Update the Segmentation Tutorial Colab to be compatible with Keras 3

[kinarr]

I've identified a couple of issues that occur under specific conditions when using TensorFlow 2.16 and Keras 3's plotting utilities, along with their respective solutions.

Issue 1: AttributeError with plot_model

• Issue: When executing tf.keras.utils.plot_model(model, show_shapes=True), users encounter an AttributeError stating that a 'list' object has no attribute 'shape'.
• Fix: Enhancing the plot_model function call by adding keyword arguments expand_nested=True and dpi=64. This not only resolves the AttributeError but also improves the visualization output (might be a little verbose but works without needing any changes to the plotting APIs). The adjusted function call looks like this:

tf.keras.utils.plot_model(model, show_shapes=True, expand_nested=True, dpi=64)

Issue 2: AttributeError with SparseCategoricalCrossentropy

• Issue: The following code sequence leads to an AttributeError similar to Issue 1, indicating a 'list' object has no attribute 'shape':

loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True, reduction=tf.keras.losses.Reduction.NONE)
loss(label, prediction, sample_weight).numpy()

This occurs when label and prediction are defined as lists, e.g., label = [0,0] and prediction = [[-3., 0], [-3, 0]].

• Fix: Converting label and prediction objects into numpy arrays resolves the issue. The corrected definitions should be as follows:

label = np.array([0,0])
prediction = np.array([[-3., 0], [-3, 0]])

Summary of Changes:

• Added expand_nested=True and dpi=64 keyword arguments to plot_model for enhanced visualization and error prevention.
• Converted y_true and y_pred objects into numpy arrays before passing them to SparseCategoricalCrossentropy to fix the AttributeError.

[github-actions]

Preview

Preview and run these notebook edits with Google Colab:

• site/en/tutorials/images/segmentation.ipynb

Rendered notebook diffs available on ReviewNB.com.

Format and style

Use the TensorFlow docs notebook tools to format for consistent source diffs and lint for style:

$ python3 -m pip install -U --user git+https://github.com/tensorflow/docs

$ python3 -m tensorflow_docs.tools.nbfmt notebook.ipynb

$ python3 -m tensorflow_docs.tools.nblint --arg=repo:tensorflow/docs notebook.ipynb

If commits are added to the pull request, synchronize your local branch: git pull origin image-segmentation-tutorial-keras-3-update

[8bitmp3]

@MarkDaoust @markmcd