Python 深度学习框架Keras资源分享

Python 深度学习框架Keras资源分享

Keras resources

This is a directory of tutorials and open-source code repositories for working with Keras, the Python deep learning library.

If you have a high-quality tutorial or project to add, please open a PR.

Official starter resources

keras.io - Keras documentationGetting started with the Sequential modelGetting started with the functional APIKeras FAQ

Tutorials

Quick start: the Iris dataset in Keras and scikit-learnUsing pre-trained word embeddings in a Keras modelBuilding powerful image classification models using very little dataBuilding Autoencoders in KerasA complete guide to using Keras as part of a TensorFlow workflowIntroduction to Keras, from University of Waterloo: video - slidesIntroduction to Deep Learning with Keras, from CERN: video - slidesInstalling Keras for deep learningDevelop Your First Neural Network in Python With Keras Step-By-StepPractical Neural Networks with Keras: Classifying Yelp Reviews (Shows basic classification and how to set up a GPU instance on AWS)Understanding Stateful LSTM Recurrent Neural Networks in Python with KerasTime Series Prediction with LSTM Recurrent Neural Networks in Python with KerasKeras video tutorials from Dan Van BoxelKeras Deep Learning Tutorial for Kaggle 2nd Annual Data Science BowlCollection of tutorials setting up DNNs with KerasFast.AI - Practical Deep Learning For Coders, Part 1 (great information on deep learning in general, heavily uses Keras for the labs)Keras Tutorial: Content Based Image Retrieval Using a Convolutional Denoising AutoencoderA Bit of Deep Learning and Keras: a multipart video introduction to deep learning and kerasFive simple examples of the Keras Functional APIKeras video tutorials playlist from Deeplizard

Books based on Keras

Deep Learning with PythonDeep Learning with KerasDeep Learning and the Game of Go (MEAP)

Code examples

Working with text

Reuters topic classificationLSTM on the IMDB dataset (text sentiment classification)Bidirectional LSTM on the IMDB dataset1D CNN on the IMDB dataset1D CNN-LSTM on the IMDB datasetLSTM-based network on the bAbI datasetMemory network on the bAbI dataset (reading comprehension question answering)Sequence to sequence learning for performing additions of strings of digitsLSTM text generationUsing pre-trained word embeddingsMonolingual and Multilingual Image CaptioningFastText on the IMDB datasetStructurally constrained recurrent nets text generationCharacter-level convolutional neural nets for text classificationLSTM to predict gender of a nameLanguage/dialect identification with multiple character-level CNNs

Working with images

Simple CNN on MNISTSimple CNN on CIFAR10 with data augmentationInception v3VGG 16 (with pre-trained weights)VGG 19 (with pre-trained weights)ResNet 50 (with pre-trained weights): 1 - 2FractalNetAlexNet, VGG 16, VGG 19, and class heatmap visualizationVisual-Semantic EmbeddingVariational Autoencoder: with deconvolutions - with upsamplingVisual question answeringDeep Networks with Stochastic DepthSmile detection with a CNNVGG-CAMt-SNE of image CNN fc7 activationsVGG16 Deconvolution networkWide Residual Networks (with pre-trained weights): 1 - 2Ultrasound nerve segmentation: 1 - 2DeepMask object segmentationDensely Connected Convolutional Networks: 1 - 2Snapshot Ensembles: Train 1, Get M for FreeSingle Shot MultiBox DetectorPopular Image Segmentation Models : FCN, Segnet, U-Net etc.

Creative visual applications

Real-time style transferStyle transfer: 1 - 2Image analogies: Generate image analogies using neural matching and blending.Visualizing the filters learned by a CNNDeep dreamsGAN / DCGAN: 1 - 2 - 3 - 4InfoGANpix2pixDFI: Deep Feature InterpolationColorful Image colorization: B&W to color

Reinforcement learning

DQNFlappyBird DQNasync-RL: Tensorflow + Keras + OpenAI Gym implementation of 1-step Q Learning from "Asynchronous Methods for Deep Reinforcement Learning"keras-rl: A library for state-of-the-art reinforcement learning. Integrates with OpenAI Gym and implements DQN, double DQN, Continuous DQN, and DDPG.

Miscallenous architecture blueprints

Stateful LSTMSiamese networkPretraining on a different datasetNeural programmer-interpreter

Third-party libraries

Elephas: Distributed Deep Learning with Keras & SparkHyperas: Hyperparameter optimizationHera: in-browser metrics dashboard for Keras modelsKerlym: reinforcement learning with Keras and OpenAI GymQlearning4K: reinforcement learning add-on for Kerasseq2seq: Sequence to Sequence Learning with KerasSeya: Keras extrasKeras Language Modeling: Language modeling tools for KerasRecurrent Shop: Framework for building complex recurrent neural networks with KerasKeras.js: Run trained Keras models in the browser, with GPU supportkeras-vis: Neural network visualization toolkit for keras.

Projects built with Keras

RocAlphaGo: An independent, student-led replication of DeepMind's 2016 Nature publication, "Mastering the game of Go with deep neural networks and tree search"BetaGo: Deep Learning Go bots using KerasDeepJazz: Deep learning driven jazz generation using Kerasdataset-sts: Semantic Text Similarity Dataset Hubsnli-entailment: Independent implementation of attention model for textual entailment from the paper "Reasoning about Entailment with Neural Attention".Headline generator: independent implementation of Generating News Headlines with Recurrent Neural NetworksLipNet: independent implementation of LipNet: End-to-End Sentence-level Lipreading.caption_generator: An implementation of image caption generation in natural language inspired from Show and Tell: A Neural Image Caption Generator.NMT-Keras: Neural Machine Translation using Keras.Conx - easy-to-use layer on top of Keras, with visualizations (eg, no knowledge of numpy needed)

版权声明：本文内容由网络用户投稿，版权归原作者所有，本站不拥有其著作权，亦不承担相应法律责任。如果您发现本站中有涉嫌抄袭或描述失实的内容，请联系我们jiasou666@gmail.com 处理，核实后本网站将在24小时内删除侵权内容。