kyakuno
commented
1 year ago データセット生成と学習もできるようなので、もし可能であれば日本のライセンスプレートも検知できるようにしたい。
Training on Custom Dataset
Hailo's LPRNet was trained on a synthetic auto-generated dataset containing 4 million license plate images. Auto-generation of synthetic data for training is cheap, allows one to obtain a large annotated dataset easily and can be adapted quickly for other domains
A notebook for auto-generation of synthetic training data for LPRNet can be found [here](https://github.com/hailo-ai/hailo_model_zoo/blob/master/hailo_models/license_plate_recognition/src/lp_autogenerate.ipynb)
For more details on the training data autogeneration, please see the training guide
A guide for training the pre-trained model on a custom dataset can be found [here](https://github.com/hailo-ai/hailo_model_zoo/blob/master/hailo_models/license_plate_recognition/docs/TRAINING_GUIDE.rst)
https://github.com/hailo-ai/hailo_model_zoo/tree/master/hailo_models/license_plate_detection