QDense_batchnorm?
Open
- Dominant language
- Python
- Stars
- 584
- Forks
- 108
- PR merge metrics
- No merged PRs in 30d
Description
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](https://github.com/fastmachinelearning/hls4ml/pull/298), 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`?
Contributor guide
Assessment
This issue has not been assessed yet.