https://github.com/pooya-mohammadi/yolov5-gradcam

Visualizing Yolov5's layers using GradCam
https://github.com/pooya-mohammadi/yolov5-gradcam

convolutional-neural-networks deep-learning deeputils gradcam pytorch visualizing yolov5

Last synced: 5 days ago
JSON representation

Visualizing Yolov5's layers using GradCam

• Host: GitHub
• URL: https://github.com/pooya-mohammadi/yolov5-gradcam
• Owner: pooya-mohammadi
• License: mit
• Created: 2021-12-09T19:47:03.000Z (almost 3 years ago)
• Default Branch: master
• Last Pushed: 2023-11-27T01:08:07.000Z (12 months ago)
• Last Synced: 2024-08-02T01:25:14.526Z (3 months ago)
• Topics: convolutional-neural-networks, deep-learning, deeputils, gradcam, pytorch, visualizing, yolov5
• Language: Jupyter Notebook
• Homepage:
• Size: 8.5 MB
• Stars: 281
• Watchers: 3
• Forks: 47
• Open Issues: 22
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-yolo-object-detection - pooya-mohammadi/yolov5-gradcam - mohammadi/yolov5-gradcam?style=social"/> : Visualizing Yolov5's layers using GradCam. (Applications)
• awesome-yolo-object-detection - pooya-mohammadi/yolov5-gradcam - mohammadi/yolov5-gradcam?style=social"/> : Visualizing Yolov5's layers using GradCam. (Applications)

README

        
# YOLO-V5 GRADCAM

I constantly desired to know to which part of an object the object-detection models pay more attention. So I searched for it, but I didn't find any for Yolov5.

Here is my implementation of Grad-cam for YOLO-v5. To load the model I used the yolov5's main codes, and for computing GradCam I used the codes from the gradcam_plus_plus-pytorch repository.

Please follow my GitHub account and star ⭐ the project if this functionality benefits your research or projects.

## Update:

Repo works fine with yolov5-v6.1

## Installation

`pip install -r requirements.txt`

## Infer

`python main.py --model-path yolov5s.pt --img-path images/cat-dog.jpg --output-dir outputs`

**NOTE**: If you don't have any weights and just want to test, don't change the model-path argument. The yolov5s model will be automatically downloaded thanks to the download function from yolov5. 

**NOTE**: For more input arguments, check out the main.py or run the following command:

```python main.py -h```

### Custom Name

To pass in your custom model you might want to pass in your custom names as well, which be done as below:

```

python main.py --model-path cutom-model-path.pt --img-path img-path.jpg --output-dir outputs --names obj1,obj2,obj3 

```

## Examples

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/pooya-mohammadi/yolov5-gradcam/blob/master/main.ipynb)







## Note

I checked the code, but I couldn't find an explanation for why the truck's heatmap does not show anything. Please inform me or create a pull request if you find the reason.

This problem is solved in version 6.1

## TO Do

1. Add GradCam++

2. Add ScoreCam

3. Add the functionality to the deep_utils library

# References

1. https://github.com/1Konny/gradcam_plus_plus-pytorch

2. https://github.com/ultralytics/yolov5

3. https://github.com/pooya-mohammadi/deep_utils

## Citation

Please cite **yolov5-gradcam** if it helps your research. You can use the following BibTeX entry:

```

@misc{deep_utils,

	title = {yolov5-gradcam},

	author = {Mohammadi Kazaj, Pooya},

	howpublished = {\url{github.com/pooya-mohammadi/yolov5-gradcam}},

	year = {2021}

}

```