tensorflow / model-optimization
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
☆1,529Updated last month
Alternatives and similar repositories for model-optimization:
Users that are interested in model-optimization are comparing it to the libraries listed below
- TensorFlow/TensorRT integration☆739Updated last year
- Tensorflow Backend for ONNX☆1,300Updated last year
- Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distille…☆4,384Updated last year
- Useful extra functionality for TensorFlow 2.x maintained by SIG-addons☆1,696Updated last week
- Quantized Neural Network PACKage - mobile-optimized implementation of quantized neural network operators☆1,537Updated 5 years ago
- Convert tf.keras/Keras models to ONNX☆379Updated 3 years ago
- Model analysis tools for TensorFlow☆1,263Updated last month
- A profiling and performance analysis tool for TensorFlow☆369Updated this week
- Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX☆2,393Updated last month
- Guide for building custom op for TensorFlow☆378Updated 2 years ago
- A performant and modular runtime for TensorFlow☆758Updated last month
- Fast & Simple Resource-Constrained Learning of Deep Network Structure☆1,028Updated 2 months ago
- Pruning and other network surgery for trained Keras models.☆408Updated last year
- Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019)☆1,515Updated 4 years ago
- Save, Load Frozen Graph and Run Inference From Frozen Graph in TensorFlow 1.x and 2.x☆302Updated 4 years ago
- TensorFlow Estimator☆301Updated last year
- PyTorch to Keras model convertor☆860Updated 2 years ago
- QKeras: a quantization deep learning library for Tensorflow Keras☆560Updated last month
- TensorFlow Code for paper "Efficient Neural Architecture Search via Parameter Sharing"☆1,579Updated 5 years ago
- PyTorch Implementation of [1611.06440] Pruning Convolutional Neural Networks for Resource Efficient Inference☆878Updated 5 years ago
- AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.☆2,261Updated this week
- An Open-Source Library for Training Binarized Neural Networks☆714Updated 7 months ago
- Collection of recent methods on (deep) neural network compression and acceleration.☆943Updated 4 months ago
- Library for faster pinned CPU <-> GPU transfer in Pytorch☆685Updated 5 years ago
- ☆371Updated 2 months ago
- ONNXMLTools enables conversion of models to ONNX☆1,064Updated 2 months ago
- A Hyperparameter Tuning Library for Keras☆2,878Updated 4 months ago
- [ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware☆1,434Updated 7 months ago
- Low-precision matrix multiplication☆1,797Updated last year
- Code for: "And the bit goes down: Revisiting the quantization of neural networks"☆633Updated 4 years ago