PINTO0309/simple-onnx-processing-tools
A set of simple tools for splitting, merging, OP deletion, size compression, rewriting attributes and constants, OP generation, change opset, change to the specified input order, addition of OP, RGB to BGR conversion, change batch size, batch rename of OP, and JSON convertion for ONNX models.
This tool helps machine learning engineers and AI model deployers modify ONNX (Open Neural Network Exchange) models for various deployment scenarios. It takes existing ONNX models as input and allows for operations like splitting, merging, compressing, or renaming parts of the model. The output is a customized ONNX model, optimized for specific hardware or software environments.
304 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to fine-tune, optimize, or adapt your ONNX deep learning models for deployment, especially when dealing with size constraints, compatibility issues, or specific operational requirements.
Not ideal if you are looking for a tool to train, evaluate, or convert models from other frameworks like TensorFlow or PyTorch, as this focuses solely on modifying existing ONNX models.
Stars
304
Forks
25
Language
Python
License
MIT
Category
Last pushed
Apr 22, 2024
Commits (30d)
0
Dependencies
25
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/PINTO0309/simple-onnx-processing-tools"
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