Missing quantized_sigmoid activation layer in QKeras?
Open
- Dominant language
- Python
- Stars
- 584
- Forks
- 108
- PR merge metrics
- No merged PRs in 30d
Description
This is more of a doubt than an issue I face with QKeras. I wanted to add a quantized Sigmoid layer to my neural network model. I was rather surprised to find no such activation layer mentioned, either in the Readme or in the research paper published by Google and CERN, on QKeras, particulalry because I see a `quantized_tanh` and a `quantized_relu`. It seemed only natural to have an analogous `quantized_sigmoid` as well.
Is a built-in quantized Sigmoid activation layer truly missing in QKeras? Or am I missing something?
Contributor guide
Assessment
This issue has not been assessed yet.