====
论文
====

======
Python
======

=========
Tensorflow
=========

=======
PyTorch
=======

=====
Keras
=====

====
专题
====

====
链接
====

====
视频
====

=======
药物设计
=======

=======
材料科学
=======

============
经济学与金融学
============

GitHub资源
PyTorch code Tensorflow code Bioinformatics 论文代码 GNN code 教程  

==========
Pytorch代码
==========

经典网络pytorch代码

语义分割

CSAILVision/semantic-segmentation-pytorch：
Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

/pytorch-segmentation：
This repository implements general network for semantic segmentation.
You can train various networks like DeepLabV3+, PSPNet, UNet, etc., just by writing the config file.

LeeJunHyun/Image_Segmentation：
pytorch Implementation of U-Net, R2U-Net, Attention U-Net, Attention R2U-Net
qubvel/segmentation_models.pytorch：
Segmentation models with pretrained backbones. PyTorch.

meetps/pytorch-semseg：
Semantic Segmentation Architectures Implemented in PyTorch

Tramac/awesome-semantic-segmentation-pytorch：
Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNe…
支持下列网络：
FCN，ENet，PSPNet，ICNet，DeepLabv3，DeepLabv3+，DenseASPP，EncNet，BiSeNet，PSANet，DANet，OCNet，CGNet，ESPNetv2，CCNet，DUNet(DUpsampling)，FastFCN(JPU)，LEDNet，Fast-SCNN，LightSeg，DFANet

zijundeng/pytorch-semantic-segmentation：
PyTorch for Semantic Segmentation
SegFormer （2021.6）
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
This repository contains the official Pytorch implementation of training & evaluation code and the pretrained models for SegFormer.
 
 
 
 

目标检测

jwyang/faster-rcnn.pytorch
A faster pytorch implementation of faster r-cnn

chenyuntc/simple-faster-rcnn-pytorch
A simplified implemention of Faster R-CNN that replicate performance from origin paper

matterport/Mask_RCNN
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
 
 
 
 
 
 
 

实例分割

/Pose2Seg
Official code for the paper "Pose2Seg: Detection Free Human Instance Segmentation"[ProjectPage][arXiv] @ CVPR2019.
matterport/Mask_RCNN
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
 
 
 
 
 
 
 
 

分类

bearpaw/pytorch-classification：
Classification with PyTorch.

hysts/pytorch_image_classification
Following models are implemented using PyTorch. ResNet， ResNet-preact，WRN， DenseNet， PyramidNet，ResNeXt， shake-shake ，LARS ，Cutout ，Random Erasing ，SENet，Mixup，Dual-Cutout ，RICAP ，CutMix.
 
 
 
 
 

自然语言处理

duoergun0729/nlp
兜哥出品 <一本开源的NLP入门书籍>
sebastianruder/NLP-progress
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-o…

NLP-LOVE/ML-NLP
此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。
graykode/nlp-tutorial
Natural Language Processing Tutorial for Deep Learning Researchers
keon/awesome-nlp
A curated list of resources dedicated to Natural Language Processing (NLP)
codertimo/BERT-pytorch
Google AI 2018 BERT pytorch implementation
jessevig/bertviz
Tool for visualizing attention in the Transformer model (BERT, GPT-2, Albert, XLNet, RoBERTa, CTRL, etc.)
UKPLab/sentence-transformers
Multilingual Sentence & Image Embeddings with BERT
Jiakui/awesome-bert
bert nlp papers, applications and github resources, including the newst xlnet ， BERT、XLNet 相关论文和 github 项目
 
 
 

===========
自动机器学习
===========

/auto-sklearn

auto-sklearn详解

/autokeras
AutoKeras: An AutoML system based on Keras. It is developed by DATA Lab at Texas A&M University. The goal of AutoKeras is to make machine learning accessible to everyone.

/auto_ml

/Auto-PyTorch
While early AutoML frameworks focused on optimizing traditional ML pipelines and their hyperparameters, another trend in AutoML is to focus on neural architecture search. To bring the best of these two worlds together, we developed Auto-PyTorch, which jointly and robustly optimizes the network architecture and the training hyperparameters to enable fully automated deep learning (AutoDL).
Auto-PyTorch is mainly developed to support tabular data (classification, regression), but can also be applied to image data (classification). The newest features in Auto-PyTorch for tabular data are described in the paper "Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL" (see below for bibtex ref).

/AutoDL-Projects
Automated Deep Learning Projects (AutoDL-Projects) is an open source, lightweight, but useful project for everyone. This project implemented several neural architecture search (NAS) and hyper-parameter optimization (HPO) algorithms. 中文介绍见README_CN.md

/tpot
TPOT stands for Tree-based Pipeline Optimization Tool. Consider TPOT your Data Science Assistant. TPOT is a Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.

