pytorch
616f50da - [quant][pt2e] QNNPackQuantizer support annotation for resnet18 (#98507)

Commit
2 years ago
[quant][pt2e] QNNPackQuantizer support annotation for resnet18 (#98507) Summary: This PR adds annotation support for conv2d relu, linear, maxpool2d, add and add relu so that we can successfully quantize resnet18 with the prepare_pt2e_quantizer API and get the same result as fx graph mode quantization Test Plan: python test/test_quantization.py TestQuantizePT2EModels.test_resnet18_with_quantizer_api Reviewers: Subscribers: Tasks: Tags: Pull Request resolved: https://github.com/pytorch/pytorch/pull/98507 Approved by: https://github.com/vkuzo
Author
Committer
Parents
Loading