練習 2：避免過度配適
在本練習中，您將透過資料擴增和隨機捨棄規則，改善您在練習 1 中建立的貓狗分類 CNN 模型：
機器學習實務：圖片分類
除非另有註明，否則本頁面中的內容是採用創用 CC 姓名標示 4.0 授權，程式碼範例則為阿帕契 2.0 授權。詳情請參閱《Google Developers 網站政策》。Java 是 Oracle 和/或其關聯企業的註冊商標。
上次更新時間：2025-07-27 (世界標準時間)。
[null,null,["上次更新時間：2025-07-27 (世界標準時間)。"],[[["\u003cp\u003eThis exercise focuses on enhancing a Convolutional Neural Network (CNN) model for cat-vs-dog image classification, building upon a previous exercise.\u003c/p\u003e\n"],["\u003cp\u003eThe enhancements involve implementing data augmentation techniques and dropout regularization to mitigate overfitting and improve model generalization.\u003c/p\u003e\n"],["\u003cp\u003eYou will actively apply these techniques in a provided coding exercise using Google Colab.\u003c/p\u003e\n"]]],[],null,["# ML Practicum: Image Classification\n\n\u003cbr /\u003e\n\n### Exercise 2: Preventing Overfitting\n\nIn this exercise, you'll improve the CNN model for cat-vs.-dog\nclassification you built in [Exercise 1](/machine-learning/practica/image-classification/exercise-1) by applying\ndata augmentation and dropout regularization: \n[Launch exercise](https://colab.research.google.com/github/google/eng-edu/blob/main/ml/pc/exercises/image_classification_part2.ipynb?utm_source=practicum-IC&utm_campaign=colab-external&utm_medium=referral&hl=en&utm_content=imageexercise2-colab)"]]