PyTorch GPUNet0 model
quic-bharathr
released this
30 Mar 00:46
·
7 commits
to develop
since this release
Optimized w8a8 checkpoint, encoding and FP32 checkpoint for Pytorch GPUNet0 model.
For w8a8 optimization:
- Adaround followed by bn_fold_to_scale in per channel mode have been applied on the original FP32 model.
- Percentile was used in per channel mode for quantsim.