We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
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
In ONNX graph surgeon, it appears that models whose edges have sequence and, possibly, map type don't get properly imported.
sequence
The text was updated successfully, but these errors were encountered:
I suggest that zipmap op need split two output.
zipmap
Sorry, something went wrong.
The amount of outputs can be arbitrary because it accepts classlabels_int / classlabels_str attribute which can be any length.
classlabels_int
classlabels_str
That is your outputs are dynamic shape. TRT support this feature.
Ah, well, the issue is with onnx_graphsurgeon Python library.
No branches or pull requests
Description
In ONNX graph surgeon, it appears that models whose edges have
sequence
and, possibly, map type don't get properly imported.The text was updated successfully, but these errors were encountered: