-
Notifications
You must be signed in to change notification settings - Fork 101
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
OnnxConstantOfShape Cannot Properly Infer Data Type for Argument value
#703
Comments
Update
This makes me believe it is expecting the value argument is expecting things like |
For this operator (following the example in ONNX specification for ConstantOfShape), you can use this code:
I'll create a PR to make it easier with numpy. |
With the |
I am testing my custom converter for relevance vector machien that I just created with input type np.float64 type:
Scenario 1:
With the following code:
The model could be converted without error.
However, at inference time, the following error is raised:
I visualized the exported model with Netron and found out value is of type float32.
Scenario 2:
However, if I try the following code:
The
to_onnx
call couldn't even finish:I set the data type to np.float64 for testing purpose.
The text was updated successfully, but these errors were encountered: