Haixin Liu
ca39f99d48
[Pytorch Numeric Suite] Add module level comparison ( #37242 )
...
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/37242
Add module level comparison API.
ghstack-source-id: 102853727
Test Plan: buck test mode/dev caffe2/test:quantization -- 'test_compare_model_stub'
Reviewed By: raghuramank100
Differential Revision: D21232277
fbshipit-source-id: de707eea101a66a37869129460274c56e4e07db2
2020-04-25 16:46:10 -07:00
Alban Desmaison
35b9c89dc1
Revert D21045393: [PyTorch Numeric Suite] Add module level comparison
...
Test Plan: revert-hammer
Differential Revision:
D21045393
Original commit changeset: 4303805f732c
fbshipit-source-id: 06d8a234eda800eb14bc3aa58ff14b0d3cf86d86
2020-04-24 07:03:04 -07:00
Haixin Liu
fba9b9a023
[PyTorch Numeric Suite] Add module level comparison ( #36669 )
...
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/36669
Add module level comparison API.
ghstack-source-id: 102802362
Test Plan: buck test mode/dev caffe2/test:quantization -- 'test_compare_model_stub'
Differential Revision: D21045393
fbshipit-source-id: 4303805f732cc8c8fc67ce40d9594b664507bf82
2020-04-24 00:17:22 -07:00
Nikita Shulga
3b832ee2bf
Use Python3 super() throughout torch.testing. ( #37024 )
...
Summary:
Hattip to ezyang
Pull Request resolved: https://github.com/pytorch/pytorch/pull/37024
Differential Revision: D21173244
Pulled By: malfet
fbshipit-source-id: 7079703e28777d873f69bf9fd4dcbad8d53a2682
2020-04-22 09:00:28 -07:00
Supriya Rao
ee2a9ac56e
[quant][graph] Support for quantized::mul and quantized::mul_scalar ( #36818 )
...
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/36818
Test Plan:
python test_quantize_script.py test_quantized_mul
python test_quantize_script.py test_quantized_mul_scalar
Imported from OSS
Differential Revision: D21134438
fbshipit-source-id: 9ed5e852c5c0c6899a11e3ed36e12b5045608ea4
2020-04-20 15:40:32 -07:00
Supriya Rao
dcfc121fd7
Enable jit trace check_trace for quantized inputs ( #36740 )
...
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/36740
Issue #23986
Test Plan:
python test/quantization/test_quantized_nn_mods.py
Imported from OSS
Differential Revision: D21077551
fbshipit-source-id: fdd15db3284975c99b3e250a568fa94c617d21eb
2020-04-16 19:06:55 -07:00
Vasiliy Kuznetsov
2c558dba3d
quantized layer norm: add to static quant ( #36690 )
...
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/36690
Adds the static quantization hook for LayerNorm
Test Plan:
```
python test/quantization/test_quantized_nn_mods.py ModuleAPITest.test_layer_norm
python test/quantization/test_quantization.py EagerModePostTrainingQuantTest.test_normalization
```
Imported from OSS
Differential Revision: D21055401
fbshipit-source-id: 188329f35359576d50ed0db5fb675ce68c28bf7d
2020-04-16 18:18:02 -07:00
Vasiliy Kuznetsov
91f1d79d1b
hardswish: enable for QAT ( #36604 )
...
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
2020-04-15 18:04:11 -07:00
Vasiliy Kuznetsov
65df8b3886
hardswish: make it work in static quantization ( #36545 )
...
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
2020-04-15 18:02:35 -07:00
Supriya Rao
6972c27d94
[quant] Enable fusion for conv modules with bias ( #36173 )
...
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
2020-04-08 15:53:32 -07:00
Jerry Zhang
6fc2403951
[quant][graphmode] qconfig_dict support None ( #35336 )
...
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/35336
Test Plan:
python test/test_quantization.py
Imported from OSS
Differential Revision: D20655302
fbshipit-source-id: b453f3240ac487aa29629953b4d71274dbbc25fc
2020-03-29 12:47:47 -07:00
Lingyi Liu
fddcd72a31
Add the more fusion (conv3d and batchnorm)support in pytorch quantization flow ( #33540 )
...
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/33540
Differential Revision: D19994498
Pulled By: lly-zero-one
fbshipit-source-id: e5e13eab6924bd2ce1b57b16b672844b8b9638f5
2020-03-23 20:36:03 -07:00
Raghuraman Krishnamoorthi
243cc20451
Enable inplace relu fusion for training ( #33105 )
...
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/33105
Support inplace relu for Conv+BN+Relu fusion during training.
ghstack-source-id: 97944659
Test Plan: buck test caffe2/test:quantization -- 'test_fuse_module_train \(test_quantization\.FusionTest\)' --print-passing-details
Differential Revision: D19795221
fbshipit-source-id: 056dc06050d145750c4d0044c0fc1c3febcfdafc
2020-02-14 12:15:58 -08:00
James Reed
812b1ad869
[quantization] FP16 dynamic quantized Linear
...
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/32331
Test Plan: Imported from OSS
Differential Revision: D19441158
Pulled By: jamesr66a
fbshipit-source-id: c04247ffe707be68718c486c31bc6c6040f7dc11
2020-01-27 15:45:32 -08:00
Pritam Damania
f050b16dd9
Move pytorch distributed tests to separate folder for contbuild. ( #30445 )
...
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
2020-01-22 21:16:59 -08:00
