Keras is a neural network API written in Python and integrated with TensorFlow. You can learn how to use Keras in a new video course on the freeCodeCamp.org YouTube channel.

Keras是一个用Python编写并与TensorFlow集成的神经网络API。 您可以在freeCodeCamp.org YouTube频道的新视频课程中学习如何使用Keras

In this course from deeplizard, you will learn how to prepare and process data for artificial neural networks, build and train  artificial neural networks from scratch, build and train convolutional neural networks (CNNs), implement fine-tuning and transfer learning, and more.

Deeplizard的本课程中,您将学习如何准备和处理人工神经网络的数据,从头开始构建和训练人工神经网络,构建和训练卷积神经网络(CNN),实现微调和转移学习等。

Keras课程–学习Python深度学习和神经网络

Each section of the course focuses on a specific concept, and shows how the full implementation is done in code using Keras and Python.

本课程的每个部分都专注于一个特定的概念,并说明如何使用Keras和Python在代码中完成完整的实现。

You will learn to build some networks from scratch. Others will be pre-trained state-of-the-art models that you'll get to fine-tune to the data. Then you'll learn how to deploy models using both front-end and back-end deployment techniques.

您将学习从头开始构建一些网络。 其他将是经过预训练的最新模型,您将可以对数据进行微调。 然后,您将学习如何使用前端和后端部署技术来部署模型。

Here's the full course syllabus:

这是完整的课程提纲:

第1部分:人工神经网络基础 (Part 1: Artificial Neural Network Basics)

Section 1: Intro to Keras and neural networks

第1节:Keras和神经网络入门

  • Processing data

    处理数据

  • Building and training neural networks

    建立和训练神经网络

  • Validation and inference

    验证与推论

  • Saving and loading models

    保存和加载模型

Section 2: Convolutional Neural Networks (CNNs)

第2节:卷积神经网络(CNN)

  • Image processing

    图像处理

  • Building and training CNNs

    建立和培训CNN

  • Using CNNs for inference

    使用CNN进行推理

Section 3: Fine-tuning and transfer learning

第3节:微调和迁移学习

  • Intro to fine-tuning and VGG16 model

    微调和VGG16模型简介

  • Implement fine-tuning on VGG16 model

    在VGG16模型上实施微调

  • Using fine-tuned models for inference

    使用微调的模型进行推理

  • Intro to MobileNet

    MobileNet简介

  • Fine-tuning MobileNet on subset of data

    在数据子集上微调MobileNet

Section 4: Additional topics

第4节:其他主题

  • Data augmentation

    资料扩充

  • Keras' image labeling implementation

    Keras的图像标签实现

  • Achieving reproducible results

    实现可重复的结果

  • Learnable parameters

    可学习的参数

第2部分:神经网络模型部署 (Part 2: Neural network model deployment)

Section 1: Deployment with Flask

第1节:使用Flask进行部署

  • Introduction to Flask and web services

    Flask和Web服务简介

  • Build a simple Flask app and web app

    构建一个简单的Flask应用程序和Web应用程序

  • Send and receive data with Flask

    使用Flask发送和接收数据

  • Host neural network with Flask

    用Flask托管神经网络

  • Build neural network web app to interact with Flask service

    构建神经网络Web应用程序以与Flask服务进行交互

  • Integrating data visualization with D3, DC, Crossfilter

    将数据可视化与D3,DC,Crossfilter集成

  • Alternative ways to access neural network from Powershell and Curl

    从Powershell和Curl访问神经网络的替代方法

  • Information privacy and data protection

    信息隐私和数据保护

Section 2: Deployment with TensorFlow.js

第2节:使用TensorFlow.js进行部署

  • Introduction to client-side neural networks

    客户端神经网络简介

  • Convert Keras model to TFJS model

    将Keras模型转换为TFJS模型

  • Set up Node.js and Express

    设置Node.js和Express

  • Build UI for neural network web app

    为神经网络Web应用程序构建UI

  • Host a neural network with TFJS

    使用TFJS托管神经网络

  • Explore tensor operations through image processing

    通过图像处理探索张量操作

  • Examine tensor operations with debugger

    使用调试器检查张量操作

  • Broadcasting tensors

    广播张量

  • Efficiency of hosting MobileNet in the browser

    在浏览器中托管MobileNet的效率

You can watch the full course on the freeCodeCamp.org YouTube channel (3 hour watch).

您可以在freeCodeCamp.org YouTube频道上观看完整的课程 (观看3小时)。

翻译自: https://www.freecodecamp.org/news/keras-video-course-python-deep-learning/