pytorch/torch/quantization
Raghuraman Krishnamoorthi d5298b6e66 Default observer and fake-quant for backends (#26627)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/26627

ghstack-source-id: 91008337

Test Plan: buck test caffe2/test:quantization -- --print-passing-details

Differential Revision: D17518194

fbshipit-source-id: 1eb8a7a85dc811c4ee5228d68563abb157613ceb
2019-09-30 00:37:11 -07:00
..
__init__.py PyTorch Graph Mode Quantization API (#26390) 2019-09-27 19:23:51 -07:00
_quantize_script.py PyTorch Graph Mode Quantization API (#26390) 2019-09-27 19:23:51 -07:00
fake_quantize.py Per channel fake quant (#26623) 2019-09-30 00:21:25 -07:00
fuse_modules.py ConvBn2d/ConvBnReLU2d (#23357) 2019-08-01 10:07:00 -07:00
observer.py Per channel fake quant (#26623) 2019-09-30 00:21:25 -07:00
QConfig.py Default observer and fake-quant for backends (#26627) 2019-09-30 00:37:11 -07:00
quantize.py Add more inplace arguments to quantization top level API (#26782) 2019-09-26 00:07:07 -07:00