-
Notifications
You must be signed in to change notification settings - Fork 1.9k
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 run a existing model training in Tensorflow and converted by converter, transpose
rank error
#8084
Comments
transpose
rank errortranspose
rank error
Hi, @Lutra-Fs I apologize for the delayed response and I've invested time in replicating the reported issue on my end and have observed the same behavior you've described. It's evident that further investigation is necessary to thoroughly understand and address this issue. Thank you for bringing this issue to our attention and will update you soon. Thank you for your understanding and patience. Here is error output log for reference :
|
Please make sure that this is a bug. As per our
GitHub Policy,
we only address code/doc bugs, performance issues, feature requests and
build/installation issues on GitHub. tag:bug_template
System information
Describe the current behavior
when running rfft and the after transpose in the browser using WebGL:
in
in
transpose.ts
in@tfjs/core
, although x is a complex64 shape in [1, 13, 64, 33], inlet $real = real($x); let $imag = imag($x);
these two functions get a tensor with shape [832,33]. I have tried to find where the issue happens in the code but failed.
Describe the expected behavior
model runs correctly
Standalone code to reproduce the issue
converted model:
FNO2dLite_from_saved_model.zip
Other info / logs
Node.js cpu backend debug info:
The text was updated successfully, but these errors were encountered: