图像处理/识别
1.PixelCNN & PixelRNN in TensorFlow
TensorFlow implementation of Pixel Recurrent Neural Networks.
地址：https://github.com/carpedm20/pixel-rnn-tensorflow
2.Simulated+Unsupervised (S+U) learning in TensorFlow
TensorFlow implementation of Learning from Simulated and Unsupervised Images through Adversarial Training.
地址：https://github.com/carpedm20/simulated-unsupervised-tensorflow
3.ResNet in TensorFlow
Implemenation of Deep Residual Learning for Image Recognition. Includes a tool to use He et al's published trained Caffe weights in TensorFlow.
地址：https://github.com/ry/tensorflow-resnet
4.A composable Generative Adversarial Network(GAN) with API and command line tool
HyperGAN，A versatile GAN(generative adversarial network) implementation focused on scalability and ease-of-use.
地址：https://github.com/255BITS/HyperGAN
5.conversation of caffe vgg16 model to tensorflow
VGG-16 is my favorite image classification model to run because of its simplicity and accuracy. The creators of this model published a pre-trained binary that can be used in Caffe.
地址：https://github.com/ry/tensorflow-vgg16
6.A Kitti Road Segmentation model implemented in tensorflow
KittiSeg performs segmentation of roads by utilizing an FCN based model. The model achieved first place on the Kitti Road Detection Benchmark at submission time. Check out our paper for a detailed model description.
地址：https://github.com/MarvinTeichmann/KittiSeg
7.TensorFlow tutorial on Generative Adversarial Models
地址：https://github.com/ericjang/genadv_tutorial
8.Pretrained models for TFLearn and TensorFlow
地址：https://github.com/tflearn/models
9.Generative Models with TensorFlow
地址：https://github.com/arahuja/generative-tf
10.Re-implementation of the m-RNN model using TensorFLow
This package is a re-implementation of the m-RNN image captioning method using TensorFlow. The training speed is optimized with buckets of different lengths of the training sentences. It also support the Beam Search method to decode image features into sentences.
地址：https://github.com/mjhucla/TF-mRNN
11.Recurrent Models of Visual Attention
Modified from https://github.com/jlindsey15/RAM
Implementation of "Recurrent Models of Visual Attention" V. Mnih et al.
Run by python ram.py and it can reproduce the result on Table 1 (a) 28x28 MNIST
地址：https://github.com/zhongwen/RAM
12.Simple Image Classification Models for the CIFAR-10 dataset using TensorFlow
This is the code for the blog post 'How to Build a Simple Image Recognition System Using TensorFlow'.
地址：https://github.com/wolfib/image-classification-CIFAR10-tf
13.IllustrationGAN
A simple, clean TensorFlow implementation of Generative Adversarial Networks with a focus on modeling illustrations.
地址：https://github.com/tdrussell/IllustrationGAN
14.ImageNet pre-trained models with batch normalization
This repository contains convolutional neural network (CNN) models trained on ImageNet by Marcel Simon at the Computer Vision Group Jena (CVGJ) using the Caffe framework. Each model is in a separate subfolder and contains everything needed to reproduce the results. This repository focuses currently contains the batch-normalization-variants of AlexNet and VGG19 as well as the training code for Residual Networks (Resnet).
地址：https://github.com/cvjena/cnn-models
15.Face recognition using Tensorflow
This is a TensorFlow implementation of the face recognizer described in the paper "FaceNet: A Unified Embedding for Face Recognition and Clustering". The project also uses ideas from the paper "A Discriminative Feature Learning Approach for Deep Face Recognition" as well as the paper "Deep Face Recognition" from the Visual Geometry Group at Oxford.
地址：https://github.com/davidsandberg/facenet
语音/语义/文字
1.Multi-layer Recurrent Neural Networks (LSTM, RNN) for word-level language models in Python using TensorFlow
Mostly reused code from https://github.com/sherjilozair/char-rnn-tensorflow which was inspired from Andrej Karpathy's char-rnn.
地址：https://github.com/hunkim/word-rnn-tensorflow
2.LSTM language model with CNN over characters in TensorFlow
Tensorflow implementation of Character-Aware Neural Language Models. The original code of author can be found here.
地址：https://github.com/carpedm20/lstm-char-cnn-tensorflow
3.A neural conversational model
My tensorflow implementation of "A neural conversational model", a Deep learning based chatbot. This work tries to reproduce the results of A Neural Conversational Model (aka the Google chatbot). It uses a RNN (seq2seq model)for sentence predictions. It is done using python and TensorFlow.
地址：https://github.com/Conchylicultor/DeepQA
4.Tensorflow based Neural Conversation Models
This implementation contains an extension of seq2seq tutorial for conversation models in Tensorflow. Examples of basic model can be found in this paper.
地址：https://github.com/pbhatia243/Neural_Conversation_Models
5.ByteNet for character-level language modelling
This is a tensorflow implementation of the byte-net model from DeepMind's paper Neural Machine Translation in Linear Time.
地址：https://github.com/paarthneekhara/byteNet-tensorflow
6.Language Modeling with Gated Convolutional Networks
This is a Tensorflow implementation of Facebook AI Research Lab's paper: Language Modeling with Gated Convolutional Networks. This paper applies a convolutional approach to language modelling with a novel Gated-CNN model.
地址：https://github.com/anantzoid/Language-Modeling-GatedCNN
7.Experiment diverse Deep learning models for music generation with TensorFlow
The different models and experiments are explained here.
地址：https://github.com/Conchylicultor/MusicGenerator
8.TensorFlow RNN Language Model
This module is an example of how create a recursive neural network language model using TensorFlow.
地址：https://github.com/wpm/tfrnnlm
9.tensorflow port of the lda2vec model for unsupervised learning of document + topic + word embeddings
TensorFlow implementation of Christopher Moody's lda2vec, a hybrid of Latent Dirichlet Allocation & word2vec.
地址：https://github.com/meereeum/lda2vec-tf
10.Implement character-level language models for text generation based-on LSTM, in Python/TensorFlow
本程序用于自动生成一段中文文本（训练语料是英文时也可用于生成英文文本），具体生成文本的内容和形式取决于训练语料。模型基本思想和 karpathy 的 char-rnn 程序一致，利用循环神经网络 (RNN) 在大规模语料上训练一个 language model，然后利用训练好的 language model 去自动生成一段文本。相比于 theano 版本的 char-rnn 模型，本模型采用了多层 RNN 而不是单层（tensorflow 中实现一个多层 RNN 简直太方便了），同时还支持 max、sample 和 beam-search 多种生成策略。本程序代码参考了 tensorflow 官方给出的一个 language model 程序 ptb_word_lm.py。
地址：https://github.com/hit-computer/char-rnn-tf
11.Visual Question Answering Demo on pretrained model
This is a simple Demo of Visual Question answering which uses pretrained models (see models/CNN and models/VQA) to answer a given question about the given image.
地址：https://github.com/iamaaditya/VQA_Demo
12.tf-adaptive-softmax-lstm-lm
This repository shows the experiment result of LSTM language models on PTB (Penn Treebank) and GBW (Google One Billion Word) using AdaptiveSoftmax on TensorFlow.
地址：https://github.com/TencentAILab/tf-adaptive-softmax-lstm-lm
Speech Recognition
1.Linux Speech Recognition
Open speech recognition for Linux
地址：https://github.com/JamezQ/Palaver
2.Speech-to-Text-WaveNet : End-to-end sentence level English speech recognition based on DeepMind's WaveNet and tensorflow
A tensorflow implementation of speech recognition based on DeepMind's WaveNet: A Generative Model for Raw Audio. (Hereafter the Paper)
地址：https://github.com/buriburisuri/speech-to-text-wavenet
3.Automatic-Speech-Recognition
End-to-end automatic speech recognition from scratch in Tensorflow
地址：https://github.com/zzw922cn/Automatic_Speech_Recognition
4.PocketSphinx 5prealpha
This is PocketSphinx, one of Carnegie Mellon University's open source large vocabulary, speaker-independent continuous speech recognition engine.
THIS IS A RESEARCH SYSTEM. This is also an early release of a research system. We know the APIs and function names are likely to change, and that several tools need to be made available to make this all complete. With your help and contributions, this can progress in response to the needs and patches provided.
Please see the LICENSE file for terms of use.
地址：https://github.com/cmusphinx/pocketsphinx
5.Tensorflow Speech Recognition
Speech recognition using google's tensorflow deep learning framework, sequence-to-sequence neural networks.
Replaces caffe-speech-recognition, see there for some background.
地址：https://github.com/pannous/tensorflow-speech-recognition
6.HanLP: Han Language Processing
自然语言处理 中文分词 词性标注 命名实体识别 依存句法分析 关键词提取 自动摘要 短语提取 拼音 简繁转换http://www.hankcs.com/nlp/
地址：https://github.com/hankcs/HanLP
视频/动作检测
1.Action Recognition using Visual Attention
We propose a soft attention based model for the task of action recognition in videos. We use multi-layered Recurrent Neural Networks (RNNs) with Long-Short Term Memory (LSTM) units which are deep both spatially and temporally. Our model learns to focus selectively on parts of the video frames and classifies videos after taking a few glimpses. The model essentially learns which parts in the frames are relevant for the task at hand and attaches higher importance to them. We evaluate the model on UCF-11 (YouTube Action), HMDB-51 and Hollywood2 datasets and analyze how the model focuses its attention depending on the scene and the action being performed.
地址：https://github.com/kracwarlock/action-recognition-visual-attention
2.Deep Video Analytics
A highly configurable visual search & analytics platform for images and videos. https://deepvideoanalytics.com/
地址：https://github.com/AKSHAYUBHAT/DeepVideoAnalytics
3.Visual Search Server
As of Jan 2017 I am now developing Deep Video Analytics. It provides a more complete set of functionality for video and image analytics (such as uploads, async processing, docker-compose etc.) in addition to all the features provided by this repository. You can find the Deep Video Analytics repo here.
地址：https://github.com/AKSHAYUBHAT/VisualSearchServer
综合
1.TensorFlow Models
This repository contains machine learning models implemented in TensorFlow. The models are maintained by their respective authors.
地址：https://github.com/tensorflow/models
2.Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow
What's in it?
GAN:1.Vanilla GAN 2.Conditional GAN 3.InfoGAN 4.Wasserstein GAN 5.Mode Regularized GAN 6.Coupled GAN 7.Auxiliary Classifier GAN 8.Least Squares GAN 9.Boundary Seeking GAN 10.Energy Based GAN 11.f-GAN 12.Generative Adversarial Parallelization 12.DiscoGAN 13Adversarial Feature Learning & Adversarially Learned Inference
VAE:1.Vanilla VAE 2.Conditional VAE 3.Denoising VAE 4.Adversarial Autoencoder 5.Adversarial Variational Bayes
地址：https://github.com/wiseodd/generative-models
3.Deep learning using tensorflow
Tensorflow Projects A repo of everything deep and neurally related. Implementations and ideas are largely based on papers from arxiv and implementations, tutorials from the internet.
地址：https://github.com/shekkizh/TensorflowProjects
4.A library for probabilistic modeling, inference, and criticism. Deep generative models, variational inference. Runs on TensorFlow.
Edward is a Python library for probabilistic modeling, inference, and criticism. It is a testbed for fast experimentation and research with probabilistic models, ranging from classical hierarchical models on small data sets to complex deep probabilistic models on large data sets. Edward fuses three fields: Bayesian statistics and machine learning, deep learning, and probabilistic programming.
地址：https://github.com/blei-lab/edward
5.Tensorflow Tutorial files and Implementations of various Deep NLP and CV Models.
This repository contains Tensorflow implementations of various deep learning models, with a focus on problems in Natural Language Processing. Each individual subdirectory is self-contained, addressing one specific model.
地址：https://github.com/siddk/deep-nlp
6.A tensorflow library for building all kinds of models
TensorGraph is a framework for building any imaginable models based on TensorFlow.
As deep learning becomes more and more common and the architectures becoming more and more complicated, it seems that we need some easy to use framework to quickly build these models and that's why TensorGraph is born. It's a very simple and easy to use framework, but it allows you to build all kinds of imaginable models.
地址：https://github.com/hycis/TensorGraph
7.PyTorch and Tensorflow functional model definitions
Model definitions and pretrained weights for PyTorch and Tensorflow
PyTorch, unlike lua torch, has autograd in it's core, so using modular structure of torch.nn modules is not necessary, one can easily allocate needed Variables and write a function that utilizes them, which is sometimes more convenient. This repo contains model definitions in this functional way, with pretrained weights for some models.
