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

Tensorflow 'webgl' back-end gets aborted when ran on Chrome with big input file #21

Open
snowme34 opened this issue Dec 24, 2018 · 0 comments
Labels
bug Something isn't working help wanted Extra attention is needed wontfix This will not be worked on

Comments

@snowme34
Copy link
Owner

tensorflow/tfjs#416 (comment)

tensorflow/tfjs#263

If the user uses a big file as input of the Onsets and Frames: Dual-Objective Piano Transcription model and when the model is running on Tensorflow's default backend, webgl, as the issue above states, due to Chrome's watchdog, the model will not be able to finish its job.

Workaround: Use CPU as backend. But it's around 10 times slower.

@snowme34 snowme34 added bug Something isn't working help wanted Extra attention is needed wontfix This will not be worked on labels Dec 24, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working help wanted Extra attention is needed wontfix This will not be worked on
Projects
None yet
Development

No branches or pull requests

1 participant