automl icon indicating copy to clipboard operation
automl copied to clipboard

Published 20 hours ago • verified publisher icon google

How to apply quantization aware training on EfficientDet keras model?

Open kimwj94 opened this issue 2 years ago • 0 comments

I'm trying to do quantization aware training on EfficientDet keras model. I tried use Nvidia TensorFlow-2.x-Quantization-Toolkit, but I got error: ValueError: to_quantize can only either be a tf.keras Sequential or Functional model.

How can I modify the model to do QAT?

kimwj94 avatar Mar 27 '23 04:03 kimwj94