Weights are serialized as a dict of arrays in hdf5, so should be easily loadable in other frameworks. Thanks to @edgarriba we have cpp_parser for loading weights in C++.
More models coming! We also plan to add definitions for other frameworks in future, probably tiny-dnn first. Contributions are welcome.
See also imagenet classification with PyTorch demo.ipynb
地址：https://github.com/szagoruyko/functional-zoo
8.Neural network models in tensorflow
地址：https://github.com/AJwader/Tensorflow-models
其他
1.Caffe models in TensorFlow
Convert Caffe models to TensorFlow.
地址：https://github.com/ethereon/caffe-tensorflow
2.Run Keras models (tensorflow backend) in the browser, with GPU support
Models are created directly from the Keras JSON-format configuration file, using weights serialized directly from the corresponding HDF5 file. Also works in node, but only in CPU mode.
地址：https://github.com/transcranial/keras-js
3.Simplify the training and tuning of Tensorflow models
Stop wasting your time rewriting the training, evaluation & visualization procedures for your ML model: let DyTB do the work for you!
地址：https://github.com/galeone/dynamic-training-bench
4.Observations and notes to understand the workings of neural network models and other thought experiments using Tensorflow
A repo of observations and notes to understand the workings of neural network models and other simple thought experiments using Tensorflow.
地址：https://github.com/shekkizh/neuralnetworks.thought-experiments
5.attention model for entailment on SNLI corpus implemented in Tensorflow and Keras
Implementations of a attention model for entailment from this paper in keras and tensorflow.
Compatible with keras v1.0.6 and tensorflow 0.11.0rc2
I implemented the model to learn the APIs for keras and tensorflow, so I have not really tuned on the performance. The models implemented in keras is a little different, as keras does not expose a method to set a LSTMs state.
地址：https://github.com/shyamupa/snli-entailment
6.Multilayer Feed-Forward Neural Network predictive model implementations with TensorFlow and scikit-learn
This project provides multilayer perceptron predictive models, implemented using TensorFlow and following the scikit-learnPredictor API.
地址：https://github.com/civisanalytics/muffnn
7.Keras pretrained models (VGG16 and InceptionV3)+ Transfer Learning for predicting classes in the Oxford 102 flower dataset
See my application for identifying plants and taking care them - Plant Care. It works using the code from the model implemented in this repo.
This bootstraps the training of deep convolutional neural networks with Keras to classify images in the Oxford 102 category flower dataset.
Train process is fully automated and the best weights for the model will be saved.
This code can be used for any dataset, just follow the original files structure in data/sorted directory after running bootstrap.py. If you wish to store your dataset somewhere else, you can do it and run train.py with setting a path to dataset with a special parameter --data_dir==path/to/your/sorted/data.
地址：https://github.com/Arsey/keras-transfer-learning-for-oxford102
8.Tensorflow Model Zoo for Torch7 and PyTorch
This is a porting of tensorflow pretrained models made by Remi Cadene and Micael Carvalho. Special thanks to Moustapha Cissé. All models have been tested on Imagenet.
This work was inspired by inception-v3.torch.
地址：https://github.com/Cadene/tensorflow-model-zoo.torch
9.Keras implementation of "Wide Residual Networks"
This repo contains the code to run Wide Residual Networks using Keras.
Paper (v1): http://arxiv.org/abs/1605.07146v1 (the authors have since published a v2 of the paper, which introduces slightly different preprocessing and improves the accuracy a little).
Original code: https://github.com/szagoruyko/wide-residual-networks
地址：https://github.com/asmith26/wide_resnets_keras
10.Caffe Model Zoo
Check out the model zoo documentation for details.
To acquire a model:
download the model gist by ./scripts/download_model_from_gist.sh <gist_id><dirname> to load the model metadata, architecture, solver configuration, and so on.(<dirname> is optional and defaults to caffe/models).
download the model weights by ./scripts/download_model_binary.py <model_dir> where <model_dir> is the gist directory from the first step.
or visit the model zoo documentation for complete instructions.
地址：https://github.com/BVLC/caffe/wiki/Model-Zoo
