batch out of range & loss value becomes 'nan' when running monocular depth estimation about keras-io HOT 6 OPEN

You seem to be using the older Keras version in your local system. Keras 3 with multi backend feature is available, you can upgrade the Keras package and try again.

pip install -U keras

from keras-io.

Below screenshot is using Keras 3. Batch no longer goes out of range but loss values still become nan.

from keras-io.

Are you satisfied with the resolution of your issue?
Yes
No

from keras-io.

The tutorial which you are referring to has not been migrated to Keras 3 yet, possibly due to some dependency on Tensorflow or Keras 2 APIs.

I was able ti run the tutorial successfully for 1 epoch with TensorFlow 2.15 which uses Keras 2.15 in it's backend.
Attaching the working Gist here for reference https://colab.sandbox.google.com/gist/sachinprasadhs/5aead85438db273c01e72ec257d6c09e/depth_estimation.ipynb

from keras-io.

It works for 1 epoch for me as well in both Keras 2 and Keras 3. The issue arises when I need to train the model for more than 1 epoch which results in the above behavior. Also, since the loss values become undefined, the neural network starts to output nothing but a black screen as shown here.

from keras-io.

In the published tutorial we can see output for more number of epochs.
Since the tutorial is not yet migrated to Keras 3, we can look at it once the tutorial is migrated to Keras 3, Keras team doesn't have enough bandwidth to migrate tutorials.
Community contributions are welcome.

from keras-io.