Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/39090
Makes quantized GroupNorm work in eager mode post training static quant.
Test Plan:
```
python test/test_quantization.py TestPostTrainingStatic.test_normalization
python test/test_quantization.py TestStaticQuantizedModule.test_group_norm
```
Imported from OSS
Differential Revision: D21885262
fbshipit-source-id: 58b0ffb59c601fcb4c79f711c7c98a667ffc6170
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/38434
We insert dequantize for each use in order to produce quantization patterns that will
later be fused, after that we should also remove extra dequantize node produced by this operation.
Test Plan: Imported from OSS
Differential Revision: D21597834
fbshipit-source-id: 18dfb2760bbb08932aa4e1d06f96cfc5fb37ed88
Summary:
Return unmodified type from decorator if fbgemm is present.
Fix `Tried to trace <__torch__.torch.classes.rnn.CellParamsBase object at 0x55f504c56b40> but it is not part of the active trace. Modules that are called during a trace must be registered as submodules of the thing being traced` thrown from `TestPostTrainingDynamic.test_quantized_rnn` by preserving modules in returned qRNNBase (i.e. by partially reverting https://github.com/pytorch/pytorch/pull/38134 )
Pull Request resolved: https://github.com/pytorch/pytorch/pull/38432
Differential Revision: D21567333
Pulled By: malfet
fbshipit-source-id: 364fa2c8fc6e400b4f2e425b922a977756aec1d8
Summary:
I've picked wrong revision when landed the diff, it should have had an actual check rather than `if True`:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/38058
Differential Revision: D21466152
Pulled By: malfet
fbshipit-source-id: 03fdc510562fab44b7d64a42284d4c3c1f8e940a
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/37366
- we can put both fake quant module and observer module tests in the test_workflow_module.py
- added test_quantized_functional.py
- moved tests in test_numerics.py to test_quantize.py and removed test_numerics.py
Test Plan:
python test/test_quantization.py
Imported from OSS
Differential Revision: D21282198
fbshipit-source-id: 60107cee7d1ed2cd14a45650e91ec28b8a262c52
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/36604
Adds the logic to wrap the HardSwish module in FakeQuant
to support QAT.
Test Plan:
Added test to cover that this happens properly.
Imported from OSS
Differential Revision: D21045322
fbshipit-source-id: 8c46559ade58a5d5c56442285842627a3143eb0f
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/36545
* adds a quantized nn.module for Hardswish so we can observe activation values
* modifies the hardswish op to allow specifying scale + zero_point
* makes hardswish model be properly swapped in static quantization
Test Plan:
added tests and they pass for:
* the new _out flavor of hardswish
* QNNPACK changes
* static quant e2e
Imported from OSS
Differential Revision: D21045320
fbshipit-source-id: ab7e52f0f54a7d5923ab6f58197022cc28c12354
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/36173
Previously we were ignoring the conv bias during training if it existed
This PR adds the bias from the conv op during the conv+bn fusion process
Test Plan:
python test/quantization/test_quantization.py
Imported from OSS
Differential Revision: D20921613
fbshipit-source-id: eacb2ccf9107f413ac4ef23163ba914af9b90924
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/30445
Create distributed and rpc directories under caffe/test for better management
of unit tests.
Differential Revision: D18702786
fbshipit-source-id: e9daeed0cfb846ef68806f6decfcb57c0e0e3606
