Tilak
Tilak
@frost-is, To expedite the trouble-shooting process, could you please provide a complete code you are using. It helps to analyse the issue. Thank you!
@frost-is, The files which are provided consist of a huge amount of data which we are unable to download and difficult to reproduce the issue. Could you please simplify the...
@frost-is, Thanks for opening this issue. Development of keras moved to another [repository](https://github.com/keras-team/keras/issues). Could you please post this issue on keras-team/keras [repo](https://github.com/keras-team/keras/issues). To know more please refer: https://discuss.tensorflow.org/t/keras-project-moved-to-new-repository-in-https-github-com-keras-team-keras/1999 Thank you!
@frost-is, Could you please feel free to move this issue to closed status, so that we can track the issue there. Thank you!
@Zahlii, There is a behavior change for `tf.keras.initializers` in tensorflow v**2.10**. `Keras initializers` will now use stateless random ops to generate random numbers. Both seeded and unseeded initializers will always...
@maybeLee, Could you please confirm where the issue persists when the code is executed in GPU mode only or CPU too? Thank you!
@gowthamkpr , I was able to reproduce the issue on tensorflow [v2.8](https://colab.research.google.com/gist/tilakrayal/0bf3486af1547a05eaeb6495bb35ab36/2-8.ipynb), [v2.9](https://colab.research.google.com/gist/tilakrayal/9db305dedadd9933780415a957678be4/2-9.ipynb) and [nightly](https://colab.research.google.com/gist/tilakrayal/25efbf0fc3aaae7bc02193ce9e4c5bae/2-11.ipynb). Kindly find the gist of it here.
@crbean, Could you please try to use the latest stable tensorflow v2.10 from [here](https://github.com/tensorflow/tensorflow/blob/master/RELEASE.md#breaking-changes) and let us know if you are facing same issue. Thank you!
@crbean, Could you please take a look at this [comment](https://github.com/tensorflow/tensorflow/issues/57734#issuecomment-1254322274) from the developer. Thank you!
@crbean, Could you please try to use the latest stable tensorflow v2.10 from [here](https://github.com/tensorflow/tensorflow/blob/master/RELEASE.md#breaking-changes) and let us know if you are facing same issue. Thank you!