Vasiliy Kuznetsov 2a2bc1fc8a ns for fx: add fqn to results, when present (#61377) ... Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/61377 Both the quantization tracer and the NS tracer record `_node_name_to_scope`, which contains the mapping from node name to FQN. This PR adds the FQN information to the NS results, so that it is more convenient for users to attribute a NS result to the corresponding module in their model. Test Plan: ``` python test/test_quantization.py TestFXNumericSuiteCoreAPIs.test_extract_weights_fqn python test/test_quantization.py TestFXNumericSuiteCoreAPIs.test_match_activations_fqn python test/test_quantization.py TestFXNumericSuiteCoreAPIs.test_shadow_activations_fqn ``` Imported from OSS Reviewed By: jerryzh168 Differential Revision: D29600349 fbshipit-source-id: df489e03daff97dd380f59c83ffdc2b0012a0a53		2021-07-17 20:53:41 -07:00
..
fx	ns for fx: support comparing fp32 vs fp32_prepared, except shadowed (#61129)	2021-07-17 20:52:23 -07:00
ns	ns for fx: add fqn to results, when present (#61377)	2021-07-17 20:53:41 -07:00
__init__.py	Un-ignore F403 in .flake8 (#55838)	2021-04-13 09:24:07 -07:00
_correct_bias.py
_equalize.py	[quant] Eager mode equalization support for ConvReLU and LinearReLU (#58792)	2021-05-24 17:25:13 -07:00
_learnable_fake_quantize.py	[docs] Fix backticks in docs (#60474)	2021-06-24 06:27:41 -07:00
_numeric_suite_fx.py	ns for fx: add fqn to results, when present (#61377)	2021-07-17 20:53:41 -07:00
_numeric_suite.py	Add lint for unqualified type: ignore (#56290)	2021-04-21 08:07:23 -07:00
fake_quantize.py	[quant] update FakeQuant modules to use tensor qparams (#61318)	2021-07-10 19:43:02 -07:00
fuse_modules.py	Add lint for unqualified noqa (#56272)	2021-04-19 13:16:18 -07:00
fuser_method_mappings.py	fix docstring for fusing functions (#58638)	2021-05-24 18:27:22 -07:00
observer.py	[quant] Add tensor_qparam variant to fake_quantize_per_tensor (#61317)	2021-07-10 19:41:55 -07:00
qconfig.py	Un-ignore F403 in .flake8 (#55838)	2021-04-13 09:24:07 -07:00
quant_type.py
quantization_mappings.py	[quant][graphmode][fx] Produce reference linear module in convert (#60152)	2021-06-20 20:08:12 -07:00
quantize_fx.py	[quant] Input Weight Equalization - prepare modifications (#59747)	2021-06-16 22:32:28 -07:00
quantize_jit.py	Enable the quantization on XPU devices (#54857)	2021-05-20 17:02:13 -07:00
quantize.py	[quant][eager][fix] Fix a typo in convert function in eager mode quantization (#59571)	2021-06-08 10:24:22 -07:00
stubs.py
utils.py	[quant] Equalization Observer modifications (#59953)	2021-06-16 22:32:30 -07:00