| Example | Description | |----------------------|------------------------------------| | addition_rnn | Implementation of sequence to sequence learning for performing addition of two numbers (as strings). | | babi_memnn | Trains a memory network on the bAbI dataset for reading comprehension. | | babi_rnn | Trains a two-branch recurrent network on the bAbI dataset for reading comprehension. | | cifar10_cnn | Trains a simple deep CNN on the CIFAR10 small images dataset. | | cifar10_densenet | Trains a DenseNet-40-12 on the CIFAR10 small images dataset. | | conv_lstm | Demonstrates the use of a convolutional LSTM network. | | deep_dream | Deep Dreams in Keras. | | eager_dcgan | Generating digits with generative adversarial networks and eager execution. | | eager_image_captioning | Generating image captions with Keras and eager execution. | | eager_pix2pix | Image-to-image translation with Pix2Pix, using eager execution. | | eager_styletransfer | Neural style transfer with eager execution. | | fine_tuning | Fine tuning of a image classification model. | | imdb_bidirectional_lstm | Trains a Bidirectional LSTM on the IMDB sentiment classification task. | | imdb_cnn | Demonstrates the use of Convolution1D for text classification. | | imdb_cnn_lstm | Trains a convolutional stack followed by a recurrent stack network on the IMDB sentiment classification task. | | imdb_fasttext | Trains a FastText model on the IMDB sentiment classification task. | | imdb_lstm | Trains a LSTM on the IMDB sentiment classification task. | | lstm_text_generation | Generates text from Nietzsche's writings. | | lstm_seq2seq | This script demonstrates how to implement a basic character-level sequence-to-sequence model. | | mnist_acgan | Implementation of AC-GAN (Auxiliary Classifier GAN ) on the MNIST dataset | | mnist_antirectifier | Demonstrates how to write custom layers for Keras | | mnist_cnn | Trains a simple convnet on the MNIST dataset. | | mnist_cnn_embeddings | Demonstrates how to visualize embeddings in TensorBoard. | | mnist_irnn | Reproduction of the IRNN experiment with pixel-by-pixel sequential MNIST in "A Simple Way to Initialize Recurrent Networks of Rectified Linear Units" by Le et al. | | mnist_mlp | Trains a simple deep multi-layer perceptron on the MNIST dataset. | | mnist_hierarchical_rnn | Trains a Hierarchical RNN (HRNN) to classify MNIST digits. | | mnist_tfrecord | MNIST dataset with TFRecords, the standard TensorFlow data format. | | mnist_transfer_cnn | Transfer learning toy example. | | neural_style_transfer | Neural style transfer (generating an image with the same “content” as a base image, but with the “style” of a different picture). | | nmt_attention | Neural machine translation with an attention mechanism. | | quora_siamese_lstm | Classifying duplicate quesitons from Quora using Siamese Recurrent Architecture. | | reuters_mlp | Trains and evaluatea a simple MLP on the Reuters newswire topic classification task. | | stateful_lstm | Demonstrates how to use stateful RNNs to model long sequences efficiently. | | text_explanation_lime | How to use lime to explain text data. | | variational_autoencoder | Demonstrates how to build a variational autoencoder. | | variational_autoencoder_deconv | Demonstrates how to build a variational autoencoder with Keras using deconvolution layers. | | tfprob_vae | A variational autoencoder using TensorFlow Probability on Kuzushiji-MNIST. | | vq_vae | Discrete Representation Learning with VQ-VAE and TensorFlow Probability. |



dfalbel/keras documentation built on Nov. 27, 2019, 8:16 p.m.