jakobwonisch / faceblur

Batch processing and web interface for face blur tool.

yolov7-face-blur

This repository is created on top of two repository

1. Object Blurring by RizwanMunawar
2. Face detction by derronqi

---

How to install

1. Create Virutal Environment of Python, Recommended python version 3.9.0, incase you dont have 3.9.0, see pyenv guide.
2. Activate the Environment using python -m venv your_env_name/Scripts/activate
3. install required libraries using pip install -r requirements
4. (Optional) If you want to use GPU, you have to install additional requirements i.e, pip install -r requirements_gpu.txt

---

Models:

Models	Test Size	Easy	Medium	Hard	FLOPs (B) @640	Google	Baidu
yolov7-lite-t	640	88.7	85.2	71.5	0.8	google	gsmn
yolov7-lite-s	640	92.7	89.9	78.5	3.0	google	3sp4
yolov7-tiny	640	94.7	92.6	82.1	13.2	google	aujs
yolov7s	640	94.8	93.1	85.2	16.8	google	w72z
yolov7	640	96.9	95.5	88.0	103.4	google	jrj6
yolov7+TTA	640	97.2	95.8	87.7	103.4	google	jrj6
yolov7-w6	960	96.4	95.0	88.3	89.0	google	-
yolov7-w6+TTA	1280	96.9	95.8	90.4	89.0	google	-

---

Required Arguments to run

1. --weights contains your downloaded model from the above table
2. --bluurratio to determine the strength of blurring, default value is 20
3. --device either cpu or 0 in case of gpu.
4. --source containes your images (png, jpg etc) or video (mp4 etc)

---

Examples

# Example with detected accuracy (usng CPU)
python detect.py --weights yolov7-tiny.pt --blurratio 50 --device cpu --source myimage.jpg

# Example with hiding detected area, only blur (usng CPU)
python detect.py --weights yolov7-tiny.pt --blurratio 50 --hidedetarea --device cpu --source myimage.jpg

# Example on video (usng CPU)
python detect.py --weights yolov7-tiny.pt --blurratio 50 --hidedetarea --device cpu --source myvideo.mp4