Skip to content

Instantly share code, notes, and snippets.

@sammlapp
Created October 24, 2025 12:29
Show Gist options
  • Select an option

  • Save sammlapp/7e087d4949d5ace04410836a71233a5f to your computer and use it in GitHub Desktop.

Select an option

Save sammlapp/7e087d4949d5ace04410836a71233a5f to your computer and use it in GitHub Desktop.
Model Status Error Type Error Message Full Traceback
ConvNeXt Success
EfficientNet Failed ConversionError Failed to convert the exported program to an ONNX model. This is step 3/3 of exporting the model to ONNX. Next steps: - If there is a missing ONNX function, implement it and register it to the registry. - If there is an internal error during ONNX conversion, debug the error and submit a PR to PyTorch. - Create an error report with `torch.onnx.export(..., report=True)`, and save the ExportedProgram as a pt2 file. Create an issue in the PyTorch GitHub repository against the *onnx* component. Attach the error report and the pt2 model. Error report has been saved to 'onnx_export_2025-10-24_08-22-58-034161_conversion.md'. ## Exception summary <class 'ValueError'>: Key 'b_features_0_1_running_mean' does not match the name of the value 'getitem_3'. Please use the value.name as the key. (Refer to the full stack trace above for more information.) Traceback (most recent call last): File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/torch/onnx/_internal/exporter/_core.py", line 1475, in export onnx_program = _exported_program_to_onnx_program( decomposed_program, registry=registry ) File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/torch/onnx/_internal/exporter/_core.py", line 1165, in _exported_program_to_onnx_program model.graph.initializers[value_name] = value ~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^ File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/onnx_ir/_graph_containers.py", line 264, in __setitem__ raise ValueError( f"Key '{key}' does not match the name of the value '{value.name}'. Please use the value.name as the key." ) ValueError: Key 'b_features_0_1_running_mean' does not match the name of the value 'getitem_3'. Please use the value.name as the key. The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/var/folders/d8/265wdp1n0bn_r85dh3pp95fh0000gq/T/ipykernel_75925/728818843.py", line 21, in <module> onnx_program = torch.onnx.export( m, ...<3 lines>... dynamo=True, ) File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/torch/onnx/__init__.py", line 296, in export return _compat.export_compat( ~~~~~~~~~~~~~~~~~~~~~^ model, ^^^^^^ ...<20 lines>... legacy_export_kwargs=legacy_export_kwargs, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ) ^ File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/torch/onnx/_internal/exporter/_compat.py", line 143, in export_compat onnx_program = _core.export( model, ...<11 lines>... verbose=verbose, ) File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/torch/onnx/_internal/exporter/_flags.py", line 27, in wrapper return func(*args, **kwargs) File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/torch/onnx/_internal/exporter/_core.py", line 1521, in export raise _errors.ConversionError( ...<3 lines>... ) from e torch.onnx._internal.exporter._errors.ConversionError: Failed to convert the exported program to an ONNX model. This is step 3/3 of exporting the model to ONNX. Next steps: - If there is a missing ONNX function, implement it and register it to the registry. - If there is an internal error during ONNX conversion, debug the error and submit a PR to PyTorch. - Create an error report with `torch.onnx.export(..., report=True)`, and save the ExportedProgram as a pt2 file. Create an issue in the PyTorch GitHub repository against the *onnx* component. Attach the error report and the pt2 model. Error report has been saved to 'onnx_export_2025-10-24_08-22-58-034161_conversion.md'. ## Exception summary <class 'ValueError'>: Key 'b_features_0_1_running_mean' does not match the name of the value 'getitem_3'. Please use the value.name as the key. (Refer to the full stack trace above for more information.)
MobileNetV2 Failed ConversionError Failed to convert the exported program to an ONNX model. This is step 3/3 of exporting the model to ONNX. Next steps: - If there is a missing ONNX function, implement it and register it to the registry. - If there is an internal error during ONNX conversion, debug the error and submit a PR to PyTorch. - Create an error report with `torch.onnx.export(..., report=True)`, and save the ExportedProgram as a pt2 file. Create an issue in the PyTorch GitHub repository against the *onnx* component. Attach the error report and the pt2 model. Error report has been saved to 'onnx_export_2025-10-24_08-23-01-437732_conversion.md'. ## Exception summary <class 'ValueError'>: Key 'b_features_0_1_running_mean' does not match the name of the value 'getitem_3'. Please use the value.name as the key. (Refer to the full stack trace above for more information.) Traceback (most recent call last): File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/torch/onnx/_internal/exporter/_core.py", line 1475, in export onnx_program = _exported_program_to_onnx_program( decomposed_program, registry=registry ) File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/torch/onnx/_internal/exporter/_core.py", line 1165, in _exported_program_to_onnx_program model.graph.initializers[value_name] = value ~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^ File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/onnx_ir/_graph_containers.py", line 264, in __setitem__ raise ValueError( f"Key '{key}' does not match the name of the value '{value.name}'. Please use the value.name as the key." ) ValueError: Key 'b_features_0_1_running_mean' does not match the name of the value 'getitem_3'. Please use the value.name as the key. The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/var/folders/d8/265wdp1n0bn_r85dh3pp95fh0000gq/T/ipykernel_75925/728818843.py", line 21, in <module> onnx_program = torch.onnx.export( m, ...<3 lines>... dynamo=True, ) File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/torch/onnx/__init__.py", line 296, in export return _compat.export_compat( ~~~~~~~~~~~~~~~~~~~~~^ model, ^^^^^^ ...<20 lines>... legacy_export_kwargs=legacy_export_kwargs, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ) ^ File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/torch/onnx/_internal/exporter/_compat.py", line 143, in export_compat onnx_program = _core.export( model, ...<11 lines>... verbose=verbose, ) File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/torch/onnx/_internal/exporter/_flags.py", line 27, in wrapper return func(*args, **kwargs) File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/torch/onnx/_internal/exporter/_core.py", line 1521, in export raise _errors.ConversionError( ...<3 lines>... ) from e torch.onnx._internal.exporter._errors.ConversionError: Failed to convert the exported program to an ONNX model. This is step 3/3 of exporting the model to ONNX. Next steps: - If there is a missing ONNX function, implement it and register it to the registry. - If there is an internal error during ONNX conversion, debug the error and submit a PR to PyTorch. - Create an error report with `torch.onnx.export(..., report=True)`, and save the ExportedProgram as a pt2 file. Create an issue in the PyTorch GitHub repository against the *onnx* component. Attach the error report and the pt2 model. Error report has been saved to 'onnx_export_2025-10-24_08-23-01-437732_conversion.md'. ## Exception summary <class 'ValueError'>: Key 'b_features_0_1_running_mean' does not match the name of the value 'getitem_3'. Please use the value.name as the key. (Refer to the full stack trace above for more information.)
ResNet Failed ConversionError Failed to convert the exported program to an ONNX model. This is step 3/3 of exporting the model to ONNX. Next steps: - If there is a missing ONNX function, implement it and register it to the registry. - If there is an internal error during ONNX conversion, debug the error and submit a PR to PyTorch. - Create an error report with `torch.onnx.export(..., report=True)`, and save the ExportedProgram as a pt2 file. Create an issue in the PyTorch GitHub repository against the *onnx* component. Attach the error report and the pt2 model. Error report has been saved to 'onnx_export_2025-10-24_08-23-04-738877_conversion.md'. ## Exception summary <class 'ValueError'>: Key 'b_bn1_running_mean' does not match the name of the value 'getitem_3'. Please use the value.name as the key. (Refer to the full stack trace above for more information.) Traceback (most recent call last): File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/torch/onnx/_internal/exporter/_core.py", line 1475, in export onnx_program = _exported_program_to_onnx_program( decomposed_program, registry=registry ) File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/torch/onnx/_internal/exporter/_core.py", line 1165, in _exported_program_to_onnx_program model.graph.initializers[value_name] = value ~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^ File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/onnx_ir/_graph_containers.py", line 264, in __setitem__ raise ValueError( f"Key '{key}' does not match the name of the value '{value.name}'. Please use the value.name as the key." ) ValueError: Key 'b_bn1_running_mean' does not match the name of the value 'getitem_3'. Please use the value.name as the key. The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/var/folders/d8/265wdp1n0bn_r85dh3pp95fh0000gq/T/ipykernel_75925/728818843.py", line 21, in <module> onnx_program = torch.onnx.export( m, ...<3 lines>... dynamo=True, ) File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/torch/onnx/__init__.py", line 296, in export return _compat.export_compat( ~~~~~~~~~~~~~~~~~~~~~^ model, ^^^^^^ ...<20 lines>... legacy_export_kwargs=legacy_export_kwargs, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ) ^ File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/torch/onnx/_internal/exporter/_compat.py", line 143, in export_compat onnx_program = _core.export( model, ...<11 lines>... verbose=verbose, ) File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/torch/onnx/_internal/exporter/_flags.py", line 27, in wrapper return func(*args, **kwargs) File "/Users/SML161/miniconda3/envs/opso_dev/lib/python3.13/site-packages/torch/onnx/_internal/exporter/_core.py", line 1521, in export raise _errors.ConversionError( ...<3 lines>... ) from e torch.onnx._internal.exporter._errors.ConversionError: Failed to convert the exported program to an ONNX model. This is step 3/3 of exporting the model to ONNX. Next steps: - If there is a missing ONNX function, implement it and register it to the registry. - If there is an internal error during ONNX conversion, debug the error and submit a PR to PyTorch. - Create an error report with `torch.onnx.export(..., report=True)`, and save the ExportedProgram as a pt2 file. Create an issue in the PyTorch GitHub repository against the *onnx* component. Attach the error report and the pt2 model. Error report has been saved to 'onnx_export_2025-10-24_08-23-04-738877_conversion.md'. ## Exception summary <class 'ValueError'>: Key 'b_bn1_running_mean' does not match the name of the value 'getitem_3'. Please use the value.name as the key. (Refer to the full stack trace above for more information.)
SqueezeNet Success
VGG Success
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment