pytorch/torch/quantization/ns
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
..
__init__.py
graph_matcher.py ns for fx: return results in execution order (#61360) 2021-07-17 20:53:39 -07:00
graph_passes.py ns for fx: add ref_node_target_type (#62685) 2021-08-05 09:26:10 -07:00
mappings.py ns for fx: preserve observers and fake_quants through passes (#61323) 2021-07-17 20:53:33 -07:00
ns_types.py
pattern_utils.py ns for fx: preserve observers and fake_quants through passes (#61323) 2021-07-17 20:53:33 -07:00
utils.py ns for fx: fix typing issue in weight extraction (#62041) 2021-07-23 09:31:33 -07:00
weight_utils.py ns for fx: add ref_node_target_type (#62685) 2021-08-05 09:26:10 -07:00