@users.noreply.github.com> Co-authored-by: Olivier Michel <Olivier.Michel@cyberbotics.com> * Yolov5 trucks fixes (#487) * Some fixes and additions on the yolov5 download method doc * Minor addition for model name yolov5 trucks * Some fixes for the yolov5 download method docstring --------- Co-authored-by: Vasilis Moustakidis <45403400+BillMousta@users.noreply.github.com> Co-authored-by: Nikolaos Passalis <passalis@users.noreply.github.com> Co-authored-by: Olivier Michel <Olivier.Michel@cyberbotics.com> Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com> * Added: A simple demo for active feature updates A RosNode to be used by Pal_Robotics for the healthcare use case Fixed pep8 errors Added Readme's * Added: Fixed pep8 errors * Update projects/opendr_ws/src/opendr_perception/scripts/active_face_recognition_node.py Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com> * Update src/opendr/perception/face_recognition/face_recognition_learner.py Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com> --------- Co-authored-by: Olivier Michel <Olivier.Michel@cyberbotics.com> Co-authored-by: Nikolaos Passalis <passalis@users.noreply.github.com> Co-authored-by: Vasilis Moustakidis <45403400+BillMousta@users.noreply.github.com> Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com>
lucamarchionni
pushed a commit
to lucamarchionni/opendr
that referenced
this pull request
Jun 10, 2024
* Yolov5 learner truck updates * Yolov5 create an inference demo for the finetuned model * Update object-detection-2d-yolov5.md yolov5_learner.py documentation for download method * Update object-detection-2d-yolov5.md * Refactor yolov5_learner.py download process in constructor for efficiency * Update docs/reference/object-detection-2d-yolov5.md Co-authored-by: Nikolaos Passalis <passalis@users.noreply.github.com> --------- Co-authored-by: Nikolaos Passalis <passalis@users.noreply.github.com> Co-authored-by: Olivier Michel <Olivier.Michel@cyberbotics.com>
lucamarchionni
pushed a commit
to lucamarchionni/opendr
that referenced
this pull request
Jun 10, 2024
* Changed Face Recognition inference return. Now class is 0/1 if not found/found Added feature_extraction method to get access to features from a face image Added active_demo in which features in database get updated with new features of the same person. * Added final carriage return * Develop (opendr-eu#489) * Finetuned yolov5 for trucks (opendr-eu#476) * Yolov5 learner truck updates * Yolov5 create an inference demo for the finetuned model * Update object-detection-2d-yolov5.md yolov5_learner.py documentation for download method * Update object-detection-2d-yolov5.md * Refactor yolov5_learner.py download process in constructor for efficiency * Update docs/reference/object-detection-2d-yolov5.md Co-authored-by: Nikolaos Passalis <passalis@users.noreply.github.com> --------- Co-authored-by: Nikolaos Passalis <passalis@users.noreply.github.com> Co-authored-by: Olivier Michel <Olivier.Michel@cyberbotics.com> * Yolov5 trucks fixes (opendr-eu#487) * Some fixes and additions on the yolov5 download method doc * Minor addition for model name yolov5 trucks * Some fixes for the yolov5 download method docstring --------- Co-authored-by: Vasilis Moustakidis <45403400+BillMousta@users.noreply.github.com> Co-authored-by: Nikolaos Passalis <passalis@users.noreply.github.com> Co-authored-by: Olivier Michel <Olivier.Michel@cyberbotics.com> Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com> * Added: A simple demo for active feature updates A RosNode to be used by Pal_Robotics for the healthcare use case Fixed pep8 errors Added Readme's * Added: Fixed pep8 errors * Update projects/opendr_ws/src/opendr_perception/scripts/active_face_recognition_node.py Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com> * Update src/opendr/perception/face_recognition/face_recognition_learner.py Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com> --------- Co-authored-by: Olivier Michel <Olivier.Michel@cyberbotics.com> Co-authored-by: Nikolaos Passalis <passalis@users.noreply.github.com> Co-authored-by: Vasilis Moustakidis <45403400+BillMousta@users.noreply.github.com> Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This pull request introduces a new download method within the YOLOv5DetectorLearner class, enabling automated fetching of pre-trained models directly into the local environment. Additionally, it showcases an inference demo leveraging a YOLOv5s model fine-tuned for enhanced truck detection accuracy. This demonstration serves as a practical example of the model's improved performance in identifying trucks.