Keras Tuner
KerasTuner is an easy-to-use, scalable hyperparameter optimization framework that solves the pain points of hyperparameter search. Easily configure your search space with a define-by-run syntax, then leverage one of the available search algorithms to find the best hyperparameter values for your models. KerasTuner comes with Bayesian Optimization, Hyperband, and Random Search algorithms built-in, and is also designed to be easy for researchers to extend in order to experiment with new search algorithms.

NNI
NNI (Neural Network Intelligence) 是一个轻量但强大的工具包，帮助用户自动的进行特征工程，神经网络架构搜索，超参调优以及模型压缩。
NNI 管理自动机器学习 (AutoML) 的 Experiment，调度运行由调优算法生成的 Trial 任务来找到最好的神经网络架构和/或超参，支持各种训练环境，如本机，远程服务器，OpenPAI，Kubeflow，基于 K8S 的 FrameworkController（如，AKS 等）， DLWorkspace (又称 DLTS), AML (Azure Machine Learning), AdaptDL（又称 ADL） ，和其他的云平台甚至 混合模式 。

/Awesome-AutoDL
A curated list of automated deep learning related resources. Inspired by awesome-deep-vision, awesome-adversarial-machine-learning, awesome-deep-learning-papers, and awesome-architecture-search.

AutoGluon
AutoGluon enables easy-to-use and easy-to-extend AutoML with a focus on automated stack ensembling, deep learning, and real-world applications spanning text, image, and tabular data.

Determined
Determined is an open-source deep learning training platform that makes building models fast and easy. Determined enables you to:
Train models faster using state-of-the-art distributed training, without changing your model code
Automatically find high-quality models with advanced hyperparameter tuning from the creators of Hyperband
Get more from your GPUs with smart scheduling and cut cloud GPU costs by seamlessly using preemptible instances
Track and reproduce your work with experiment tracking that works out-of-the-box, covering code versions, metrics, checkpoints, and hyperparameters
Determined integrates these features into an easy-to-use, high-performance deep learning environment — which means you can spend your time building models instead of managing infrastructure.
To use Determined, you can continue using popular DL frameworks such as TensorFlow and PyTorch; you just need to update your model code to integrate with the Determined API.

/aw_nas
Neural Architecture Search (NAS) has received extensive attention due to its capability to discover neural network architectures in an automated manner. aw_nas is a NAS framework with various NAS algorithms implemented in a modularized manner. Currently, aw_nas can be used to reproduce the results of many mainstream NAS algorithms, e.g., ENAS, DARTS, SNAS, FBNet, OFA, predictor-based NAS, etc. And we have applied NAS algorithms for various applications & scenarios with aw_nas, including NAS for classification, detection, text modeling, hardware fault tolerance, adversarial robustness, hardware inference efficiency, and so on.

 
 
 
 
 

 

典型网络

MingalievDinar/object_detection_YOLO5：
The idea of the project is to try (setup environment, inference and train) a PyTorch-based object detection model YOLO5…

shanglianlm0525/PyTorch-Networks：
Pytorch implementation of cnn network

huggingface/transformers：
Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

argusswift/YOLOv4-pytorch：
This is a pytorch repository of YOLOv4, attentive YOLOv4 and mobilenet YOLOv4 with PASCAL VOC and COCO

codertimo/BERT-pytorch：
Google AI 2018 BERT pytorch implementation

chenjun2hao/Attention_ocr.pytorch：
This repository implements the the encoder and decoder model with attention model for OCR

bentrevett/pytorch-seq2seq：
Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.

jadore801120/attention-is-all-you-need-pytorch：
A PyTorch implementation of the Transformer model in "Attention is All You Need".

eriklindernoren/PyTorch-GAN:
PyTorch implementations of Generative Adversarial Networks.

junyanz/pytorch-CycleGAN-and-pix2pix:
Image-to-Image Translation in PyTorch
milesial/Pytorch-UNet：
PyTorch implementation of the U-Net for image semantic segmentation with high quality images

ShawnBIT/UNet-family：
Paper and implementation of UNet-related model.

ellisdg/3DUnetCNN：
Pytorch 3D U-Net Convolution Neural Network (CNN) designed for medical image segmentation

cosmic-cortex/pytorch-UNet：
2D and 3D UNet implementation in PyTorch.

 

 

Attention Mechanism

heykeetae/Self-Attention-GAN:
Pytorch implementation of Self-Attention Generative Adversarial Networks (SAGAN)

szagoruyko/attention-transfer：
Improving Convolutional Networks via Attention Transfer (ICLR 2017)

heykeetae/Self-Attention-GAN：
Pytorch implementation of Self-Attention Generative Adversarial Networks (SAGAN)

heykeetae/Self-Attention-GAN:
Pytorch implementation of Self-Attention Generative Adversarial Networks (SAGAN)

Jongchan/attention-module：
Official PyTorch code for "BAM: Bottleneck Attention Module (BMVC2018)" and "CBAM: Convolutional Block Attention Module (ECCV2018)"

jadore801120/attention-is-all-you-need-pytorch：
A PyTorch implementation of the Transformer model in "Attention is All You Need".
/Attention-mechanism-implementation
/Various-Attention-mechanisms
/tf-rnn-attention

