saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-10 17:37:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

[Symbolic shape infer] fix a bug in loop/scan (#8694)

Browse source 
In Loop/Scan, subgraph output may be partly in subgraph input
This commit is contained in:
KeDengMS 2021-08-12 17:57:28 -07:00 committed by GitHub
parent 1a8adb96fe
commit d9d0228d0b
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
onnxruntime/python/tools/symbolic_shape_infer.py
View file

@ -1711,8 +1711,8 @@ class SymbolicShapeInference:
# topological sort nodes, note there might be dead nodes so we check if all graph outputs are reached to terminate
sorted_nodes = []
sorted_known_vi = set([i.name for i in list(self.out_mp_.graph.input) + list(self.out_mp_.graph.initializer)])
if all([o.name in sorted_known_vi for o in self.out_mp_.graph.output]):
# Loop/Scan will have all graph output in graph inputs, so don't do topological sort
if any([o.name in sorted_known_vi for o in self.out_mp_.graph.output]):
# Loop/Scan will have some graph output in graph inputs, so don't do topological sort
sorted_nodes = self.out_mp_.graph.node
else:
while not all([o.name in sorted_known_vi for o in self.out_mp_.graph.output]):