google / google/qkeras

Missing quantized_sigmoid activation layer in QKeras?

Open
#59 0 comments 1 reaction 0 assignees View on GitHub
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

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.