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.
☆324Updated this week
Related projects ⓘ
Alternatives and complementary repositories for model_optimization
- A set of simple tools for splitting, merging, OP deletion, size compression, rewriting attributes and constants, OP generation, change op…☆275Updated 6 months ago
- ☆121Updated last year
- A parser, editor and profiler tool for ONNX models.☆397Updated last month
- Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.☆413Updated last year
- This script converts the ONNX/OpenVINO IR model to Tensorflow's saved_model, tflite, h5, tfjs, tftrt(TensorRT), CoreML, EdgeTPU, ONNX and…☆339Updated 2 years ago
- ☆298Updated 11 months ago
- PyTorch implementation of Data Free Quantization Through Weight Equalization and Bias Correction.☆258Updated last year
- Neural Network Compression Framework for enhanced OpenVINO™ inference☆939Updated this week
- Supporting PyTorch models with the Google AI Edge TFLite runtime.☆360Updated this week
- Inference of quantization aware trained networks using TensorRT☆78Updated last year
- A code generator from ONNX to PyTorch code☆132Updated last year
- Pytorch implementation of BRECQ, ICLR 2021☆250Updated 3 years ago
- TFLite model analyzer & memory optimizer☆120Updated 9 months ago
- [NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep L…☆476Updated 7 months ago
- ☆214Updated 2 years ago
- ☆192Updated 3 years ago
- ONNX Script enables developers to naturally author ONNX functions and models using a subset of Python.☆280Updated this week
- Binarize convolutional neural networks using pytorch☆134Updated 2 years 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…☆699Updated last week
- OTOv1-v3, NeurIPS, ICLR, TMLR, DNN Training, Compression, Structured Pruning, Erasing Operators, CNN, Diffusion, LLM☆292Updated last month
- PyTorch implementation for the APoT quantization (ICLR 2020)☆267Updated 2 years ago
- Quantization of Convolutional Neural networks.☆239Updated 3 months ago
- Reference implementations of popular Binarized Neural Networks☆104Updated last week
- [ICLR 2022 Oral] F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization☆95Updated 2 years ago
- FakeQuantize with Learned Step Size(LSQ+) as Observer in PyTorch☆32Updated 2 years ago
- μNAS is a neural architecture search (NAS) system that designs small-yet-powerful microcontroller-compatible neural networks.☆76Updated 3 years ago
- Count number of parameters / MACs / FLOPS for ONNX models.☆88Updated 2 weeks ago
- Transform ONNX model to PyTorch representation☆315Updated last month
- PyTorch Quantization Aware Training Example☆123Updated 5 months ago
- On-the-fly Structured Pruning for PyTorch models. This library implements several attributions metrics and structured pruning utils for n…☆160Updated 4 years ago