87 Open source projects that are alternatives of or similar to Efficient-Computing

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

Research code for ACL 2020 paper: "Distilling Knowledge Learned in BERT for Text Generation".

BigGAN; Knowledge Distillation; Black-Box; Fast Training; 16x compression

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

Awesome Knowledge Distillation

[ECCV 2020] Scale Adaptive Network: Learning to Learn Parameterized Classification Networks for Scalable Input Images

⛵️The official PyTorch implementation for "BERT-of-Theseus: Compressing BERT by Progressive Module Replacing" (EMNLP 2020).

[NeurIPS'2019] Shupeng Gui, Haotao Wang, Haichuan Yang, Chen Yu, Zhangyang Wang, Ji Liu, “Model Compression with Adversarial Robustness: A Unified Optimization Framework”

Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification

PyTorch Implementation of Weights Pruning

PyTorch code for our CVPR'20 paper "Collaborative Distillation for Ultra-Resolution Universal Style Transfer"

(CVPR 2021, Oral) Dynamic Slimmable Network

pytorch implementation of Structured Bayesian Pruning

The codes for recent knowledge distillation algorithms and benchmark results via TF2.0 low-level API

OpenMMLab Model Compression Toolbox and Benchmark.

An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.

Localization Distillation for Dense Object Detection (CVPR 2022)

Java interface for fastText

Reimplementing cool papers in PyTorch...

Model Compression CLI Tool for Keras.

Official PyTorch Implementation of Embedding Transfer with Label Relaxation for Improved Metric Learning, CVPR 2021

Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling

Mobile(iOS) Text-to-Image search powered by multimodal semantic representation models(e.g., OpenAI's CLIP). Accepted at NAACL 2022.

Authors official PyTorch implementation of the "DnS: Distill-and-Select for Efficient and Accurate Video Indexing and Retrieval" [IJCV 2022]

MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Frontal Face Images

An Open Source Deep Learning Inference Engine Based on FPGA

Automatic DNN compression tool with various model compression and neural architecture search techniques

Localize to Classify and Classify to Localize: Mutual Guidance in Object Detection

Knowledge Distillation using Tensorflow

Adversarial Adaptation with Distillation for BERT Unsupervised Domain Adaptation

Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.

Intel® Neural Compressor (formerly known as Intel® Low Precision Optimization Tool), targeting to provide unified APIs for network compression technologies, such as low precision quantization, sparsity, pruning, knowledge distillation, across different deep learning frameworks to pursue optimal inference performance.

Model optimizer used in Adlik.

This is the official implementation for the AAAI-2021 paper (Cross-Layer Distillation with Semantic Calibration).

Focal and Global Knowledge Distillation for Detectors (CVPR 2022)

针对pytorch模型的自动化模型结构分析和修改工具集，包含自动分析模型结构的模型压缩算法库

Infrastructures™ for Machine Learning Training/Inference in Production.

Learnable Embedding Space for Efficient Neural Architecture Compression

A pytorch pruning toolkit for structured neural network pruning and layer dependency maintaining.

Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection (ACM MM 2018)

Deep Face Model Compression

Yolov5 distillation training | Yolov5知识蒸馏训练，支持训练自己的数据

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

BitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.

Code for "Co-Evolutionary Compression for Unpaired Image Translation" (ICCV 2019) and "SCOP: Scientific Control for Reliable Neural Network Pruning" (NeurIPS 2020).

ZSKD with PyTorch

[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices

Code and resources on scalable and efficient Graph Neural Networks

yolov3 by pytorch

[ICLR'21] PyTorch code for our paper "Neural Pruning via Growing Regularization"

Programmable Neural Network Compression

An Object Detection Knowledge Distillation framework powered by pytorch, now having SSD and yolov5.

papers about model compression

pytorch realtime multi person keypoint estimation

CVPR 2021 : Zero-shot Adversarial Quantization (ZAQ)

noisy labels; missing labels; semi-supervised learning; entropy; uncertainty; robustness and generalisation.

🤖 A machine learning framework for audio, text, image, video, or .CSV files (50+ featurizers and 15+ model trainers).

A Fast Knowledge Distillation Framework for Visual Recognition

Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons (AAAI 2019)

[IEEE Access] "Head Network Distillation: Splitting Distilled Deep Neural Networks for Resource-constrained Edge Computing Systems" and [ACM MobiCom HotEdgeVideo 2019] "Distilled Split Deep Neural Networks for Edge-assisted Real-time Systems"