Skip to content

Latest commit

 

History

History
506 lines (244 loc) · 17 KB

README.md

File metadata and controls

506 lines (244 loc) · 17 KB

Open_source_vision

Please check the wiki page for the latest version. Below is a backup.

Links

Source:

Awesome deep vision: https://github.com/kjw0612/awesome-deep-vision

Awesome deep learning: https://github.com/ChristosChristofidis/awesome-deep-learning

Caffe model zoo: https://github.com/BVLC/caffe/wiki/Model-Zoo

MatConvNet pretrain: http://www.vlfeat.org/matconvnet/pretrained/

Facebook Hong Kong Deep Learning

CUHK IE Media lab: http://mmlab.ie.cuhk.edu.hk/index.html

CUHK EE Prof. Wang http://www.ee.cuhk.edu.hk/~xgwang/

Awesome RL: https://github.com/aikorea/awesome-rl

=================================================

Awesome deep vision:

PVANet: Real-time Object Detection: https://github.com/sanghoon/pva-faster-rcnn

You only look once(YOLO): https://github.com/pjreddie/darknet https://github.com/thtrieu/darkflow https://pjreddie.com/darknet/yolo/

R-FCN: Object Detection via Region-based Fully Convolutional Networks: https://github.com/daijifeng001/R-FCN

SSD: Single Shot MultiBox Detector: https://github.com/weiliu89/caffe/tree/ssd

Hierarchical Convolutional Features for Visual Tracking: https://github.com/jbhuang0604/CF2

Visual Tracking with Fully Convolutional Networks: https://github.com/scott89/FCNT

MDNet: Multi-Domain Convolutional Neural Network Tracker: https://github.com/HyeonseobNam/MDNet

Deep Networks for Image Super-Resolution with Sparse Prior: http://www.ifp.illinois.edu/~dingliu2/iccv15/

Image Colorization: https://github.com/richzhang/colorization

Context Encoders: Feature Learning by Inpainting: https://github.com/pathak22/context-encoder

Holistically-Nested Edge Detection: https://github.com/s9xie/hed

Seed, Expand, Constrain: Three Principles for Weakly-Supervised Image Segmentation: https://github.com/kolesman/SEC

Generating images pixel by pixel: https://github.com/kundan2510/pixelCNN

iGAN: Interactive Image Generation via Generative Adversarial Networks: https://github.com/junyanz/iGAN

neural-style: https://github.com/jcjohnson/neural-style

Caffe model zoo:

Berkeley-trained models

Network in Network model

Models from the BMVC-2014 paper "Return of the Devil in the Details: Delving Deep into Convolutional Nets"

Models used by the VGG team in ILSVRC-2014

Places-CNN model from MIT.

GoogLeNet GPU implementation from Princeton.

Fully Convolutional Networks for Semantic Segmentation (FCNs)

CaffeNet fine-tuned for Oxford flowers dataset

CNN Models for Salient Object Subitizing.

Deep Learning of Binary Hash Codes for Fast Image Retrieval

Places_CNDS_models on Scene Recognition

Models for Age and Gender Classification.

GoogLeNet_cars on car model classification

ParseNet: Looking wider to see better

SegNet and Bayesian SegNet

Conditional Random Fields as Recurrent Neural Networks

Holistically-Nested Edge Detection

CCNN: Constrained Convolutional Neural Networks for Weakly Supervised Segmentation

Emotion Recognition in the Wild via Convolutional Neural Networks and Mapped Binary Patterns

Facial Landmark Detection with Tweaked Convolutional Neural Networks

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

ResNets: Deep Residual Networks from MSRA at ImageNet and COCO 2015

Pascal VOC 2012 Multilabel Classification Model

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters

Mixture DCNN

CNN Object Proposal Models for Salient Object Detection

Deep Hand: How to Train a CNN on 1 Million Hand Images When Your Data Is Continuous and Weakly Labelled

Mulimodal Compact Bilinear Pooling for VQA

Pose-Aware CNN Models (PAMs) for Face Recognition

Learning Structured Sparsity in Deep Neural Networks

Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks

Inception-BN full ImageNet model

ResFace101: ResNet-101 for Face Recognition

DeepYeast

ImageNet pre-trained models with batch normalization

ResNet-101 for regressing 3D morphable face models (3DMM) from single images

Cascaded Fully Convolutional Networks for Biomedical Image Segmentation

Deep Networks for Earth Observation

Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks

Striving for Simplicity: The All Convolutional Net

MatConvNet pretrain:

Object detection Fast R-CNN

Face recognition VGG-Face

Semantic segmentation Fully-Convolutional Networks, BVLC FCN, Torr Vision Group FCN-8s

ImageNet ILSVRC classification ResNet, GoogLeNet, VGG-VD, VGG-S,M,F, Caffe reference model, AlexNet

