Build and train a convolutional neural network (CNN) using Keras
Display results and plot 2D spectrograms with Python in Jupyter Notebook
Showcase this hands-on experience in an interview
In this 1-hour long project-based course, you will learn the basics of using Keras with TensorFlow as its backend and use it to solve an image classification problem. The data we are going to use consists of 2D spectrograms of deep space radio signals collected by the Allen Telescope Array at the SETI Institute. We will treat the spectrograms as images to train an image classification model to classify the signals into one of four classes. By the end of the project, you will have built and trained a convolutional neural network from scratch using Keras to classify signals from space. This course runs on Coursera's hands-on project platform called Rhyme. On Rhyme, you do projects in a hands-on manner in your browser. You will get instant access to pre-configured cloud desktops containing all of the software and data you need for the project. Everything is already set up directly in your internet browser so you can just focus on learning. For this project, you’ll get instant access to a cloud desktop with Python, Jupyter, and Tensorflow pre-installed. Notes: - You will be able to access the cloud desktop 5 times. However, you will be able to access instructions videos as many times as you want. - 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.
Prior Python programming experience and a theoretical understanding of convolutional neural networks is required.
Introduction and Import Libraries
Load and Preprocess SETI Data
Create Training and Validation Data Generators
Build the CNN Model
Learning Rate Scheduling and Compile the Model
Train the Model
Evaluate the Model
A very well-structured project. Surely, gave me a wonderful insight into building my own CNN. However, the cloud platform was lagging and slow. Could have been a better user experience.
Using the Rhyme platform is unstable. Some of the functions are not available for the student. Correcting the way the Rhyme platform jumps around is frustrating.
The explanations were elaborate and insightful. But the choice of hyperparams seemed to be arbitrary and no justification was provided for it.
Great course. Instructor knows the subject well and guides you through the material explaining each part. Thank you
我能直接通过 Web 浏览器来完成此指导项目，而不必安装特殊软件吗？