中文说明文档 Chinese version instruction for plate detection

---

Original English instruction for face detection

Description

MTCNN: Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
Implement training and testing by tensorflow. Referenced mtcnn_tf Still working on this repo ...

Dependencies

• Tensorflow v1.0.0 or higher
• TF-Slim
• Python 3.5
• Ubuntu 14.04 or CentOS 7.2 or higher
• Cuda 8.0 or higher

Prepare Face Data and Go Through Training Process

1. WIDER face dataset: Download WIDER_train.zip from here. You can only download Wider Face Training Images. Unzip it and move it to dataset folder.
2. Landmark dataset: Download train.zip from here. You can only download training set. Unzip it and move it to dataset folder.
3. Run ./clearAll.sh to clear all tmp file.
4. Run ./runAll.sh to finish all (include preparing data and training). Please check this shell script to get more info.

Prepare Plate Data and Train

1. Prepare your own plate dataset, make sure images named by CCPD rules. Put image files in ./dataset/traindata folder.
2. Run ./runMy.sh to finish all (include preparing data and training).

Testing and Predict

1. Copy your image file to testing/images
2. Run python testing/test_images.py --stage=onet. Anyway you can specify stage to pnet or rnet to check your model.
3. The result will output in testing/results_onet

Testing and Predict Plate Data

1. Copy your image file to testing/plates
2. Run python testing/test_plates.py --stage=onet. Anyway you can specify stage to pnet or rnet to check your model.
3. The result will output in testing/results_onet

Results

License

MIT LICENSE

References

1. Kaipeng Zhang, Zhanpeng Zhang, Zhifeng Li, Yu Qiao , " Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks," IEEE Signal Processing Letter
2. MTCNN-Tensorflow