Python Optical Character Recognition using Pytorch

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

Learn about image processing and data preparation.

Learn how to build and train a convolutional network.

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

Note: The rhyme platform currently does not support webcams, so this is not a live project. This guided project is about optical character recognition using Pythorch, a Python library. This comes under the computer vision domain. 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. 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

  • Data Science
  • Deep Learning
  • Convolutional Neural Network
  • Python Programming
  • Computer Vision

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. Learn how to convert images to Tensors and about Image preprocessing.

  2. Learn how to build a Convolutional Neural Network and about one-hot encoding images.

  3. Learn how to set the optimizer and loss function for a model to get good results

  4. Learn how to train a Convolutional Neural Network to get the best accuracy.

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