cs231n作业：Assignment1-Image features exercise

# Use the validation set to tune the learning rate and regularization strength

from cs231n.classifiers.linear_classifier import LinearSVM

learning_rates = [1e-9, 1e-8, 1e-7]
regularization_strengths = [5e4, 4e5,5e5,6e5, 5e6]

results = {}
best_val = -1
best_svm = None

################################################################################
# TODO:                                                                        #
# Use the validation set to set the learning rate and regularization strength. #
# This should be identical to the validation that you did for the SVM; save    #
# the best trained classifer in best_svm. You might also want to play          #
# with different numbers of bins in the color histogram. If you are careful    #
# you should be able to get accuracy of near 0.44 on the validation set.       #
################################################################################
# *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

pass

for lr in learning_rates:
    for reg in regularization_strengths:
        svm = LinearSVM()
        loss_hist = svm.train(X_train_feats,y_train,learning_rate=lr,reg=reg,num_iters=2500,batch_size=2000,verbose=True)
        y_train_pred = svm.predict(X_train_feats)
        y_val_pred = svm.predict(X_val_feats)
        
        rate1 = np.mean(y_train == y_train_pred)
        rate2 = np.mean(y_val == y_val_pred)
        
        results[(lr,reg)] = (rate1, rate2)
        
        if rate2 > best_val:
            best_val = rate2
            best_svm = svm

# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

# Print out results.
for lr, reg in sorted(results):
    train_accuracy, val_accuracy = results[(lr, reg)]
    print('lr %e reg %e train accuracy: %f val accuracy: %f' % (
                lr, reg, train_accuracy, val_accuracy))
    
print('best validation accuracy achieved during cross-validation: %f' % best_val)

图像经过特征提取之后的分类效果，比直接在原图像上进行计算效果要好。