Hong Kong Deep Learning:

Super resolution: https://github.com/alexjc/neural-enhance

NewYork Texi data: https://github.com/toddwschneider/nyc-taxi-data

FB's visualization: https://github.com/facebookresearch/visdom

AdaptiveAttention: https://github.com/jiasenlu/AdaptiveAttention

Chinese English dialog: https://github.com/candlewill/Dialog_Corpus

Google text tokenizer: https://github.com/google/sentencepiece

FB AI environment: https://github.com/facebookresearch/CommAI-env

Road Segmentation, Car detection and Street classification: https://github.com/MarvinTeichmann/MultiNet

Faiss is a library for efficient similarity search and clustering of dense vectors. https://github.com/facebookresearch/faiss

FB word representations and sentence classification. https://github.com/facebookresearch/fastText

Generative models: https://github.com/wiseodd/generative-models

Char2Wav speech synthesis: http://josesotelo.com/speechsynthesis/

Line drawing colorizer: https://github.com/pfnet/PaintsChainer

SketchToFace: https://github.com/richliao/SketchToFace

Chinese OCR: https://deeperic.wordpress.com/2017/02/18/chinese-ocr-tensorflow/ https://github.com/deeperic/SpikeFlow

Chinese RC dataset: https://github.com/ymcui/Chinese-RC-Dataset

Learning to Discover Cross-Domain Relations with GAN: https://github.com/SKTBrain/DiscoGAN

Style transfer: https://github.com/xunhuang1995/AdaIN-style

Chat bot corpus: https://github.com/gunthercox/chatterbot-corpus

High-Resolution Image Inpainting: https://github.com/leehomyc/High-Res-Neural-Inpainting

Deep Learning Book: https://github.com/PaddlePaddle/book/

RNN tutorial: https://github.com/silicon-valley-data-science/RNN-Tutorial

photo style transfer: https://github.com/luanfujun/deep-photo-styletransfer

Pytorch tutorial: https://github.com/yunjey/pytorch-tutorial/blob/master/README.md

Generative model: https://github.com/wiseodd/generative-models

Gen lyrics: https://github.com/tifoit/encore.ai

Every can be painter: https://github.com/alexjc/neural-doodle

Learn anytime anywhere: https://alcamy.org/?ref=producthunt

Audio synthesis and style transfer: https://dmitryulyanov.github.io/audio-texture-synthesis-and-style-transfer/

Cat papers: https://github.com/junyanz/CatPapers

Zebra GAN: https://github.com/junyanz/CycleGAN

Deep 3D Representations at High Resolutions: https://github.com/griegler/octnet

SearchQA: https://github.com/nyu-dl/SearchQA

Hybrid Code Networks: https://github.com/suriyadeepan/hcn

iNaturalist Competition: https://github.com/visipedia/inat_comp

AI for Google's t-rex game: https://github.com/wagenaartje/neuraldino

Visual Chatbot: https://github.com/Cloud-CV/visual-chatbot

Recurrent Weighted Average (RWA): https://github.com/indiejoseph/tf-rwa-cell

The GAN Zoo: https://github.com/hindupuravinash/the-gan-zoo

TF Seq2Seq Chatbot: https://github.com/ml-hongkong/chatbot

Facebook PartAI: https://github.com/facebookresearch/ParlAI

2D-3D-Semantics Data: https://github.com/alexsax/2D-3D-Semantics

AIXIjs is a JavaScript demo for running General Reinforcement Learning (RL): https://github.com/aslanides/aixijs

Deep Pill Finder: https://github.com/jmbanda/healthplusplus2016

AI-Assisted Isomorphic Application Engine for Embedded: https://github.com/Artificial-Engineering/lycheejs#quickstart

Snapshot Ensemble in Keras: https://github.com/titu1994/Snapshot-Ensembles

Sketch-RNN: A Generative Model for Vector Drawings: https://github.com/tensorflow/magenta/blob/master/magenta/models/sketch_rnn/README.md

Efficient Parallel Methods for Deep Reinforcement Learning: https://github.com/Alfredvc/paac

Visual Reasoning: https://github.com/facebookresearch/clevr-iep

pixel-wise annotations for fashion images: https://github.com/lemondan/HumanParsing-Dataset

sequence-to-sequence learning toolkit for Torch: https://github.com/facebookresearch/fairseq

ResNeXt: https://github.com/facebookresearch/ResNeXt

Dataset For Music Analysis: https://github.com/mdeff/fma

TensorFlow Best Practices: https://github.com/aicodes/tf-bestpractice

Unsupervised deep learning using unlabelled videos on the web: https://github.com/pathak22/unsupervised-video

