AlexanderLutsenko/nobuco
Pytorch to Keras/Tensorflow/TFLite conversion made intuitive
This tool helps machine learning engineers and researchers convert neural network models built in PyTorch to Keras, TensorFlow, or TFLite formats. You input a PyTorch model and its sample data, and it outputs a functionally equivalent model in the target framework. This is ideal for developers who need to deploy models to environments that prefer TensorFlow or TFLite, or integrate PyTorch models into existing Keras workflows.
343 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to translate an existing PyTorch model into Keras or TensorFlow format for deployment or integration, and you require fine-grained control over the conversion process to ensure accuracy.
Not ideal if you are looking for a fully automated, black-box conversion tool that requires no intervention for custom operations or framework differences.
Stars
343
Forks
21
Language
Python
License
MIT
Category
Last pushed
Mar 10, 2025
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AlexanderLutsenko/nobuco"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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