saymrwulf/pytorch
1
0
Fork 0
mirror of https://github.com/saymrwulf/pytorch.git synced 2026-05-14 20:57:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Remove weight from input of onnxifi backend op (#10575)

Browse source 
Summary:
The ONNXIFI backend will absorb the constant weight in Conv, so we should not add it as an input. This is just a test artifacts. Note that Onnxifi transformer will do the right thing when cutting the graph to absorb the weights.

rdzhabarov
Pull Request resolved: https://github.com/pytorch/pytorch/pull/10575

Reviewed By: houseroad

Differential Revision: D9357339

Pulled By: yinghai

fbshipit-source-id: a613fa3acafa687295312f5211f8e9d7f77b39cd
This commit is contained in:
Yinghai Lu 2018-08-16 10:53:27 -07:00 committed by Facebook Github Bot
parent 319fefe9e6
commit 4be4b4c8b5
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
caffe2/python/onnx/test_onnxifi.py
View file

@ -88,7 +88,7 @@ class OnnxifiTest(TestCase):
model_def = make_model(graph_def, producer_name='conv-test')
op = core.CreateOperator(
"Onnxifi",
["X", "W"],
["X"],
["Y"],
onnx_model=model_def.SerializeToString(),
initializers=["W", "W"],