This repository has been archived by the owner on Nov 17, 2023. It is now read-only.
A temp solution to enable GluonCV INT8 flow #14331
Labels
Quantization
Issues/Feature Requests related to Quantization
Description
A simple method to launch int8 inference with gluon is that loading back a quantized JSON file and parameter as a SymbolBlock. However, SymbolBlock function is based on CachedOP which needs both forward and backward computing graph. So, some inference_only operators like quantized operators and subgraph operators cannot be loaded back. Below are the error logs:
A temporary solution implemented in #14275 is that registering fake grad to subgraph and quantized operators. This will be reverted after the improvement of CachedOP is done.
Environment info (Required)
The text was updated successfully, but these errors were encountered: