Tutorials

Working notes from applied deep-learning practice.

Feeding the GPU: A Practical tf.data Performance Checklist

June 3, 2026

When GPU utilization is low, the input pipeline is usually the culprit. Seven checks, ordered by cost and payoff: prefetch, parallel map, cache, small-files fixes, and more.

Migrating tf.keras Code to Keras 3: What Actually Breaks

May 12, 2026

Most model definitions port to Keras 3 with minor edits — the pain concentrates in custom ops, keras.backend usage, serialization, and training loops. A field checklist for the migration.