1652 Open source projects that are alternatives of or similar to Nncf

FrostNet: Towards Quantization-Aware Network Architecture Search

A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.

Training & Quantization of embedded friendly Deep Learning / Machine Learning / Computer Vision models

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

Pruning and quantization for SSD. Model compression.

An open source framework for deep learning on satellite and aerial imagery.

Collections of model quantization algorithms

35% faster than ResNet: Harmonic DenseNet, A low memory traffic network

This repository contains the source code of our work on designing efficient CNNs for computer vision

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection, NeurIPS2020

A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights

🔥TorchSat 🌏 is an open-source deep learning framework for satellite imagery analysis based on PyTorch.

A list of popular deep learning models related to classification, segmentation and detection problems

[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator

An extension of Open3D to address 3D Machine Learning tasks

Reproduce simple cv project including attention module, classification, object detection, segmentation, keypoint detection, tracking 😄 etc.

PaddleSlim is an open-source library for deep model compression and architecture search.

reference pytorch code for named entity tagging

🚖 Object Detection (YOLOv1) implentation in tensorflow, with training, testing and video features.

The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.

The ROS Package of Mask R-CNN for Object Detection and Segmentation

Repository to track the progress in model compression and acceleration

Tensorflow implementation : U-net and FCN with global convolution

ResNet with Shift, Depthwise, or Convolutional Operations for CIFAR-100, CIFAR-10 on PyTorch

[NeurIPS 2020] Code release for paper "Deep Multimodal Fusion by Channel Exchanging" (In PyTorch)

Collection of computer vision models, ready to be included in a JVM project

Easy-to-use UI for automatically sparsifying neural networks and creating sparsification recipes for better inference performance and a smaller footprint

Online feature-extraction and classification algorithm that learns representations of input patterns.

A curated list of resources focused on Machine Learning in Geospatial Data Science.

Deep Learning sample programs using PyTorch in C++

Implement some models of RGB/RGBD semantic segmentation in PyTorch, easy to run. Such as FCN, RefineNet, PSPNet, RDFNet, 3DGNN, PointNet, DeepLab V3, DeepLab V3 plus, DenseASPP, FastFCN

Be Driven 🚘

High-level batteries-included neural network training library for Pytorch

YOLO ModelCompression MultidatasetTraining

Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller

InstantDL: An easy and convenient deep learning pipeline for image segmentation and classification

Embedded and mobile deep learning research resources

Gluon CV Toolkit

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

Object Tracking in Tensorflow ( Localization Detection Classification ) developed to partecipate to ImageNET VID competition

OpenMMLab Model Compression Toolbox and Benchmark.

Awesome machine learning model compression research papers, tools, and learning material.

Collaborate & label any type of data, images, text, or documents, in an easy web interface or desktop app.

deep learning for image processing including classification and object-detection etc.

Sandbox for training deep learning networks

A label tool aim to reduce semantic segmentation label time, rectangle and polygon annotation is supported

Hierarchical perception library in Python for pose estimation, object detection, instance segmentation, keypoint estimation, face recognition, etc.

ROS package for the Perception (Sensor Processing, Detection, Tracking and Evaluation) of the KITTI Vision Benchmark Suite

A curated list of awesome edge machine learning resources, including research papers, inference engines, challenges, books, meetups and others.

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape

Pytorch implementation of our CVPR 2020 (Oral) -- HRank: Filter Pruning using High-Rank Feature Map

Direct Graphical Models (DGM) C++ library, a cross-platform Conditional Random Fields library, which is optimized for parallel computing and includes modules for feature extraction, classification and visualization.

A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.

PyTorch Model Compression

All about acceleration and compression of Deep Neural Networks

🛠️ Tools for Transformers compression using PyTorch Lightning ⚡

Deep Learning for Automatic Pneumonia Detection, RSNA challenge

[CVPR'20] ZeroQ: A Novel Zero Shot Quantization Framework

PyTorch-based modular, configuration-driven framework for knowledge distillation. 🏆18 methods including SOTA are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy.

LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks