深度学习工程化神器Keras教程:《Keras深度学习进阶》随书代码

【导读】Keras是目前最好用的深度学习框架之一,具有非常完备和友好的工程化API接口。目前TensorFlow直接将Keras(tf.keras)作为面向使用者的主要接口。本文介绍Github上的《Keras深度学习进阶》随书代码项目。


Keras是目前最好用的深度学习框架之一,在模型构建、模型训练、模型评价、模型保存、预测、日志等功能上都具有非常完备和友好的工程化API接口。另外,由于Keras与TensorFlow无缝兼容(无论是Keras还是tf.keras),使得Keras可以依附于TensorFlow强大的生态圈。因此,Keras被工业界广泛应用在模型研发和线上业务中。


本文介绍图书《Advanced Deep Learning with Keras》(《Keras深度学习进阶》)在Github上的随书代码项目。该图书由浅入深地介绍了MLP(多层感知机)、CNN(卷积神经网络)、Autoencoder(自编码器)、GAN(生成式对抗网络)等模型的原理及Keras实现。该Github项目地址为:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras


包含内容大致如下:


Chapter 1 - Introduction


MLP on MNIST:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter1-keras-quick-tour/mlp-mnist-1.3.2.py


CNN on MNIST:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter1-keras-quick-tour/cnn-mnist-1.4.1.py


RNN on MNIST:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter1-keras-quick-tour/rnn-mnist-1.5.1.py


Chapter 2 - Deep Networks


Functional API on MNIST:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter2-deep-networks/cnn-functional-2.1.1.py


Y-Network on MNIST:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter2-deep-networks/cnn-y-network-2.1.2.py


ResNet v1 and v2 on CIFAR10:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter2-deep-networks/resnet-cifar10-2.2.1.py


DenseNet on CIFAR10:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter2-deep-networks/densenet-cifar10-2.4.1.py


Chapter 3 - AutoEncoders


Denoising AutoEncoders:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter3-autoencoders/denoising-autoencoder-mnist-3.3.1.py


Colorization AutoEncoder:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter3-autoencoders/colorization-autoencoder-cifar10-3.4.1.py


Chapter 4 - Generative Adversarial Network (GAN)


Deep Convolutional GAN (DCGAN):

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter4-gan/dcgan-mnist-4.2.1.py


Conditional (GAN):

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter4-gan/cgan-mnist-4.3.1.py


Chapter 5 - Improved GAN


Wasserstein GAN (WGAN):

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter5-improved-gan/wgan-mnist-5.1.2.py


Least Squares GAN (LSGAN):

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter5-improved-gan/lsgan-mnist-5.2.1.py


Auxiliary Classfier GAN (ACGAN):

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter5-improved-gan/acgan-mnist-5.3.1.py


Chapter 6 - GAN with Disentangled Latent Representations


Information Maximizing GAN (InfoGAN):

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter6-disentangled-gan/infogan-mnist-6.1.1.py


Stacked GAN:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter6-disentangled-gan/stackedgan-mnist-6.2.1.py


Chapter 7 - Cross-Domain GAN


CycleGAN:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter7-cross-domain-gan/cyclegan-7.1.1.py


Chapter 8 - Variational Autoencoders (VAE)


VAE MLP MNIST:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter8-vae/vae-mlp-mnist-8.1.1.py


VAE CNN MNIST:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter8-vae/cvae-cnn-mnist-8.2.1.py


Conditional VAE and Beta VAE:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter8-vae/cvae-cnn-mnist-8.2.1.py


Chapter 9 - Deep Reinforcement Learning


Q-Learning:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter9-drl/q-learning-9.3.1.py


Q-Learning on Frozen Lake Environment:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter9-drl/q-frozenlake-9.5.1.py


DQN and DDQN on Cartpole Environment:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter9-drl/dqn-cartpole-9.6.1.py


Chapter 10 - Policy Gradient Methods


REINFORCE, REINFORCE with Baseline, Actor-Critic, A2C:

https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras/blob/master/chapter10-policy/policygradient-car-10.1.1.py


参考链接:

  • https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras


-END-

专 · 知

专知,专业可信的人工智能知识分发,让认知协作更快更好!欢迎登录www.zhuanzhi.ai,注册登录专知,获取更多AI知识资料!

欢迎微信扫一扫加入专知人工智能知识星球群,获取最新AI专业干货知识教程视频资料和与专家交流咨询

请加专知小助手微信(扫一扫如下二维码添加),加入专知人工智能主题群,咨询技术商务合作~

专知《深度学习:算法到实战》课程全部完成!550+位同学在学习,现在报名,限时优惠!网易云课堂人工智能畅销榜首位!

点击“阅读原文”,了解报名专知《深度学习:算法到实战》课程

展开全文
Top
微信扫码咨询专知VIP会员