# 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](https://pan.baidu.com/s/1sJTO7TcQ2576RUqR_IIhbQ) (passcode:lsl3) face detection data then store it into ./data_set/face_detection
* run > python ./anno_store/tool/format/transform.py change .mat(wider_face_train.mat) into .txt(anno_train.txt)
* download [CNN_FacePoint](http://mmlab.ie.cuhk.edu.hk/archive/CNN_FacePoint.htm) face detection and landmark data then store it into ./data_set/face_landmark
# Training
* preparing data for P-Net
* run > python mtcnn/data_preprocessing/gen_Pnet_train_data.py
* run > python mtcnn/data_preprocessing/assemble_pnet_imglist.py
* train P-Net
* run > python mtcnn/train_net/train_p_net.py
* preparing data for R-Net
* run > python mtcnn/data_preprocessing/gen_Rnet_train_data.py (maybe you should change the pnet model path)
* run > python mtcnn/data_preprocessing/assemble_rnet_imglist.py
* train R-Net
* run > python mtcnn/train_net/train_r_net.py
* preparing data for O-Net
* run > python mtcnn/data_preprocessing/gen_Onet_train_data.py
* run > python mtcnn/data_preprocessing/gen_landmark_48.py
* run > python mtcnn/data_preprocessing/assemble_onet_imglist.py
* train O-Net
* run > python mtcnn/train_net/train_o_net.py
# Citation
[DFace](https://github.com/kuaikuaikim/DFace)
mtcnn-pytorch:人脸检测算法 （100个子文件） 
r_3.jpg 85KB r_2.jpg 79KB r_4.jpg 75KB leslie.jpg 74KB r_1.jpg 53KB s_l.jpg 19KB
wider_face_train.mat 1.48MB wider_face_val.mat 388KB wider_face_test.mat 90KB README.md 2KB
me.png 143KB l_z.png 13KB onet_epoch.pt 879KB onet_epoch.pt 879KB rnet_epoch.pt 237KB rnet_epoch.pt 237KB pnet_epoch.pt 29KB pnet_epoch.pt 29KB detect.py 25KB models.py 9KB train.py 9KB resnet_inception_v2.py 9KB gen_Rnet_train_data.py 8KB gen_Onet_train_data.py 7KB gen_Pnet_train_data.py 5KB imagedb.py 5KB vision.py 5KB gen_landmark_48.py 5KB image_reader.py 4KB utils.py 4KB train_r_net.py 3KB train_p_net.py 3KB utils.py 2KB wider_loader.py 2KB image_tools.py 1KB transform.py 1KB nms.py 1KB assemble.py 1KB config.py 1KB train_o_net.py 953B change.py 775B mtcnn_test.py 727B assemble_pnet_imglist.py 689B assemble_rnet_imglist.py 689B assemble_onet_imglist.py 687B __init__.py 0B __init__.py 0B __init__.py 0B __init__.py 0B __init__.py 0B __init__.py 0B detect.cpython-35.pyc 15KB models.cpython-35.pyc 8KB train.cpython-35.pyc 7KB image_reader.cpython-35.pyc 6KB BBox_utils.cpython-35.pyc 6KB imagedb.cpython-35.pyc 5KB vision.cpython-35.pyc 3KB utils.cpython-35.pyc 3KB landmark_utils.cpython-35.pyc 3KB utils.cpython-35.pyc 2KB image_tools.cpython-35.pyc 1KB config.cpython-35.pyc 1KB assemble.cpython-35.pyc 1KB __init__.cpython-35.pyc 165B __init__.cpython-35.pyc 160B __init__.cpython-35.pyc 155B
wider_face_train_bbx_gt.txt 4.72MB anno_train.txt 3.59MB imglist_anno_48.txt 2.9MB wider_face_val_bbx_gt.txt 1.17MB wider_face_test_filelist.txt 857KB anno_train_fixed.txt 54KB anno_train.txt 53KB readme.txt 558B tips.txt 243B tips.txt 75B tips.txt 55B tips.txt 55B tips.txt 55B tip.txt 40B tips.txt 25B tips.txt 25B tips.txt 25B tips.txt 25B tips.txt 23B tips.txt 7B neg_48.txt 0B neg_12.txt 0B imglist_anno_12.txt 0B part_48.txt 0B imglist_anno_24.txt 0B pos_12.txt 0B neg_24.txt 0B pos_48.txt 0B anno_train.txt 0B landmark_48.txt 0B part_24.txt 0B part_12.txt 0B pos_24.txt 0B共 100 条
- 1
资源评论
