Fixing example code for CategoricalCrossentropy in losses.py file

[tilakrayal]

The example mentioned for the Keras API CategoricalCrossentropy was failing with the error AttributeError: 'list' object has no attribute 'shape'.

[codecov-commenter]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 82.10%. Comparing base (660da94) to head (8125c3d).

Additional details and impacted files

@@           Coverage Diff           @@
##           master   #20523   +/-   ##
=======================================
  Coverage   82.10%   82.10%           
=======================================
  Files         515      515           
  Lines       47790    47790           
  Branches     7486     7486           
=======================================
  Hits        39238    39238           
  Misses       6738     6738           
  Partials     1814     1814           

Flag	Coverage Δ
keras	81.95% <ø> (ø)
keras-jax	65.04% <ø> (ø)
keras-numpy	60.02% <ø> (ø)
keras-tensorflow	66.03% <ø> (ø)
keras-torch	64.96% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

---

🚨 Try these New Features:

• Flaky Tests Detection - Detect and resolve failed and flaky tests