Character-Level language models: https://github.com/indiejoseph/chinese-char-rnn

code2doc: https://github.com/Avmb/code-docstring-corpus

xnor enhanced neural nets: https://github.com/hpi-xnor/BMXNet/blob/master/README.md

Deep generative models, variational inference: https://github.com/blei-lab/edward

Language Modeling: https://github.com/okuchaiev/f-lm

Awesome Figures of Neural Networks: https://github.com/aonotas/neural-figures

Image augmentation: https://github.com/aleju/imgaug

Doom-based AI Research Platform for Reinforcement Learning from Raw Visual Information: https://github.com/mwydmuch/ViZDoom

AGI??: https://github.com/WalnutiQ/wAlnut

How to Train a GAN: https://github.com/soumith/ganhacks

End-to-End Learning for Negotiation Dialogues: https://github.com/facebookresearch/end-to-end-negotiator

Video Imagination from a Single Image: https://github.com/gitpub327/VideoImagination

Facebook bAbI dataset 10k: https://github.com/ml-hongkong/resources/blob/master/babi.md

stock2vec: https://github.com/ml-hongkong/stock2vec

Pytorch-Sketch-RNN: https://github.com/alexis-jacq/Pytorch-Sketch-RNN

基于多搜索引擎和深度学习技术的自动问答: https://github.com/SnakeHacker/QA-Snake

DeepLearningFlappyBird: https://github.com/yenchenlin/DeepLearningFlappyBird

Action Recognition using Visual Attention: https://github.com/kracwarlock/action-recognition-visual-attention

µniverse: RL environments for HTML5 games: https://github.com/unixpickle/muniverse

MobileID: Face Model Compression by Distilling Knowledge from Neurons: https://github.com/liuziwei7/mobile-id

Unsupervised Image to Image Translation with GAN: https://github.com/zsdonghao/Unsup-Im2Im

Dual Path Networks: https://github.com/cypw/DPNs

Essential Cheat Sheets: https://github.com/kailashahirwar/cheatsheets-ai

sentence embeddings: https://github.com/facebookresearch/InferSent

Pointer networks: https://github.com/zygmuntz/pointer-networks-experiments

Recurrent Additive Networks (RAN): https://github.com/indiejoseph/tf-ran-cell

Iterative Pruning: https://github.com/garion9013/impl-pruning-TF

Tensorflow iOS ObjectDetection: https://github.com/JieHe96/iOS_Tensorflow_ObjectDetection_Example

Deep Value Network: https://github.com/gyglim/dvn

Recurrent Neural Networks Tutorial: https://github.com/silicon-valley-data-science/RNN-Tutorial

Stock Trading: https://github.com/kh-kim/stock_market_reinforcement_learning

FeUdal Networks: https://github.com/dmakian/feudal_networks

Visual Dialog: https://github.com/batra-mlp-lab/visdial

Image classification with synthetic gradient: https://github.com/vyraun/DNI-tensorflow

Visualizations for machine learning datasets: https://github.com/pair-code/facets

Tensorflow implementation of the SRGAN: https://github.com/brade31919/SRGAN-tensorflow

Relational Networks and a VQA: https://github.com/gitlimlab/Relation-Network-Tensorflow

Relational Networks: https://github.com/kimhc6028/relational-networks

evaluating reinforcement learning algorithms: https://github.com/rll/rllab

training RL systems from John Schulman's lecture: https://github.com/williamFalcon/DeepRLHacks

Poincaré Embedding: https://github.com/TatsuyaShirakawa/poincare-embedding

Collection of generative models: https://github.com/hwalsuklee/tensorflow-generative-model-collections

five video classification methods: https://github.com/harvitronix/five-video-classification-methods

Chinese Named Entity Recognition: https://github.com/crownpku/Information-Extraction-Chinese

Face Data Augmentation: https://github.com/iacopomasi/face_specific_augm

Video Object Segmentation: https://github.com/scaelles/OSVOS-TensorFlow

OpenData in insurance: https://github.com/Samurais/insuranceqa-corpus-zh

Image augmentation: https://github.com/mdbloice/Augmentor

transformation-invariant pooling: https://github.com/dlaptev/TI-pooling

TensorFlow tutorials and best practices: https://github.com/vahidk/EffectiveTensorflow

A TensorBoard plugin for visualizing arbitrary tensors: https://github.com/chrisranderson/beholder

A Deep Learning toolkit based on iOS: https://github.com/amazingyyc/Brouhaha

pyTorch: https://github.com/marcoleewow/Find-Optimal-Space-Embedding-for-Trees

StarCraft II Learning Environment: https://github.com/deepmind/pysc2

Google's Tacotron: https://github.com/barronalex/Tacotron

Photographic Image Synthesis: https://github.com/CQFIO/PhotographicImageSynthesis

learning by association: https://github.com/haeusser/learning_by_association

neural network for the mobile platform: https://github.com/Tencent/ncnn

Game Agent Framework: https://github.com/SerpentAI/SerpentAI

Reinforcement learning environments with musculoskeletal: https://github.com/stanfordnmbl/osim-rl

Automatic Image Cropping: https://github.com/wuhuikai/TF-A2RL

any TensorFlow model in a single line: https://github.com/ajbouh/tfi

TensorFlow Agents: https://github.com/tensorflow/agents

book "Deep Learning with Python": https://github.com/fchollet/deep-learning-with-python-notebooks

Tensorflow wrapper for DataFrames on Apache Spark: https://github.com/databricks/tensorframes

Lattice methods in TensorFlow: https://github.com/tensorflow/lattice

Distributed training framework for TensorFlow: https://github.com/uber/horovod

state of the art Reinforcement Learning algorithms: https://github.com/NervanaSystems/coach

StackGAN-v2: https://github.com/hanzhanggit/StackGAN-v2

Progressive Growing of GANs for Improved Quality: https://github.com/tkarras/progressive_growing_of_gans

two-level RCN model: https://github.com/vicariousinc/science_rcn

Synthetic Gradients for PyTorch: https://github.com/koz4k/dni-pytorch

DiracNets: https://github.com/szagoruyko/diracnets/blob/master/README.md

make Ascii Art by Deep Learing: https://github.com/OsciiArt/DeepAA

CondenseNet: Light weighted CNN for mobile devices: https://github.com/ShichenLiu/CondenseNet

GAN Timeline: https://github.com/dongb5/GAN-Timeline/blob/master/README.md

Uber's genetic algorithm for RL: https://github.com/unixpickle/uber-ga

Naive Bayes implementation with digit recognition: https://github.com/r9y9/naive_bayes

corpus of Chinese abbreviation: https://github.com/lancopku/Chinese-abbreviation-dataset

style2paints: https://github.com/lllyasviel/style2paints/blob/master/README.md

FAIR's Mask R-CNN and RetinaNet: https://github.com/facebookresearch/Detectron

Learning embeddings for classification: https://github.com/facebookresearch/StarSpace

Adversarial Examples for Evaluating Reading Comprehension Systems: https://github.com/robinjia/adversarial-squad

Automatic Training of MCMC Samplers: https://github.com/brain-research/l2hmc

A3C PyTorch: https://github.com/dgriff777/a3c_continuous

Poincare embedding: https://github.com/facebookresearch/poincare-embeddings

Dynamic_Neural_Manifold: https://github.com/Miej/Dynamic_Neural_Manifold

GAN for Photorealistic and Identity: https://github.com/HRLTY/TP-GAN

CipherGAN: https://github.com/for-ai/CipherGAN

Benchmarks and Temporal Convolutional Networks: https://github.com/locuslab/TCN

Multilingual Unsupervised or Supervised word Embeddings: https://github.com/facebookresearch/MUSE#ground-truth-bilingual-dictionaries

SpaceX Falcon 9: https://github.com/arex18/rocket-lander

Chinese Word Vectors: https://github.com/Embedding/Chinese-Word-Vectors

Deep Painterly Harmonization: https://github.com/luanfujun/deep-painterly-harmonization

Augmented Random Search: https://github.com/modestyachts/ARS

Learning-to-See-in-the-Dark: https://github.com/cchen156/Learning-to-See-in-the-Dark

Music database: https://github.com/chrisdonahue/nesmdb

Fast deep net: https://github.com/mitdbg/fastdeepnets

gradient-checkpointing: https://github.com/openai/gradient-checkpointing

Full World Models Implementation: https://github.com/AdeelMufti/WorldModels

State of the art: https://paperswithcode.com/sota?fbclid=IwAR1Rdpnx2Uazou_3gnzOcfYhq1zOlfW6W9RngR2hl42ND1KOl9nKqT0Ij-U

CUHK IE Media lab:

Deep Fashion: http://mmlab.ie.cuhk.edu.hk/projects/DeepFashion.html

Others:

Openface: https://cmusatyalab.github.io/openface/

dlib c++: http://blog.dlib.net/2014/08/real-time-face-pose-estimation.html

Age and gender: http://www.openu.ac.il/home/hassner/projects/cnn_agegender/ https://gist.github.com/GilLevi/c9e99062283c719c03de

OCR: https://github.com/ayman/textr

Chinese front generation: https://github.com/kaonashi-tyc/Rewrite

Deep Learning Face Detection: https://github.com/guoyilin/FaceDetection_CNN

simple GAN: https://github.com/kvfrans/generative-adversial

simple Variational autoencoder: https://github.com/kvfrans/variational-autoencoder

Nvidia pix2pix: https://github.com/NVIDIA/pix2pixHD