文件名称：Python-Deep-Learning-Cookbook:Packt出版的《 Python深度学习食谱》
文件大小：5.71MB
文件格式：ZIP
更新时间：2024-06-17 05:33:50
JupyterNotebook
Python深度学习食谱 这是发布的的代码库。 它包含从头到尾完成本书所必需的所有支持项目文件。 关于这本书 深度学习正在彻底改变各种行业。 在许多应用中，深度学习已被证明可以做出更快，更准确的预测，从而胜过人类。 本书提供了自上而下和自下而上的方法，以演示针对不同领域的现实问题的深度学习解决方案。 这些应用程序包括计算机视觉，自然语言处理，时间序列和机器人技术。 Python深度学习食谱提供了针对所提出问题的技术解决方案，以及对解决方案的详细说明。 此外，提供了有关使用诸如TensorFlow，PyTorch，Keras和CNTK的流行框架之一实施建议的解决方案的利弊的讨论。 这本书包括与神经网络的基本概念有关的食谱。 所有技术以及经典网络拓扑。 本书的主要目的是为Python程序员提供详细的配方列表，以将深度学习应用于常见和不常见的场景。 说明和导航 所有代码都组织在文件夹中。 每个
【文件预览】：
Python-Deep-Learning-Cookbook-master
----Chapter05()
--------Chapter 5 - Implementing a deep Q-learning algorithm.ipynb(49KB)
--------Chapter 5 - Implementing policy gradients.ipynb(139KB)
----Chapter04()
--------Chapter 4 - Implementing bidirectional RNNs.ipynb(9KB)
--------Chapter 4 - Using gated recurrent units (GRUs).ipynb(8KB)
--------Chapter 4 - Implementing a simple RNN.ipynb(5KB)
--------Chapter 4 - Character-level text generation.ipynb(11KB)
--------Chapter 4 - Adding Long Short-Term Memory (LSTM).ipynb(8KB)
--------Chapter 4 - Adding attention.ipynb(22KB)
----Chapter02()
--------Chapter 2 - Understanding the Perceptron.ipynb(31KB)
--------Chapter 2 - Adding dropout to prevent overfitting.ipynb(6KB)
--------Chapter 2 - Implementing an autoencoder.ipynb(54KB)
--------Chapter 2 - Improving generalization with regularization.ipynb(6KB)
--------Chapter 2 - Implementing a single-layer neural network.ipynb(21KB)
--------Chapter 2 - Getting started with activation functions.ipynb(54KB)
--------Chapter 2 - Tuning the loss function.ipynb(6KB)
--------Chapter 2 - Building a multi-layer neural network.ipynb(19KB)
--------Chapter 2 - Experiment with hidden layers and hidden units.ipynb(41KB)
--------Chapter 2 - Experimenting with different optimizers.ipynb(8KB)
----README.md(3KB)
----Chapter10()
--------Chapter 10 - Predicting stock prices with neural networks.ipynb(5KB)
--------Chapter 10 - Using a shallow neural network for binary classification.ipynb(9KB)
--------Chapter 10 - Predicting bike sharing demand.ipynb(5KB)
----Chapter06()
--------Chapter 6 - Understanding GANs.ipynb(5KB)
--------Chapter 6 - Upscaling the resolution of images with Super-Resolution GANs (SRGANs).ipynb(13KB)
--------Chapter 6 - Implementing Deep Convolutional GANs (DCGANs) .ipynb(2.04MB)
----Chapter11()
--------Chapter 11 - Learning to play games with deep reinforcement learning.ipynb(11KB)
--------Chapter 11 - Learning to drive a car with end-to-end learning.ipynb(8KB)
--------Chapter 11 - Genetic Algorithm (GA) to optimize hyperparameters.ipynb(9KB)
----LICENSE(1KB)
----Chapter07()
--------Chapter 7 - Segmenting classes in images with U-net.ipynb(112KB)
--------Chapter 7 - Augmenting images with computer vision techniques.ipynb(5KB)
--------Chapter 7 - Recognizing faces.ipynb(261KB)
--------Chapter 7 - Transferring styles to images.ipynb(3.36MB)
--------Chapter 7 - Scene understanding (semantic segmentation).ipynb(14KB)
--------Chapter 7 - Localizing an object in images.ipynb(8KB)
--------Chapter 7 - Classifying objects in images.ipynb(7KB)
--------Chapter 7 - Finding facial key points.ipynb(218KB)
----Chapter09()
--------Chapter 9 - Implementing a speech recognition pipeline from scratch.ipynb(5KB)
--------Chapter 9 - Understanding videos with deep learning.ipynb(6KB)
--------Chapter 9 - Identifying speakers with voice recognition.ipynb(5KB)
----Chapter14()
--------Chapter 14 - Large-scale visual recognition with GoogLeNet_Inception.ipynb(2KB)
--------Chapter 14 - Extracting bottleneck features with ResNet.ipynb(2KB)
--------Chapter 14 - Leveraging pretrained VGG models for new classes.ipynb(4KB)
--------Chapter 14 - Fine-tuning with Xception.ipynb(4KB)
----Chapter08()
--------Chapter 8 - Analyzing sentiment.ipynb(5KB)
--------Chapter 8 - Summarizing text.ipynb(8KB)
--------Chapter 8 - Translating sentences.ipynb(10KB)
----Chapter12()
--------Chapter 12 - Comparing optimizers.ipynb(5KB)
--------Chapter 12 - Working with batches and mini-batches.ipynb(4KB)
--------Chapter 12 - Adding dropouts to prevent overfitting.ipynb(6KB)
--------Chapter 12 - Learning rates and learning rate schedulers.ipynb(4KB)
--------Chapter 12 - Using grid search for parameter tuning.ipynb(5KB)
--------Chapter 12 - Making a model more robust with data augmentation.ipynb(4KB)
--------Chapter 12 - Visualizing training with TensorBoard and Keras.ipynb(4KB)
----Chapter13()
--------Chapter 13 - Storing the network topology and trained weights.ipynb(7KB)
--------Chapter 13 - Visualizing training with TensorBoard.ipynb(12KB)
--------Chapter 13 - Analyzing network weights and more.ipynb(8KB)
--------Chapter 13 - Freezing layers.ipynb(6KB)
----Chapter01()
--------Chapter 1 - Using PyTorchGÇÖs dynamic computation graphs for RNNs.ipynb(3KB)
--------Chapter 1 - Building efficient models with MXNet.ipynb(3KB)
--------Chapter 1 - Intuitively building networks with Keras .ipynb(4KB)
--------Chapter 1 - Implementing high-performance models with CNTK.ipynb(2KB)
--------Chapter 1 - Building state-of-the-art, production-ready models with TensorFlow.ipynb(3KB)
--------Chapter 1 - Defining networks using simple and efficient code with Gluon.ipynb(2KB)
----Chapter03()
--------Chapter 3 - Optimizing with batch normalization.ipynb(47KB)
--------Chapter 3 - Experimenting with different types of initialization.ipynb(63KB)
--------Chapter 3 - Getting started with filters and parameter sharing.ipynb(35KB)
--------Chapter 3 - Understanding padding and strides.ipynb(1.12MB)
--------Chapter 3 - Applying a 1D CNN to text.ipynb(9KB)
--------Chapter 3 - Applying pooling layers.ipynb(11KB)
--------Chapter 3 - Implementing a convolutional autencoder.ipynb(165KB)