pip install onnxruntime==1.9.0
ONNX Runtime is a runtime accelerator for Machine Learning models
SourceAmong top 1000 packages on PyPI.
Over 5.7M downloads in the last 90 days.
onnxruntime
Based on how often these packages appear together in public
requirements.txt
files on GitHub.
pytorch-optimizer |
|
Ranger - a synergistic optimizer using RAdam (Rectified Adam) and LookAhead in one codebase |
|
Convert ONNX (Open Neural Network Exchange)models into Apple CoreML format. |
|
Simplify your ONNX model |
|
(Unofficial) PyTorch Image Models |
|
Fast image augmentation library and easy to use wrapper around other libraries |
|
A flexible configuration library |
|
Python bindings to Atari games |
|
TensorFlow Addons. |
|
PyTorch Lightning is the lightweight PyTorch wrapper for ML researchers. Scale your models. Write less boilerplate. |
|
TensorFlow Estimator. |
|
Community Tools for Core ML |
|
TensorFlow-Slim: A lightweight library for defining, training and evaluating complex models in TensorFlow |
|
A ctypes-based wrapper for GLFW3. |
|
TensorBoard lets you watch Tensors Flow |
|
Gin-Config: A lightweight configuration library for Python |
|
Dopamine: A framework for flexible Reinforcement Learning research |
|
Flax: A neural network library for JAX designed for flexibility |
|
Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research. |
onnxruntime
Proportion of downloaded versions in the last 3 months (only versions over 1%).
1.5.2 |
34.51% |
1.4.0 |
25.95% |
1.3.0 |
12.99% |
1.8.0 |
7.07% |
1.8.1 |
4.95% |
1.9.0 |
4.79% |
1.7.0 |
3.09% |
1.6.0 |
1.99% |
1.5.1 |
1.55% |
1.1.0 |
1.16% |