# Keras examples directory
## Vision models examples
[mnist_mlp.py](mnist_mlp.py)
Trains a simple deep multi-layer perceptron on the MNIST dataset.
[mnist_cnn.py](mnist_cnn.py)
Trains a simple convnet on the MNIST dataset.
[cifar10_cnn.py](cifar10_cnn.py)
Trains a simple deep CNN on the CIFAR10 small images dataset.
[cifar10_cnn_capsule.py](cifar10_cnn_capsule.py)
Trains a simple CNN-Capsule Network on the CIFAR10 small images dataset.
[cifar10_resnet.py](cifar10_resnet.py)
Trains a ResNet on the CIFAR10 small images dataset.
[conv_lstm.py](conv_lstm.py)
Demonstrates the use of a convolutional LSTM network.
[image_ocr.py](image_ocr.py)
Trains a convolutional stack followed by a recurrent stack and a CTC logloss function to perform optical character recognition (OCR).
[mnist_acgan.py](mnist_acgan.py)
Implementation of AC-GAN (Auxiliary Classifier GAN) on the MNIST dataset
[mnist_hierarchical_rnn.py](mnist_hierarchical_rnn.py)
Trains a Hierarchical RNN (HRNN) to classify MNIST digits.
[mnist_siamese.py](mnist_siamese.py)
Trains a Siamese multi-layer perceptron on pairs of digits from the MNIST dataset.
[mnist_swwae.py](mnist_swwae.py)
Trains a Stacked What-Where AutoEncoder built on residual blocks on the MNIST dataset.
[mnist_transfer_cnn.py](mnist_transfer_cnn.py)
Transfer learning toy example on the MNIST dataset.
[mnist_denoising_autoencoder.py](mnist_denoising_autoencoder.py)
Trains a denoising autoencoder on the MNIST dataset.
----
## Text & sequences examples
[addition_rnn.py](addition_rnn.py)
Implementation of sequence to sequence learning for performing addition of two numbers (as strings).
[babi_rnn.py](babi_rnn.py)
Trains a two-branch recurrent network on the bAbI dataset for reading comprehension.
[babi_memnn.py](babi_memnn.py)
Trains a memory network on the bAbI dataset for reading comprehension.
[imdb_bidirectional_lstm.py](imdb_bidirectional_lstm.py)
Trains a Bidirectional LSTM on the IMDB sentiment classification task.
[imdb_cnn.py](imdb_cnn.py)
Demonstrates the use of Convolution1D for text classification.
[imdb_cnn_lstm.py](imdb_cnn_lstm.py)
Trains a convolutional stack followed by a recurrent stack network on the IMDB sentiment classification task.
[imdb_fasttext.py](imdb_fasttext.py)
Trains a FastText model on the IMDB sentiment classification task.
[imdb_lstm.py](imdb_lstm.py)
Trains an LSTM model on the IMDB sentiment classification task.
[lstm_stateful.py](lstm_stateful.py)
Demonstrates how to use stateful RNNs to model long sequences efficiently.
[lstm_seq2seq.py](lstm_seq2seq.py)
Trains a basic character-level sequence-to-sequence model.
[lstm_seq2seq_restore.py](lstm_seq2seq_restore.py)
Restores a character-level sequence to sequence model from disk (saved by [lstm_seq2seq.py](lstm_seq2seq.py)) and uses it to generate predictions.
[pretrained_word_embeddings.py](pretrained_word_embeddings.py)
Loads pre-trained word embeddings (GloVe embeddings) into a frozen Keras Embedding layer, and uses it to train a text classification model on the 20 Newsgroup dataset.
[reuters_mlp.py](reuters_mlp.py)
Trains and evaluate a simple MLP on the Reuters newswire topic classification task.
----
## Generative models examples
[lstm_text_generation.py](lstm_text_generation.py)
Generates text from Nietzsche's writings.
[conv_filter_visualization.py](conv_filter_visualization.py)
Visualization of the filters of VGG16, via gradient ascent in input space.
[deep_dream.py](deep_dream.py)
Deep Dreams in Keras.
[neural_doodle.py](neural_doodle.py)
Neural doodle.
[neural_style_transfer.py](neural_style_transfer.py)
Neural style transfer.
[variational_autoencoder.py](variational_autoencoder.py)
Demonstrates how to build a variational autoencoder.
[variational_autoencoder_deconv.py](variational_autoencoder_deconv.py)
Demonstrates how to build a variational autoencoder with Keras using deconvolution layers.
----
## Examples demonstrating specific Keras functionality
[antirectifier.py](antirectifier.py)
Demonstrates how to write custom layers for Keras.
[mnist_sklearn_wrapper.py](mnist_sklearn_wrapper.py)
Demonstrates how to use the sklearn wrapper.
[mnist_irnn.py](mnist_irnn.py)
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_net2net.py](mnist_net2net.py)
Reproduction of the Net2Net experiment with MNIST in "Net2Net: Accelerating Learning via Knowledge Transfer".
[reuters_mlp_relu_vs_selu.py](reuters_mlp_relu_vs_selu.py)
Compares self-normalizing MLPs with regular MLPs.
[mnist_tfrecord.py](mnist_tfrecord.py)
MNIST dataset with TFRecords, the standard TensorFlow data format.
[mnist_dataset_api.py](mnist_dataset_api.py)
MNIST dataset with TensorFlow's Dataset API.
[cifar10_cnn_tfaugment2d.py](cifar10_cnn_tfaugment2d.py)
Trains a simple deep CNN on the CIFAR10 small images dataset using Tensorflow internal augmentation APIs.
[tensorboard_embeddings_mnist.py](tensorboard_embeddings_mnist.py)
Trains a simple convnet on the MNIST dataset and embeds test data which can be later visualized using TensorBoard's Embedding Projector.
没有合适的资源?快使用搜索试试~ 我知道了~
资源推荐
资源详情
资源评论
收起资源包目录
Keras-2.4.3.tar.gz (225个子文件)
setup.cfg 100B
theme.css 114KB
theme_extra.css 3KB
base.html 6KB
breadcrumbs.html 2KB
nav.html 1KB
footer.html 1KB
versions.html 992B
search.html 538B
toc.html 486B
searchbox.html 224B
404.html 145B
main.html 26B
MANIFEST.in 96B
jquery-2.1.1.min.js 82KB
modernizr-2.8.3.min.js 11KB
theme.js 4KB
LICENSE 2KB
applications.md 31KB
faq.md 26KB
functional-api-guide.md 17KB
sequential-model-guide.md 13KB
CONTRIBUTING.md 8KB
datasets.md 8KB
why-use-keras.md 6KB
backend.md 5KB
README.md 5KB
about-keras-models.md 5KB
writing-your-own-keras-layers.md 3KB
callbacks.md 2KB
scikit-learn-api.md 2KB
visualization.md 2KB
losses.md 2KB
metrics.md 2KB
regularizers.md 1KB
about-keras-layers.md 1KB
optimizers.md 1KB
initializers.md 1KB
README.md 1KB
activations.md 913B
model.md 686B
constraints.md 612B
README.md 608B
sequential.md 187B
index.md 181B
text.md 43B
image.md 42B
PKG-INFO 1012B
PKG-INFO 1012B
test_training.py 77KB
test_multiprocessing.py 43KB
convolutional_test.py 39KB
metrics_confusion_matrix_test.py 39KB
recurrent_test.py 37KB
metrics_test.py 37KB
callbacks_test.py 35KB
losses_test.py 32KB
test_topology.py 27KB
image_test.py 25KB
wrappers_test.py 23KB
image_ocr.py 21KB
test_model_saving.py 20KB
autogen.py 17KB
data_utils_test.py 17KB
cifar10_resnet.py 16KB
mnist_net2net.py 16KB
metrics_correctness_test.py 16KB
test_sequential_model.py 16KB
neural_doodle.py 14KB
mnist_acgan.py 13KB
core_test.py 11KB
neural_style_transfer.py 10KB
tensorboard_test.py 10KB
conv_filter_visualization.py 9KB
structure.py 9KB
lstm_seq2seq.py 9KB
merge_test.py 9KB
babi_rnn.py 9KB
sequence_test.py 9KB
babi_memnn.py 8KB
cnn_seq2seq.py 8KB
normalization_test.py 8KB
lstm_stateful.py 8KB
test_temporal_data_tasks.py 7KB
variational_autoencoder_deconv.py 7KB
addition_rnn.py 7KB
mnist_swwae.py 7KB
activations_test.py 7KB
generic_utils.py 7KB
variational_autoencoder.py 7KB
layer_subclassing_tests.py 6KB
test_loss_weighting.py 6KB
scikit_learn_test.py 6KB
convolutional_recurrent_test.py 6KB
deep_dream.py 6KB
conv_utils.py 6KB
optimizers_test.py 6KB
lstm_seq2seq_restore.py 6KB
reuters_mlp_relu_vs_selu.py 5KB
conv_lstm.py 5KB
共 225 条
- 1
- 2
- 3
资源评论
假技术po主
- 粉丝: 514
- 资源: 4199
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功