Skip to content

Fix bug that renamed subgraph i/o twice #1478

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Apr 27, 2021
Merged

Fix bug that renamed subgraph i/o twice #1478

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
dd45f8e
Fix bug that renamed subgraph i/o twice
TomWildenhain-Microsoft Apr 27, 2021
f261c27
Merge branch 'master' into tom/fix_subgraph_bug
TomWildenhain-Microsoft Apr 27, 2021
e350e7e
Don't rename tensors in subgraphs at all
TomWildenhain-Microsoft Apr 27, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 7 additions & 8 deletions tf2onnx/tfonnx.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -511,8 +511,6 @@ def rename_tensors_in_nodes(onnx_nodes):
for func in ordered_func:
f_inputs_names = [t.name for t in func.inputs]
f_output_names = [t.name for t in func.outputs]
f_inputs_names = rename_tensors_in_list(f_inputs_names)
f_output_names = rename_tensors_in_list(f_output_names)
fg = process_tf_graph(func, continue_on_error, False, target, opset,
custom_op_handlers, custom_rewriter,
extra_opset, shape_override, inputs_as_nchw,
Expand All @@ -524,12 +522,13 @@ def rename_tensors_in_nodes(onnx_nodes):

check_io(input_names, output_names, output_shapes)

rename_tensors_in_nodes(onnx_nodes)
input_names = rename_tensors_in_list(input_names)
output_names = rename_tensors_in_list(output_names)
output_shapes = rename_tensors_in_dict(output_shapes)
dtypes = rename_tensors_in_dict(dtypes)
inputs_as_nchw = rename_tensors_in_list(inputs_as_nchw)
if not is_subgraph:
rename_tensors_in_nodes(onnx_nodes)
Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We actually don't need to rename tensors in subgraphs at all.

input_names = rename_tensors_in_list(input_names)
output_names = rename_tensors_in_list(output_names)
output_shapes = rename_tensors_in_dict(output_shapes)
dtypes = rename_tensors_in_dict(dtypes)
inputs_as_nchw = rename_tensors_in_list(inputs_as_nchw)
g = Graph(onnx_nodes, output_shapes, dtypes, target, opset, extra_opset, input_names, output_names, is_subgraph)
g = process_parsed_graph(g, custom_op_handlers, inputs_as_nchw, continue_on_error, custom_rewriter, target,
output_names, initialized_tables, outputs_to_values, outputs_to_dtypes, op_cnt, attr_cnt)
Expand Down