https://github.com/MNConnor/YoloV5-AI-Label

YoloV5 AI Assisted Labeling
https://github.com/MNConnor/YoloV5-AI-Label

Last synced: about 1 month ago
JSON representation

YoloV5 AI Assisted Labeling

• Host: GitHub
• URL: https://github.com/MNConnor/YoloV5-AI-Label
• Owner: MNConnor
• Created: 2022-03-16T13:30:50.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2022-04-03T20:31:19.000Z (over 2 years ago)
• Last Synced: 2024-08-02T01:25:11.434Z (4 months ago)
• Language: Python
• Size: 5.51 MB
• Stars: 4
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-object-detection-datasets - MNConnor/YoloV5-AI-Label - AI-Label?style=social"/> : YoloV5 AI Assisted Labeling. (Summary)
• awesome-yolo-object-detection - MNConnor/YoloV5-AI-Label - AI-Label?style=social"/> : YoloV5 AI Assisted Labeling. (Applications)
• awesome-yolo-object-detection - MNConnor/YoloV5-AI-Label - AI-Label?style=social"/> : YoloV5 AI Assisted Labeling. (Applications)

README

        
# YoloV5-AI-Label

YoloV5 AI Assisted Labeling

![Example Image](https://i.imgur.com/62AzXtD.jpg)

YoloV5 model automatically labels, then you can make corrections before saving to a label file

1. Enter your classes in the Classes.txt file, starting with class 0

2. Replace the best.pt YoloV5 model with your own YoloV5 model

3. Place your unlabled images in the images folder

4. Run main.py to start the program.

5. Use the slider to select the class you want to label

6. Click and drag on the image to draw label boxes

7. Right click on a box to remove it

8. Once everything in the frame is labeled, press 1 to apply

9. Image and its label file will be moved to the labels folder

With these labels, you can train your model with [YoloV5](https://github.com/ultralytics). Once your new model is trained, replace the best.pt file with your new model

and start labeling again. As the model gets better, less manual labeling will be needed. 

###### Requirements

- OpenCV

- Shapely

- PyTorch

- [YoloV5 Requirements](https://github.com/ultralytics/yolov5/blob/master/requirements.txt)