amir-abdi/keras_to_tensorflow
General code to convert a trained keras model into an inference tensorflow model
This tool helps machine learning engineers and researchers convert trained Keras deep learning models into a format optimized for deployment and inference using TensorFlow. It takes your Keras model, saved as an HDF5 file (and optionally a JSON file for architecture), and outputs a frozen TensorFlow model in a binary protobuf (.pb) file. This allows for efficient use of your trained model in production environments.
1,652 stars. No commits in the last 6 months.
Use this if you need to take a deep learning model trained in Keras and prepare it for efficient, production-ready inference within a TensorFlow ecosystem.
Not ideal if you plan to continue training your model after conversion, as the primary output is optimized for inference rather than further training.
Stars
1,652
Forks
529
Language
Python
License
MIT
Category
Last pushed
Nov 23, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/amir-abdi/keras_to_tensorflow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
microsoft/onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
onnx/onnx
Open standard for machine learning interoperability
PINTO0309/onnx2tf
Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The...
NVIDIA/TensorRT
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This...
onnx/onnxmltools
ONNXMLTools enables conversion of models to ONNX