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

Convert pytorch module to openvino #32

Open
kentngooi opened this issue May 30, 2022 · 1 comment
Open

Convert pytorch module to openvino #32

kentngooi opened this issue May 30, 2022 · 1 comment

Comments

@kentngooi
Copy link

kentngooi commented May 30, 2022

I am facing this error when i run convert_model.py Then i got the error below.
(File "convert_model.py", line 46, in main
num_layers = args.num_layers
AttributeError: 'Namespace' object has no attribute 'num_layers')
Screenshot from 2022-06-01 10-46-53

Then i have removed the num_layer by hashing it as picture below.
Screenshot from 2022-06-01 10-50-56

Then i got the error below.
(torch.nn.modules.module.ModuleAttributeError: 'MobileNetV3' object has no attribute 'scaling')
Screenshot from 2022-05-30 16-05-39
Anyone facing this issue while converting pytorch mobilenetv3 module to onnx? Appreciate if anyone can help to solve this. Thank you.

@kentngooi kentngooi changed the title torch.nn.modules.module.ModuleAttributeError: 'MobileNetV3' object has no attribute 'scaling' Convert pytorch module to openvino Jun 1, 2022
@kentngooi
Copy link
Author

I found that the issue of the no attribute from 'scaling' is from the model_tools.py
After removing the line as picture below:
Screenshot from 2022-06-01 11-52-26
I am able to convert the file to onnx and able to run the demo.py with the .xml i produced.
May i ask what is the usage of the line in model_tools.py line 230 spoof_out*self.scaling. And will it affect the result if i did not include it?

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

1 participant