Creating Multi Task Models With Keras

4.7
35 个评分
提供方
Coursera Project Network
1,508 人已注册
在此免费指导项目中,您将:

Creating multi-task models with Keras

Training multi-task models with Keras

在面试中展现此实践经验

Clock2 hours
Intermediate中级
Cloud无需下载
Video分屏视频
Comment Dots英语(English)
Laptop仅限桌面

In this 1 hour long guided project, you will learn to create and train multi-task, multi-output models with Keras. You will learn to use Keras' functional API to create a multi output model which will be trained to learn two different labels given the same input example. The model will have one input but two outputs. A few of the shallow layers will be shared between the two outputs, you will also use a ResNet style skip connection in the model. If you are familiar with Keras, you have probably come across examples of models that are trained to perform multiple tasks. For example, an object detection model where a CNN is trained to find all class instances in the input images as well as give a regression output to localize the detected class instances in the input. Being able to use Keras' functional API is a first step towards building complex, multi-output models like object detection models. We will be using TensorFlow as our machine learning framework. The project uses the Google Colab environment. You will need prior programming experience in Python. You will also need prior experience with Keras. Consider this to be an intermediate level Keras project. This is a practical, hands on guided project for learners who already have theoretical understanding of Neural Networks, Convolutional Neural Networks, and optimization algorithms like gradient descent but want to understand how to use use Keras to write custom, more complex models than just plain sequential neural networks. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

必备条件

Prior programming experience in Python. Conceptual understanding of Neural Networks. Prior experience with TensorFlow and Keras is recommended.

您要培养的技能

  • Deep Learning
  • Machine Learning
  • Tensorflow
  • Computer Vision
  • keras

分步进行学习

在与您的工作区一起在分屏中播放的视频中,您的授课教师将指导您完成每个步骤:

  1. Introduction

  2. Create Dataset

  3. Dataset Generator

  4. Create Model

  5. Train the Model

  6. Final Predictions

指导项目工作原理

您的工作空间就是浏览器中的云桌面,无需下载

在分屏视频中,您的授课教师会为您提供分步指导

审阅

来自CREATING MULTI TASK MODELS WITH KERAS的热门评论

查看所有评论

常见问题

常见问题

还有其他问题吗?请访问 学生帮助中心