search

AIWintermuteAI / aXeleRate

Keras-based framework for AI on the Edge
MIT License
179 stars 71 forks source link

[unstable branch] yolo training quantize or not can be switched by config.json #52

Closed yangtuo250 closed 3 years ago

yangtuo250 commented 3 years ago

Is your feature request related to a problem? Please describe. in axelerate/training.py custom training is commented out and quantize training is a default choice.

Describe the solution you'd like Add a boolean "quantize" param in config.json and switch training mode for yolo in training.py.

AIWintermuteAI commented 3 years ago

That's because this branch is called "unstable"... It is used for QAT and pruning experiments.