Vasiliy Kuznetsov b524a1101a ns for fx: add ref_node_target_type (#62685) ... Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/62685 Adds a `ref_node_target_type` field to hold the string type of the base node. This is needed because in some cases the previous node does not match ref_node (if we have observers, or if we are logging inputs), and it is useful to know the type of ref_node. Test Plan: ``` python test/test_quantization.py TestFXNumericSuiteCoreAPIs ``` Imported from OSS Reviewed By: hx89 Differential Revision: D30082947 fbshipit-source-id: 98ded7b25a5d8d5ea820e0ef62c3799b65c3fc77		2021-08-05 09:26:10 -07:00
..
fx	[quant] Input-weight equalization - branch support (#62366)	2021-08-03 12:45:25 -07:00
ns	ns for fx: add ref_node_target_type (#62685)	2021-08-05 09:26:10 -07:00
__init__.py	[quant][graphmode] relax the constraint for supported_dtypes for reference option (Linear and Conv) (#62348)	2021-07-29 16:31:04 -07:00
_correct_bias.py
_equalize.py
_learnable_fake_quantize.py
_numeric_suite.py
_numeric_suite_fx.py	ns for fx: add ref_node_target_type (#62685)	2021-08-05 09:26:10 -07:00
fake_quantize.py	[quant] Support PerChannel quantization in FusedMovingAvgObsFakeQuantize (#62346)	2021-08-01 21:45:11 -07:00
fuse_modules.py
fuser_method_mappings.py
observer.py	[quant] update per-channel observer min/max_val attribute names (#62345)	2021-07-29 22:28:53 -07:00
qconfig.py	Support for reference convert_fx working on gpu	2021-07-23 10:30:38 -07:00
quant_type.py
quantization_mappings.py
quantize.py	Support for reference convert_fx working on gpu	2021-07-23 10:30:38 -07:00
quantize_fx.py
quantize_jit.py
stubs.py
utils.py