作业介绍

• 作业主页：Assignment #1
• 作业目的：
  • 在之前的作业中，我们已经能够编写简单的分类器，接收原始RGB像素输入来进行分类，并且获得了不错的性能，本次作业中，我们将尝试使用从像素值中提取的稍微高级一点的特征（例如颜色直方图、HOG特征，SIFT特特征）来提升我们分类器的性能。
• 官方给的示例代码：assigment #1 code

1. 加载数据

from cs231n.features import color_histogram_hsv, hog_feature

def get_CIFAR10_data(num_training=49000, num_validation=1000, num_test=1000):
    # Load the raw CIFAR-10 data
    cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'

    X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
    
    # Subsample the data
    mask = list(range(num_training, num_training + num_validation))
    X_val = X_train[mask]
    y_val = y_train[mask]
    mask = list(range(num_training))
    X_train = X_train[mask]
    y_train = y_train[mask]
    mask = list(range(num_test))
    X_test = X_test[mask]
    y_test = y_test[mask]
    
    return X_train, y_train, X_val, y_val, X_test, y_test

# Cleaning up variables to prevent loading data multiple times (which may cause memory issue)
try:
   del X_train, y_train
   del X_test, y_test
   print('Clear previously loaded data.')
except:
   pass

X_train, y_train, X_val, y_val, X_test, y_test = get_CIFAR10_data()

2. 提取特征

• 我们将提取HOG（方向梯度特征），其更注重图像的纹理特征，而忽略图像的颜色特征
• 而且，我们也会提取HSV 色彩空间的 H 颜色通道的颜色直方图（color histogram）特征，其更加注重颜色特征
• 最后，我们将两个特征联合起来（concatenation）。
• fearture.py中hog_feature提取HOG特征，color_histogram_hsv提取颜色直方图，它们都作用于一张图像，并返回一个维特征向量
• extract_features(imgs, feature_fns, verbose=False) 输入多个图像imgs和多个特征提取函数feature_fns，然后返回多个图像的特征，每个图像占一行，然后每行的特征就是多个特征提取函数的特征联合起来

from cs231n.features import *

num_color_bins = 10 # Number of bins in the color histogram
feature_fns = [hog_feature, lambda img: color_histogram_hsv(img, nbin=num_color_bins)]
X_train_feats = extract_features(X_train, feature_fns, verbose=True)
X_val_feats = extract_features(X_val, feature_fns)
X_test_feats = extract_features(X_test, feature_fns)

# Preprocessing: Subtract the mean feature
mean_feat = np.mean(X_train_feats, axis=0, keepdims=True)
X_train_feats -= mean_feat
X_val_feats -= mean_feat
X_test_feats -= mean_feat

# Preprocessing: Divide by standard deviation. This ensures that each feature
# has roughly the same scale.
std_feat = np.std(X_train_feats, axis=0, keepdims=True)
X_train_feats /= std_feat
X_val_feats /= std_feat
X_test_feats /= std_feat

# Preprocessing: Add a bias dimension
X_train_feats = np.hstack([X_train_feats, np.ones