saymrwulf/pytorch
1
0
Fork 0
mirror of https://github.com/saymrwulf/pytorch.git synced 2026-05-15 21:00:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
pytorch/test/quantization
History
Vasiliy Kuznetsov 9fe2673d1c ns for fx: additional bugfix for user defined functions (#57028) 
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/57028

Adds a test case for wrapped sigmoid, and fixes the following issues
to make it pass in NS:
* allows comparing between x.sigmoid() and torch.sigmoid(x), if they are related
* allows dtype cast from FP32_OR_INT8 to FP32, via dequantize (this will be improved later)

Test Plan:
```
python test/test_quantization.py TestFXNumericSuiteCoreAPIs.test_user_defined_function
```

Reviewed By: jerryzh168

Differential Revision: D28030089

Pulled By: vkuzo

fbshipit-source-id: b237353e2d564a4476f409df461746a259015a4b
2021-04-27 16:29:03 -07:00
..
serialized Adding a version serialization type to ConvPackedParam (#43086) 2020-08-28 15:41:30 -07:00
__init__.py remediation of S205607 2020-07-17 17:19:47 -07:00
test_backward_compatibility.py Adding a version serialization type to ConvPackedParam (#43086) 2020-08-28 15:41:30 -07:00
test_bias_correction.py Numeric Suite: Swap with shadow modules only for quantized part of model (#51052) 2021-02-04 11:40:30 -08:00
test_equalize.py cross_layer_equalization (#41685) 2020-07-22 08:39:23 -07:00
test_fusion_passes.py
test_numeric_suite.py Numeric Suite: Swap with shadow modules only for quantized part of model (#51052) 2021-02-04 11:40:30 -08:00
test_numeric_suite_fx.py ns for fx: additional bugfix for user defined functions (#57028) 2021-04-27 16:29:03 -07:00
test_qat_module.py Remove legacy constructor calls from pytorch codebase. (#54142) 2021-04-11 15:45:17 -07:00
test_quantize.py quant: fix conv transpose with qconfig == None (#52844) 2021-02-25 11:52:30 -08:00
test_quantize_fx.py [quant][graphmode][fx] Support preserving attributes in deepcopy of observed/quantized graphmodule (#56550) 2021-04-22 15:02:44 -07:00
test_quantize_jit.py Add padding_idx argument to EmbeddingBag (#49237) 2021-04-14 09:38:01 -07:00
test_quantized_functional.py [reland][quant] Remove nn.quantized.ReLU module and nn.quantized.functional.relu (#47415) (#48038) 2020-11-17 09:52:21 -08:00
test_quantized_module.py [quantization] Fix deepcopy on quantized ConvNd (#56154) 2021-04-15 15:18:22 -07:00
test_quantized_op.py Fix overflow issue in quantized instance_norm/layer_norm/group_norm (#54872) 2021-04-13 10:21:38 -07:00
test_quantized_tensor.py [quant] PerChannelFloatQParams support for quint4x2 dtype (#45594) 2020-10-01 23:59:53 -07:00
test_workflow_module.py Remove legacy constructor calls from pytorch codebase. (#54142) 2021-04-11 15:45:17 -07:00