sony / model_optimization
Model Compression Toolkit (MCT) is an open source project for neural network model optimization under efficient, constrained hardware. This project provides researchers, developers, and engineers advanced quantization and compression tools for deploying state-of-the-art neural networks.
☆379Updated last week
Alternatives and similar repositories for model_optimization:
Users that are interested in model_optimization are comparing it to the libraries listed below
- ☆316Updated last year
- A set of simple tools for splitting, merging, OP deletion, size compression, rewriting attributes and constants, OP generation, change op…☆291Updated 11 months ago
- TFLite model analyzer & memory optimizer☆124Updated last year
- Count number of parameters / MACs / FLOPS for ONNX models.☆89Updated 5 months ago
- Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massiv…☆772Updated last week
- A parser, editor and profiler tool for ONNX models.☆422Updated 2 months ago
- ONNX Script enables developers to naturally author ONNX functions and models using a subset of Python.☆329Updated this week
- [NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep L…☆544Updated last year
- Conversion of PyTorch Models into TFLite☆371Updated 2 years ago
- Supporting PyTorch models with the Google AI Edge TFLite runtime.☆512Updated this week
- QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX☆143Updated last week
- Neural Network Compression Framework for enhanced OpenVINO™ inference☆991Updated this week
- PyTorch Quantization Aware Training Example☆132Updated 10 months ago
- Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.☆429Updated last year
- Inference of quantization aware trained networks using TensorRT☆80Updated 2 years ago
- Convert tflite to JSON and make it editable in the IDE. It also converts the edited JSON back to tflite binary.☆27Updated 2 years ago
- Highly optimized inference engine for Binarized Neural Networks☆249Updated 3 weeks ago
- Binarize convolutional neural networks using pytorch☆143Updated 2 years ago
- Model compression for ONNX☆88Updated 4 months ago
- A code generator from ONNX to PyTorch code☆135Updated 2 years ago
- List of papers related to neural network quantization in recent AI conferences and journals.☆575Updated last week
- ☆141Updated 2 years ago
- PyTorch implementation for the APoT quantization (ICLR 2020)☆271Updated 3 months ago
- Implementation of YOLOv9 QAT optimized for deployment on TensorRT platforms.☆105Updated last month
- Reference implementations of popular Binarized Neural Networks☆107Updated this week
- ☆130Updated 3 weeks ago
- PyTorch implementation of Data Free Quantization Through Weight Equalization and Bias Correction.☆262Updated last year
- Convert ONNX models to PyTorch.☆660Updated 7 months ago
- MLPerf™ Tiny is an ML benchmark suite for extremely low-power systems such as microcontrollers☆392Updated this week
- This script converts the ONNX/OpenVINO IR model to Tensorflow's saved_model, tflite, h5, tfjs, tftrt(TensorRT), CoreML, EdgeTPU, ONNX and…☆340Updated 2 years ago