caiwenpu

awesome-free-chatgpt. 🆓免费的 ChatGPT 镜像网站列表，持续更新。List of free ChatGPT mirror sites, continuously updated.

sam-hq. Segment Anything in High Quality [NeurIPS 2023]

Awesome-Segmentation-With-Transformer. [T-PAMI-2024] Transformer-Based Visual Segmentation: A Survey

mmsegmentation. OpenMMLab Semantic Segmentation Toolbox and Benchmark.

Transformer_for_medical_image_analysis. A collection of papers about Transformer in the field of medical image analysis.

LibMTL. A PyTorch Library for Multi-Task Learning

nn_vis. A project for processing neural networks and rendering to gain insights on the architecture and parameters of a model through a decluttered representation.

Next-ViT. Python

BCDNet. Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies

DeepClustering. Methods and Implements of Deep Clustering

Awesome-Federated-Machine-Learning. Everything about federated learning, including research papers, books, codes, tutorials, videos and beyond

Nonuniform-to-Uniform-Quantization. Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation. In CVPR 2022.

Efficient-AI-Backbones. Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

noah-research. Noah Research

vpt. ❄️🔥 Visual Prompt Tuning [ECCV 2022] https://arxiv.org/abs/2203.12119

ResNeSt. ResNeSt: Split-Attention Networks

vit-explain. Explainability for Vision Transformers

Awesome-Transformer-Attention. An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

openfold. Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

ConvNeXt. Code release for ConvNeXt model

ecco. Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, BERT, RoBERTA, T5, and T0).

TensorRT. PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

pytea. PyTea: PyTorch Tensor shape error analyzer

Arch-Net. Arch-Net: Model Distillation for Architecture Agnostic Model Deployment

Transformer-in-Vision. Recent Transformer-based CV and related works.

External-Attention-pytorch. 🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

Non-Local-Sparse-Attention. PyTorch code for our paper "Image Super-Resolution with Non-Local Sparse Attention" (CVPR2021).

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

pytorch-distributed. A quickstart and benchmark for pytorch distributed training.

tutorials. PyTorch tutorials.

pytorch-meta. A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch

multi-task-learning. Code for the ICML 2021 paper "Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation", Haoxiang Wang, Han Zhao, Bo Li.

fastNLP. fastNLP: A Modularized and Extensible NLP Framework. Currently still in incubation.

TR-BERT. Source code for NAACL 2021 paper "TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference"

CLUE. 中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard

EWGS. An official implementation of "Network Quantization with Element-wise Gradient Scaling" (CVPR 2021) in PyTorch.

actnn. ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training

diffq. DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight or group of weights, in order to achieve a given trade-off between model size and accuracy.

pytorch-gpu-benchmark. Using the famous cnn model in Pytorch, we run benchmarks on various gpu.

FAT_Quantization. Pytorch implementation for FAT: learning low-bitwidth parametric representation via frequency-aware transformation

Nystromformer. Python

transformer-xl. Python

fast-weight-transformers. Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.

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

Informer2020. The GitHub repository for the paper "Informer" accepted by AAAI 2021.

Riptide. Simple Training and Deployment of Fast End-to-End Binary Networks

one-key-hidpi. Enable macOS HiDPI and have a native setting.

I-BERT. [ICML'21 Oral] I-BERT: Integer-only BERT Quantization

RepVGG. RepVGG: Making VGG-style ConvNets Great Again

long-range-arena. Long Range Arena for Benchmarking Efficient Transformers

fastformers. FastFormers - highly efficient transformer models for NLU

awesome-fast-attention. list of efficient attention modules

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

Torch-Pruning. [CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.

EasyQuant. EasyQuant(EQ) is an efficient and simple post-training quantization method via effectively optimizing the scales of weights and activations.

RobustQuantization. source code of the paper: Robust Quantization: One Model to Rule Them All

pytorch_geometric. Graph Neural Network Library for PyTorch

pytorch-optimizer. torch-optimizer -- collection of optimizers for Pytorch

awesome-papers-fewshot. Collection for Few-shot Learning

PWLQ. Code for our paper at ECCV 2020: Post-Training Piecewise Linear Quantization for Deep Neural Networks

GNNPapers. Must-read papers on graph neural networks (GNN)

RBNN. Pytorch implementation of our paper accepted by NeurIPS 2020 -- Rotated Binary Neural Network

ai-research. Python

bnas. Official PyTorch Implementation of "Learning Architectures for Binary Networks" (ECCV2020)

EdMIPS. PyTorch implementation of EdMIPS: https://arxiv.org/pdf/2004.05795.pdf

ReActNet. ReActNet: Towards Precise Binary NeuralNetwork with Generalized Activation Functions. In ECCV 2020.

nncf. Neural Network Compression Framework for enhanced OpenVINO™ inference

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

channel-distillation. PyTorch implementation for Channel Distillation

Gradient-Centralization. A New Optimization Technique for Deep Neural Networks

CalibTIP. Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming

AdderNet. Code for paper " AdderNet: Do We Really Need Multiplications in Deep Learning?"

