Skip to content
#

customsubclassmodel

Here is 1 public repository matching this topic...

Implementation of a custom TensorFlow/Keras model by subclassing tf.keras.Model, including custom layers, a user-defined loss function, and full control over the forward pass. Demonstrates dataset loading, preprocessing, and training on MNIST using the Model Subclassing API for maximum flexibility

  • Updated Aug 17, 2025
  • Jupyter Notebook

Improve this page

Add a description, image, and links to the customsubclassmodel topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the customsubclassmodel topic, visit your repo's landing page and select "manage topics."

Learn more