Skip to content
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.

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

Cannot export EfficientNet to onnx #296

Closed
LamyaMohaned opened this issue Jun 24, 2021 · 2 comments
Closed

Cannot export EfficientNet to onnx #296

LamyaMohaned opened this issue Jun 24, 2021 · 2 comments

Comments

@LamyaMohaned
Copy link

LamyaMohaned commented Jun 24, 2021

Hello

I used the same script for exporting a model to onnx, but I got this error:

RuntimeError: ONNX export failed: Couldn't export Python operator SwishImplementation

when I added this part:
module.set_swish(memory_efficient=False), I got this error:

RuntimeError: Exporting the operator silu to ONNX opset version 9 is not supported. Please open a bug to request ONNX export support for the missing operator.

@LamyaMohaned
Copy link
Author

The problem is solved by upgrading pytorch to 1.8.1

@ShunLu91
Copy link

Hi,
I solved the above issue and managed to export the onnx model.
However, I failed to load the onnx model when transform it to the tensorrt format. Have you ever encountered such issue?

In node -1 (importPad): UNSUPPORTED_NODE: Assertion failed: inputs.at(1).is_weights()

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants