Vasiliy Kuznetsov
f6b25e758d
ns for fx: move it to top level file ( #55060 )
...
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/55060
Removes the previous iteration of Numeric Suite for FX graph mode
quantization, and moves the current iteration into the top level
file.
Test Plan:
```
python test/test_quantization.py TestFXNumericSuiteCoreAPIs
python test/test_quantization.py TestFXGraphMatcher
```
Imported from OSS
Reviewed By: jerryzh168
Differential Revision: D27467725
fbshipit-source-id: 4c22b5a3221857231f9f59cf6d2908820e6a7f12
2021-04-02 09:35:27 -07:00
Xin (Annie) Guan
74ec9e7ccf
compare_model_outputs_fx API implementation ( #49266 )
...
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/49266
compare_model_outputs_fx API implementation
ghstack-source-id: 120828880
Test Plan:
buck test mode/dev caffe2/test:quantization_fx -- 'test_compare_model_outputs_linear_static_fx'
buck test mode/dev caffe2/test:quantization_fx -- 'test_compare_model_outputs_conv_static_fx'
buck test mode/dev caffe2/test:quantization_fx -- 'test_compare_model_stub_linear_static_fx'
buck test mode/dev caffe2/test:quantization_fx -- 'test_compare_model_stub_conv_static_fx'
buck test mode/dev caffe2/test:quantization -- 'test_compare_model_outputs_linear_static'
buck test mode/dev caffe2/test:quantization -- 'test_compare_model_outputs_conv_static'
Reviewed By: vkuzo
Differential Revision: D25507933
fbshipit-source-id: 1b502b5eadb0fafbe9e8c2e843410bca03c63fd6
2021-02-02 10:43:25 -08:00
Xin (Annie) Guan
c354888e5d
compare_model_stub_fx API implementation ( #48951 )
...
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/48951
compare_model_stub_fx API implementation
ghstack-source-id: 120817825
Test Plan:
buck test mode/dev caffe2/test:quantization_fx -- 'test_compare_model_stub_conv_static_fx'
buck test mode/dev caffe2/test:quantization_fx -- 'test_compare_model_stub_linear_static_fx'
Reviewed By: vkuzo
Differential Revision: D25379000
fbshipit-source-id: f1321d37b60b56b202e7d227e370ce13addb10cc
2021-02-01 22:16:14 -08:00
Richard Barnes
14edc726d9
Clean up some type annotations in caffe2/torch/quantization ( #49942 )
...
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/49942
Upgrades type annotations from Python2 to Python3
Test Plan: Sandcastle tests
Reviewed By: vkuzo
Differential Revision: D25717551
fbshipit-source-id: 1b63dc485ecf6641641b05f7ce095ae1d2d87346
2020-12-29 15:43:50 -08:00
Xin Guan
f8722825b5
Compare Weights FX Implementation ( #48056 )
...
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/48056
PyTorch FX Quantization API: Compare weights
ghstack-source-id: 117255311
Test Plan:
buck test mode/dev caffe2/test:quantization -- 'test_remove_qconfig_observer_fx'
buck test mode/dev caffe2/test:quantization -- 'test_compare_weights_linear_dynamic_fx'
buck test mode/dev caffe2/test:quantization -- 'test_compare_weights_linear_static_fx'
buck test mode/dev caffe2/test:quantization -- 'test_compare_weights_conv_static_fx'
Reviewed By: hx89
Differential Revision: D24940516
fbshipit-source-id: 301c1958c0e64ead9072e0fd002e4b21e8cb5b79
2020-11-20 17:17:19 -08:00
