CIFAR-10

CIFAR10_SVM_glay.py

import numpy as np
import matplotlib.pyplot as plt
from keras.datasets import cifar10
from sklearn.svm import LinearSVC
import time

start_time = time.time()
# データの読み込み
(x_train_origin, y_train), (x_test_origin, y_test) = cifar10.load_data()
# 小数化
x_train_origin = x_train_origin / 255
x_test_origin = x_test_origin / 255
# データ数
m_train, m_test = x_train_origin.shape[0], x_test_origin.shape[0]
# グレースケール化
def to_grayscale(tensor):
    # https://ja.wikipedia.org/wiki/%E3%82%B0%E3%83%AC%E3%83%BC%E3%82%B9%E3%82%B1%E3%83%BC%E3%83%AB#%E8%BC%9D%E5%BA%A6%E4%BF%9D%E5%AD%98%E5%A4%89%E6%8F%9B
    # Y = 0.2126R + 0.7152G + 0.0722B
    return 0.2126*tensor[:, :, :, 0] + 0.7152*tensor[:, :, :, 1] + 0.0722*tensor[:, :, :, 2]
x_train, x_test = to_grayscale(x_train_origin), to_grayscale(x_test_origin)
print(x_train.shape) #(50000, 32, 32)
#plt.imshow(x_train[0], cmap="gray")
#plt.show()
# ベクトル化
x_train, x_test = x_train.reshape(m_train, -1), x_test.reshape(m_test, -1)
# ノルムで標準化
x_train = x_train / np.linalg.norm(x_train, ord=2, axis=1, keepdims=True)
x_test = x_test / np.linalg.norm(x_test, ord=2, axis=1, keepdims=True)

# サポートベクトルマシン
svc = LinearSVC()
svc.fit(x_train, y_train)
print("Elapsed[s] : ", time.time() - start_time)
print("Train :", svc.score(x_train, y_train))
print("Test :", svc.score(x_test, y_test))

#Elapsed[s] :  91.28059148788452
#Train : 0.3313
#Test : 0.2901