DeepInversion. Official PyTorch implementation of Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion (CVPR 2020)

SNIP-it. This repository is the official implementation of the paper Pruning via Iterative Ranking of Sensitivity Statistics and implements novel pruning / compression algorithms for deep learning / neural networks. Amongst others it implements structured pruning before training, its actual parameter shrinking and unstructured before/during training.

CIFAR-ZOO. PyTorch implementation of CNNs for CIFAR benchmark

NAT. Implementation for NAT.

dmcp. Python

pytorch-blockswap. Code for BlockSwap (ICLR 2020).

pruning-from-scratch. Python

Any-Precision-DNNs. Any-Precision Deep Neural Networks (AAAI 2021)

IR-Net. [CVPR 2020] This project is the PyTorch implementation of our accepted CVPR 2020 paper : forward and backward information retention for accurate binary neural networks.

pycls. Codebase for Image Classification Research, written in PyTorch.

CAT. Implementation of CAT paper

SinglePathOneShot. Python

DFS. Python

dnn-gating. Conditional channel- and precision-pruning on neural networks

pdarts. Codes for our paper "Progressive Differentiable Architecture Search:Bridging the Depth Gap between Search and Evaluation"

darts. Differentiable architecture search for convolutional and recurrent networks

albert. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

invertible-resnet. Official Code for Invertible Residual Networks

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

BiDet. This is the official pytorch implementation for paper: BiDet: An Efficient Binarized Object Detector, which is accepted by CVPR2020.

GraSP. Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH

MAML-Pytorch. Elegant PyTorch implementation of paper Model-Agnostic Meta-Learning (MAML)

filter-grafting. Filter Grafting for Deep Neural Networks(CVPR 2020)

BayesBiNN. Code for the paper "Training Binary Neural Networks with Bayesian Learning Rule

soft-sharing. Implementation of soft parameter sharing for neural networks

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

geti. Build computer vision models in a fraction of the time and with less data.

The-compression-of-Transformer. Python

DeepHoyer. DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures

CNN-FCF-CVPR-2019. Python

Cross-Distillation. Codes for paper "Few Shot Network Compression via Cross Distillation", AAAI 2020.

uda. Unsupervised Data Augmentation (UDA)

ONE_NeurIPS2018. Python

ZeroShotKnowledgeTransfer. Accompanying code for the paper "Zero-shot Knowledge Transfer via Adversarial Belief Matching"

nn-quantization-pytorch. Jupyter Notebook

FilterSketch. Pytorch implementation of our paper accepted by IEEE TNNLS, 2021 -- Filter Sketch for Network Pruning

backpack. This repository is no longer maintained. Check

TNT. Jupyter Notebook

compression. Python

scale-adjusted-training. PyTorch implementation of Towards Efficient Training for Neural Network Quantization

Data-Free-Adversarial-Distillation. Code and pretrained models for paper: Data-Free Adversarial Distillation

einconv. Python

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

APoT_Quantization. PyTorch implementation for the APoT quantization (ICLR 2020)

Tutorial_BayesianCompressionForDL. A tutorial on "Bayesian Compression for Deep Learning" published at NIPS (2017).

code.

NeuralRejuvenation-CVPR19. Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilization at CVPR'19

Towards-Effective-Low-bitwidth-Convolutional-Neural-Networks. This repository implements the paper "Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations"

imgclsmob. Sandbox for training deep learning networks

DSQ. pytorch implementation of "Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks"

brevitas. Brevitas: neural network quantization in PyTorch

dnw. Discovering Neural Wirings (https://arxiv.org/abs/1906.00586)

are-16-heads-really-better-than-1. Code for the paper "Are Sixteen Heads Really Better than One?"

learning_filter_basis. Pytorch implemenation of "Learning Filter Basis for Convolutional Neural Network Compression" ICCV2019

LMA. AAAI'2020: Light Multi-segment Activation for model compression

SiamMask. [CVPR19/TPAMI23] SiamMask: A Framework for Fast Online Object Tracking and Segmentation

quantized.pytorch. Python

training-mixed-precision-quantized-networks. This repository containts the pytorch scripts to train mixed-precision networks for microcontroller deployment, based on the memory contraints of the target device.

DB. A PyTorch implementation of "Real-time Scene Text Detection with Differentiable Binarization".

Centripetal-SGD. Codes of Centripetal SGD

sparse_learning. Sparse learning library and sparse momentum resources.

Soft-VQ-VAE. Jupyter Notebook

model_based_energy_constrained_compression. Code for paper "Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking"

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

GSM-SGD. Global Sparse Momentum SGD for pruning very deep neural networks

Awesome-Knowledge-Distillation. Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。

PC-DARTS. PC-DARTS:Partial Channel Connections for Memory-Efficient Differentiable Architecture Search

pytorch-prunes. Code for https://arxiv.org/abs/1810.04622

AutoBNN. Python

RepDistiller. [ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods

ORN. Oriented Response Networks, in CVPR 2017

Pytorch-HarDNet. 35% faster than ResNet: Harmonic DenseNet, A low memory traffic network

condensa. Programmable Neural Network Compression

alibabacloud-quantization-networks. alibabacloud-quantization-networks

CCNet. CCNet: Criss-Cross Attention for Semantic Segmentation (TPAMI 2020 & ICCV 2019).

