google / qkeras

QKeras: a quantization deep learning library for Tensorflow Keras
Apache License 2.0
532 stars 102 forks source link

QDense_batchnorm? #64

Open thesps opened 3 years ago

thesps commented 3 years ago

I see you have qconv2d_batchnorm layer which folds the weights of the two layers and then quantizes.

We're bringing support for that to hls4ml, and it should help us save some resources & latency.

I'm wondering, do you plan to add the equivalent combined QDense + BatchNormalization layer to QKeras?

zhuangh commented 3 years ago

@thesps great and glad to see this helps! Yes, QDenseBatchnorm is one of our TODO items, but we have other higher priority tasks at this moment.

zhuangh commented 3 years ago

https://github.com/google/qkeras/pull/74