Training traffic sign recognition with faster rcnn using ga

ahmedfgad / GeneticAlgorithmPython

Source code of PyGAD, a Python 3 library for building the genetic algorithm and training machine learning algorithms (Keras & PyTorch).

https://pygad.readthedocs.io

BSD 3-Clause "New" or "Revised" License

1.84k stars 462 forks source link

Training traffic sign recognition with faster rcnn using ga #280

Open Zhihao1002 opened 7 months ago

Zhihao1002 commented 7 months ago

Hi,

I would like to ask if I want to integrate the ga to optimize the faster rcnn model's accuracy, could you explain a little on how i can modify the code to integrate GA into the model.

ahmedfgad commented 6 months ago

If you mean training the model using GA, then I highly recommend using pygad.kerasga (for Keras models) or pygad.torchga (for PyTorch models). But it is important to check that all the layers are compatible with the libraries so that their weights can be set and get by PyGAD.