It is a simple demo including face detection and face aligment, and some optimizations were made to make the result smooth.
CAUTION: this is the tensorflow2.0 branch, if you want to work on tf1, please switch to tf1 branch, it still works.
Purpose: I want to make a face analyzer including face detect and face alignment. Most of the face keypoints codes that opensourced are neither stable nor smooth, including some research papers. And the commercial sdk is pretty expensive. So, there is Peppa_Pig_Face_Engine.
I think it is pretty cool, see the demo:
click the gif to see the video:
-
tensorflow2.0
-
opencv
-
python 3.6
-
easydict
- download pretrained model, put them into ./model
-
detector
+baiduyun (code zn3x )
-
keypoints
+baiduyun (code rt7p)
the dir structure as :
./model/ ├── detector │ ├── saved_model.pb │ └── variables │ ├── variables.data-00000-of-00001 │ └── variables.index └── keypoints ├── saved_model.pb └── variables ├── variables.data-00000-of-00002 ├── variables.data-00001-of-00002 └── variables.index
- run
python demo.py --cam_id 0
orpython demo.py --video test.mp4
orpython demo.py --video test.mp4 --mask True
if u want a face mask
The project is based on two of my other repos, and both tensorflow1 and tensorflow2 are supported. If you want to train with your own data, or you want to know the details about the models, click them.
The project is supported by myself, and i need your advice to improve it. Hope the codes can help you, contact me if u have any question( 2120140200@mail.nankai.edu.cn). At last, i need your star,also your contribution.
- Transfer to tensorflow 2.0
- small model
- Add some GAN model to make it fun ing....
- 3-d face algorithm