CutMix-PyTorch. Official Pytorch implementation of CutMix regularizer

EMANet. The code for Expectation-Maximization Attention Networks for Semantic Segmentation (ICCV'2019 Oral)

COP. Code for IJCAI2019 paper

GroupNorm-reproduce. An official collection of code in different frameworks that reproduces experiments in "Group Normalization"

AdaBound. An optimizer that trains as fast as Adam and as good as SGD.

pytorch-scalable-neural-networks. A pytorch implement of scalable neural netowrks.

WeightStandardization. Standardizing weights to accelerate micro-batch training

IMTA. Python

MEAL. Official Implementation of MEAL: Multi-Model Ensemble via Adversarial Learning on AAAI 2019

pmf. Proximal Mean-field for Neural Network Quantization

DSConv. Python

PyTorch-GAN. PyTorch implementations of Generative Adversarial Networks.

Robustness-Aware-Pruning-ADMM. Code release for "Adversarial Robustness vs Model Compression, or Both?"

bit-rnn. Quantize weights and activations in Recurrent Neural Networks.

rethinking-bnn-optimization. Implementation for the paper "Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization"

VIBNet. Compressing Neural Networks using the Variational Information Bottleneck

Normalized-Quantized-LSTM. Implementation of NeurIPS 2019 paper "Normalization Helps Training of Quantized LSTM"

Knowledge-Distillation-Zoo. Pytorch implementation of various Knowledge Distillation (KD) methods.

MainSubsidaryBNN. Python

L2T-ww. Learning What and Where to Transfer (ICML 2019)

EagleEye. (ECCV'2020 Oral)EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning

slimmable_networks. Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019

mobileNet-v2_cifar10. a pytorch implement of mobileNet v2 on cifar10

CondenseNet. CondenseNet: Light weighted CNN for mobile devices

Ternarized_Neural_Network. Optimizing Deep Convolutional Neural Network with Ternarized Weights and High Accuracy

MetaPruning. MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning. In ICCV 2019.

kill-the-bits. Code for: "And the bit goes down: Revisiting the quantization of neural networks"

gate-decorator-pruning. Code for the NuerIPS'19 paper "Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks"

overhaul-distillation. Official PyTorch implementation of "A Comprehensive Overhaul of Feature Distillation" (ICCV 2019)

Efficient-Computing. Efficient computing methods developed by Huawei Noah's Ark Lab

LegoNet. A Pytorch implementation of "LegoNet: Efficient Convolutional Neural Networks with Lego Filters" (ICML 2019).

lit-code. Code for LIT, ICML 2019

haq. [CVPR 2019, Oral] HAQ: Hardware-Aware Automated Quantization with Mixed Precision

HBONet. [ICCV 2019] Harmonious Bottleneck on Two Orthogonal Dimensions, surpassing MobileNetV2

KD_methods_with_TF. Knowledge distillation methods implemented with Tensorflow (now there are 11 (+1) methods, and will be added more.)

QPyTorch. Low Precision Arithmetic Simulation in PyTorch

EigenDamage-Pytorch. Code for "EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis" https://arxiv.org/abs/1905.05934

OctaveConv_pytorch. Pytorch implementation of newly added convolution

LD-Net. Language Model Pruning for Sequence Labeling

BENN-PyTorch. Codes for Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?

pytorch-moonshine. Cheap distillation for convolutional neural networks.

mmdetection. OpenMMLab Detection Toolbox and Benchmark

deficient-efficient. Successfully training approximations to full-rank matrices for efficiency in deep learning.

deep_learning_object_detection. A paper list of object detection using deep learning.

Distilling-Object-Detectors. Implementation of CVPR 2019 paper: Distilling Object Detectors with Fine-grained Feature Imitation

GrOWL. Learning to share: simultaneous parameter tying and sparsification in deep learning

selective-convolution. Code for the paper "Training CNNs with Selective Allocation of Channels" (ICML 2019)

Decompose-CNN. CP and Tucker decomposition for Convolutional Neural Networks

g2-lstm. Codes for "Towards Binary-Valued Gates for Robust LSTM Training".

CU-Net. Code for "Quantized Densely Connected U-Nets for Efficient Landmark Localization" (ECCV 2018) and "CU-Net: Coupled U-Nets" (BMVC 2018 oral)

Efficient-Deep-Learning. Collection of recent methods on (deep) neural network compression and acceleration.

Awesome-Pruning. A curated list of neural network pruning resources.

EmbeddingDistillation. Learning Metrics from Teachers: Compact Networks for Image Embedding (CVPR19)