Image Colorization using TensorFlow 2 and Keras

提供方
Coursera Project Network
在此指導項目中,您將:

Learn how to work with images in the .npy file format.

Learn how to create a custom CNN model.

Create an app to allow users to colorize black and white images using the model you trained.

Clock1 hour 30 minutes
Beginner初級
Cloud無需下載
Video分屏視頻
Comment Dots英語(English)
Laptop僅限桌面

This guided project is about image colorization using TensorFlow2 and Keras. Image colorization comes under the computer vision domain. In this project you will learn how to build a convolutional neural network(CNN) using Tensorflow2 and Keras. While you are watching me code, you will get a cloud desktop with all the required software pre-installed. This will allow you to code along with me. After all, we learn best with active, hands-on learning. Special Feature: 1) Explanation of the process of image colorization. 2) How to reshape data to fit a CNN. 3) Explanation of each layer in a CNN. 4) Create a Streamlit app to allow users to colorize a black and white image using the model you trained. Note: This project works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

您要培養的技能

  • Deep Learning
  • Convolutional Neural Network
  • Tensorflow
  • Streamlit
  • keras

分步進行學習

在與您的工作區一起在分屏中播放的視頻中,您的授課教師將指導您完成每個步驟:

  1. Preprocess grayscale images.

  2. Extract colors from colorful images to provide as inputs to the model.

  3. Build the CNN with TensorFlow2 and Keras.

  4. Save the model.

  5. Load the pre-trained model in a streamlit app.

指導項目工作原理

您的工作空間就是瀏覽器中的雲桌面,無需下載

在分屏視頻中,您的授課教師會為您提供分步指導

常見問題

常見問題

還有其他問題嗎?請訪問 學生幫助中心