cs231n assignment1 features

最新推荐文章于 2021-08-02 16:33:56 发布

一叶知秋Autumn

最新推荐文章于 2021-08-02 16:33:56 发布

阅读量1.8k

点赞数

分类专栏：计算机视觉 CS231N 文章标签：计算机视觉

本文链接：https://blog.csdn.net/SpicyCoder/article/details/96323584

版权

features

前几个作业都是直接将图片的原始像素作为模型输入，本次作业是通过使用定向梯度直方图Histogram of Oriented Gradients (HOG)和HSV颜色空间。简单说，HOG不考虑图片的颜色信息，只捕获图片的纹理；而颜色直方图只考虑颜色，不考虑纹理。使用这两个方法一起工作，效果会更好。

Train SVM on features
learning_rates = [0.8e-7,1e-7,1.2e-7,1.4e-7]
regularization_strengths = [5e4,5.1e4]

for lr in learning_rates:
    for rs in regularization_strengths:
        svm = LinearSVM()
        loss_history = svm.train(X_train_feats,y_train,learning_rate=lr,reg=rs,num_iters=1000)
        train_pred = svm.predict(X_train_feats)
        train_acc = np.mean(train_pred == y_train)
        val_pred = svm.predict(X_val_feats)
        val_acc = np.mean(val_pred == y_val)
        if val_acc > best_val:
            best_val = val_acc
            best_svm