/awesome-attention-mechanism-in-cv
PyTorch实现多种计算机视觉中网络设计中用到的Attention机制，还收集了一些即插即用模块。由于能力有限精力有限，可能很多模块并没有包括进来，有任何的建议或者改进，可以提交issue或者进行PR。
datalogue/keras-attention

Implementation and visualization of a custom RNN layer with attention in Keras for translating dates.
This repository comes with a tutorial found here: https://medium.com/datalogue/attention-in-keras-1892773a4f22
/attention-mechanisms

/keras-attention-mechanism
/Tensorflow-Attention

/MNIST_AttentionMap
[TensorFlow] Attention mechanism with MNIST dataset
/keras-self-attention
/Various-Attention-mechanisms
/keras-attention-mechanism-master
/attention-mechanism-keras
laugh12321/3D-Attention-Keras
 
 
 
 
 
 
 

transformer

huggingface/transformers
Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.
 
 
 
 
 

其它

deepmind/deepmind-research：
This repository contains implementations and illustrative code to accompany DeepMind publications

luanshiyinyang/PlotNeuralNet：
包含PlotNeuralNet绘制神经网络结构图的教程源码

649453932/Chinese-Text-Classification-Pytorch：
中文文本分类，TextCNN，TextRNN，FastText，TextRCNN，BiLSTM_Attention，DPCNN，Transformer，基于pytorch，开箱即用。

weiaicunzai/pytorch-cifar100：
Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet…

rwightman/pytorch-image-models：
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Tra…

jessevig/bertviz：
Tool for visualizing attention in the Transformer model (BERT, GPT-2, Albert, XLNet, RoBERTa, CTRL, etc.)

DM3Loc：
DM3Loc is a novel Deep-learning framework with multi-head self-attention for multi-label mRNA subcellular localization prediction and analyses, which provide prediciton for six subcellular compartments, including nucleus, exosome, cytoplasm, ribosome, membrane, and endoplasmic reticulum.

RNATracker：
RNATracker is a deep learning approach to learn mRNA subcellular localization patterns and to infer its outcome. It operates on the cDNA of the longest isoformic protein-coding transcript of a gene with or without its corresponding secondary structure annnotations. The learning targets are fractions/percentage of the transcripts being localized to a fixed set of subcellular compartments of interest.

Github： /RIMs
An implementation of Recurrent Independent Mechanisms (Goyal et al. 2019) in PyTorch.

/PyTorch-VAE
A collection of Variational AutoEncoders (VAEs) implemented in pytorch with focus on reproducibility. The aim of this project is to provide a quick and simple working example for many of the cool VAE models out there. All the models are trained on the CelebA dataset for consistency and comparison. The architecture of all the models are kept as similar as possible with the same layers, except for cases where the original paper necessitates a radically different architecture (Ex. VQ VAE uses Residual layers and no Batch-Norm, unlike other models). Here are the results of each model.

/auto-sklearn
auto-sklearn is an automated machine learning toolkit and a drop-in replacement for a scikit-learn estimator. Find the documentation here

auto-sklearn
Auto-sklearn is an automated machine learning toolkit and a drop-in replacement for a scikit-learn estimator:

/autokeras
AutoKeras: An AutoML system based on Keras. It is developed by DATA Lab at Texas A&M University. The goal of AutoKeras is to make machine learning accessible to everyone.

/Auto-PyTorch
While early AutoML frameworks focused on optimizing traditional ML pipelines and their hyperparameters, another trend in AutoML is to focus on neural architecture search. To bring the best of these two worlds together, we developed Auto-PyTorch, which jointly and robustly optimizes the network architecture and the training hyperparameters to enable fully automated deep learning (AutoDL).
Auto-PyTorch is mainly developed to support tabular data (classification, regression), but can also be applied to image data (classification). The newest features in Auto-PyTorch for tabular data are described in the paper "Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL" (see below for bibtex ref).

/AutoDL-Projects
Automated Deep Learning Projects (AutoDL-Projects) is an open source, lightweight, but useful project for everyone. This project implemented several neural architecture search (NAS) and hyper-parameter optimization (HPO) algorithms. 中文介绍见README_CN.md
 
/attention-module

 

 

人工智能

人工智能（Artificial Intelligence），英文缩写为AI。它是研究、开发用于模拟、延伸和扩展人的智能的理论、方法、技术及应用系统的一门新的技术科学。 人工智能是计算机科学的一个分支，它企图了解智能的实质，并生产出一种新的能以人类智能相似的方式做出反应的智能机器，该领域的研究包括机器人、语言识别、图像识别、自然语言处理和专家系统等。人工智能从诞生以来，理论和技术日益成熟，应用领域也不断扩大，可以设想，未来人工智能带来的科技产品，将会是人类智慧的“容器”。人工智能可以对人的意识、思维的信息过程的模拟。人工智能不是人的智能，但能像人那样思考、也可能超过人的智能。

上海市浦东新区沪城环路999号