October 12, 2026
Quantization is the first compression lever, not the only one. Structured pruning, magnitude sparsity, and knowledge distillation in Keras 3 — what each one actually buys on real hardware, and how to measure it.
Read moreSeptember 21, 2026 · LayerGenius
A sigmoid output is not a probability and 0.5 is not a threshold. How to measure calibration on a Keras classifier, fix it with temperature scaling or isotonic regression, pick an operating point from the cost of each error, and keep both honest after deploy.
Read moreSeptember 21, 2026 · LayerGenius
Keras 3 can quantize a model's weights in place with model.quantize("int8") — no converter, no second toolchain. What it touches, what it skips, how to measure the accuracy cost, and when GPTQ or a calibration pass is worth the trouble.
Read moreSeptember 14, 2026 · LayerGenius
The server-side half of deployment: exporting a clean serving signature, numbered version directories and rollback, server-side batching for throughput, and how to measure p99 latency before you promise it.
Read moreSeptember 11, 2026 · LayerGenius
Accuracy on the test set is the last honest number you get for free. What to log at serving time, which drift signals are worth alerting on, and how to decide when a retrain is justified.
Read moreJuly 16, 2026
A trained model is not a deliverable — a verified inference artifact is. Export contracts, op coverage, the quantization ladder, and the parity tests that make conversions safe.
Read more