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
tf.keras.layers.MaxPooling3D crashes #51936
Comments
|
It turns out that |
|
@lugalUrim Please post this issue on keras-team/keras repo. |
|
Hi, I have created a PR for Keras to solve this issue. |
|
While the original issue is coming from tf.keras.layers.MaxPooling3D, the issue is triggered when max_pool3d is called directly with tensorflow itself. For that PR #51975 has been created to fix the issue inside tensorflow. |
|
Thanks for the information @sushreebarsa, I will post new issues in the keras repo, but I guess we can keep this issue in tensorflow, as mentioned by @yongtang there are related bugs in the tensorflow operator implementations as well. |
|
Thank you @WingsBrokenAngel and @yongtang for your PRs! Actually here are more crash bugs I find when
|
System information
Describe the current behavior
tf.keras.layers.MaxPooling3Dcrashes whenpool_sizecontains0, and outputs a all-inf tensor whenpool_sizecontains negative values.Describe the expected behavior
Expect a
ValueErrorto be thrown if the inputpool_sizecontains zero or negative values.Standalone code to reproduce the issue
If the
pool_sizehas0:Outputs:
If the
pool_sizehas negative values:The output is a tensor with
shape=(3, 3, 9, 14, 12)and allinfvalues.The text was updated successfully, but these errors were encountered: