amir-abdi/keras_to_tensorflow

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1646 stars · 524 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python CLI tool that converts trained Keras models (.h5 or .h5 + .) into frozen, inference-ready TensorFlow protobuf (.pb) files. It freezes variables to constants, prunes unused nodes, and optionally exports checkpoint/metagraph files.

Use cases

• convert keras h5 model to tensorflow pb file
• freeze keras model for inference
• export keras model as tensorflow protobuf
• deploy keras model in tensorflow without keras dependency
• rename output tensors of a keras model
• convert keras model weights and architecture to tf graph

When to choose

• you have a trained Keras (TF 1.x era) model and need a standalone frozen TensorFlow graph for inference
• you want to strip Keras dependencies from a deployed model
• you need node pruning and variable freezing in a single .pb file

When to avoid

• you are using TensorFlow 2.x with Keras and can use native SavedModel export instead
• you need continued training rather than inference-only export
• you need actively maintained tooling for modern TF/Keras versions

Facets

cli-tool · maturity maintenance

machine-learning deep-learning serialization developer-tools machine-learning deep-learning developer-tools python cli cross-platform keras tensorflow model-conversion model-freezing inference protobuf

Member repositories

For agents

markdown · JSON · MCP: product_card(name="amir-abdi/keras_to_tensorflow")