mtcnn-pytorch

by Sierkinhane

Sierkinhane / mtcnn-pytorch

A face detection algorithm

233 Stars 94 Forks Last release: Not found 6 Commits 0 Releases

Available items

No Items, yet!

The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:

mtcnn-pytorch

Descriptions in chinese

https://blog.csdn.net/Sierkinhane/article/details/83308658

results:

Test an image

  • run > python mtcnn_test.py

Training data prepraring

  • download WIDER FACE (passcode:lsl3) face detection data then store it into ./dataset/facedetection
    • run > python ./annostore/tool/format/transform.py change .mat(widerfacetrain.mat) into .txt(annotrain.txt)
  • download CNN_FacePoint face detection and landmark data then store it into ./dataset/facelandmark

Training

  • preparing data for P-Net
    • run > python mtcnn/datapreprocessing/genPnettraindata.py
    • run > python mtcnn/datapreprocessing/assemblepnet_imglist.py
  • train P-Net

    • run > python mtcnn/trainnet/trainp_net.py
  • preparing data for R-Net

    • run > python mtcnn/datapreprocessing/genRnettraindata.py (maybe you should change the pnet model path)
    • run > python mtcnn/datapreprocessing/assemblernet_imglist.py
  • train R-Net

    • run > python mtcnn/trainnet/trainr_net.py
  • preparing data for O-Net

    • run > python mtcnn/datapreprocessing/genOnettraindata.py
    • run > python mtcnn/datapreprocessing/genlandmark_48.py
    • run > python mtcnn/datapreprocessing/assembleonet_imglist.py
  • train O-Net

    • run > python mtcnn/trainnet/traino_net.py

# Citation DFace

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.