Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/23891
This adds an initial set of testing coverage for quantization that checks if the modules can be scripted. Testing for tracing and serialization is forthcoming
Test Plan: Imported from OSS
Differential Revision: D16698045
Pulled By: jamesr66a
fbshipit-source-id: 96d80d938b816220af72359165a7b96d998a30c9
Summary:
adding qconv+relu and qlinear+relu modules in nn/_intrinsic/quantized
Pull Request resolved: https://github.com/pytorch/pytorch/pull/23410
Test Plan:
Extended tests to test these new modules as well
buck test mode/dev caffe2/test:quantized -- 'test_linear_api' --print-passing-details
```
Running 1 tests
Started new test run: https://our.intern.facebook.com/intern/testinfra/testrun/2251799820197379
✓ caffe2/test:quantized - test_linear_api (test_nn_quantized.ModuleAPITest) 4.055 1/1 (passed)
Test output:
> test_linear_api (test_nn_quantized.ModuleAPITest)
> test API functionality for nn.quantized.linear and nn._intrinsic.quantized.linear_relu ... ok
>
> ----------------------------------------------------------------------
> Ran 1 test in 4.056s
>
> OK
Finished test run: https://our.intern.facebook.com/intern/testinfra/testrun/2251799820197379
Summary (total time 10.66s):
PASS: 1
FAIL: 0
SKIP: 0
FATAL: 0
TIMEOUT: 0
OMIT: 0
```
buck test mode/dev caffe2/test:quantized -- 'test_conv_api' --print-passing-details
```
Running 2 tests
Started new test run: https://our.intern.facebook.com/intern/testinfra/testrun/4785074607089664
✓ caffe2/test:quantized - test_conv_api (test_quantized_conv.QuantizedConvTest) 5.195 1/2 (passed)
Test output:
> test_conv_api (test_quantized_conv.QuantizedConvTest)
> Tests the correctness of the conv functional. ... ok
>
> ----------------------------------------------------------------------
> Ran 1 test in 5.195s
>
> OK
✓ caffe2/test:quantized - test_conv_api (test_nn_quantized.ModuleAPITest) 10.616 2/2 (passed)
Test output:
> test_conv_api (test_nn_quantized.ModuleAPITest)
> Tests the correctness of the conv module. ... ok
>
> ----------------------------------------------------------------------
> Ran 1 test in 10.616s
>
> OK
Finished test run: https://our.intern.facebook.com/intern/testinfra/testrun/4785074607089664
Summary (total time 17.31s):
PASS: 2
FAIL: 0
SKIP: 0
FATAL: 0
TIMEOUT: 0
OMIT: 0
``
Differential Revision: D16505333
Pulled By: dskhudia
fbshipit-source-id: 04f45cd0e76dc55f4694d558b913ab2958b7d727
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/22733
This refactor changes the conv module to avoid the usage of the functional ops.
Reviewed By: jerryzh168
Differential Revision: D15835572
fbshipit-source-id: f2294cd708fbe8372eb3a15cc60d83777d4f7029
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/22765
the pooling signature is the same as the non-quantized one. Adding it to the native_functions.yaml
Reviewed By: jerryzh168
Differential Revision: D16102608
fbshipit-source-id: 7627ad8f02a231f488b74d1a245b853f89d9c419
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/21921
Call FBGEMM kernels to implement quantized linear operator. This operator is used only for inference.
Differential Revision: D15375695
fbshipit-source-id: b9ca6c156fd60481fea83e55603b2897f7bfc3eb
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/19816
We need this for quantization for bias
add third argument of ScalarType to `quantize_linear`
Differential Revision: D15094174
fbshipit-source-id: f19ec8f4716cf5fe0aa21b38d45af6d27c9ab377
