GitLab

Fixes #1746

BatchNorm only has x as the runtime input parameter for the following equation. All the other parameters are compile-time constants and related operations can be const-folded before quantizing to fp16 to preserve precision.

Rewrites the TF batch norm like operators to other MIGX operators
Removes the code related to batch_norm_inference

Updated each source file in the repo with the existing license.

* refactor files

* formatting

* fix add_bcast test

* fix some tidy errors

* add transpose field and fix more tidy

* formatting

* add pad test and fix more tidy

* formatting

* fix conv parser

* fix depthwiseconv

* remove unsed functions

* remove includes and functions
Co-authored-by: Paul Fultz II <pfultz2@yahoo.com>