Explainable AI: Scene Classification and GradCam Visualization

4.7
46 個評分
提供方
Coursera Project Network
2,102 人已註冊
在此指導項目中,您將:

Understand the theory and intuition behind Deep Neural Networks, Residual Nets, and Convolutional Neural Networks (CNNs)

Build a deep learning model based on Convolutional Neural Network and Residual blocks using Keras with Tensorflow 2.0 as a backend

Visualize the Activation Maps used by CNN to make predictions using Grad-CAM and Deploy the trained model using Tensorflow Serving

Clock2 hours
Intermediate中級
Cloud無需下載
Video分屏視頻
Comment Dots英語(English)
Laptop僅限桌面

In this 2 hour long hands-on project, we will train a deep learning model to predict the type of scenery in images. In addition, we are going to use a technique known as Grad-Cam to help explain how AI models think. This project could be practically used for detecting the type of scenery from the satellite images.

您要培養的技能

  • Deep Learning
  • Machine Learning
  • Python Programming
  • Artificial Intelligence(AI)
  • 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. Understand the theory and intuition behind Deep Neural Networks, Residual Nets, and Convolutional Neural Networks (CNNs)

  2. Apply Python libraries to import, pre-process and visualize images

  3. Perform data augmentation to improve model generalization capability

  4. Build a deep learning model based on Convolutional Neural Network and Residual blocks using Keras with Tensorflow 2.0 as a backend

  5. Compile and fit Deep Learning model to training data

  6. Assess the performance of trained CNN and ensure its generalization using various KPIs such as accuracy, precision and recall

  7. Understand the theory and intuition behind GradCam and Explainable AI

  8. Visualize the Activation Maps used by CNN to make predictions using Grad-CAM

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

審閱

來自EXPLAINABLE AI: SCENE CLASSIFICATION AND GRADCAM VISUALIZATION 的熱門評論

查看所有評論

常見問題

常見問題

還有其他問題嗎?請訪問 學生幫助中心