1.执行预测
prediction = model.predict_classes(x_img_test_normalize)
2.预测结果
print(prediction[:10]) [3 8 8 0 6 6 1 6 3 1]
3.查看预测概率
（1）使用测试数据进行预测
我们使用model.predict输入测试数据，就可以预测概率
Predicted_Probability = model.predict(x_img_test_normalize)
（2）建立show_Predicted_Probability函数
def show_Predicted_Probability(y, prediction, x_img, Predicted_Probability, i):
print('label:', label_dict[y[i][0]], 'predict', label_dict[prediction[i]])
plt.figure(figsize=(2, 2))
plt.imshow(np.reshape(x_img_test[i], (32, 32, 3)))
plt.show()
for j in range(10):
print(label_dict[j] + ' probability:%1.9f' % (Predicted_Probability[i][j]))
（3）查看第1项数据的预测结果
label: cat predict cat airplane probability:0.002762204 automobile probability:0.003279740 bird probability:0.010363355 cat probability:0.625037074 deer probability:0.012193166 dog probability:0.292445958 frog probability:0.034173731 horse probability:0.001061088 ship probability:0.017909575 truck probability:0.000774055
（3）查看第3项数据的预测结果
label: airplane predict airplane airplane probability:0.649241984 automobile probability:0.002572708 bird probability:0.041379604 cat probability:0.002955899 deer probability:0.021011690 dog probability:0.000034731 frog probability:0.000030690 horse probability:0.000025793 ship probability:0.281421483 truck probability:0.001325390
4.显示混淆矩阵
{0: 'airplane', 1: 'automobile', 2: 'bird', 3: 'cat', 4: 'deer', 5: 'dog', 6: 'frog', 7: 'horse', 8: 'ship', 9: 'truck'}
predict 0 1 2 3 4 5 6 7 8 9
label
0 795 8 67 8 18 5 18 4 52 25
1 23 811 20 5 5 6 22 3 39 66
2 47 1 641 22 112 60 85 15 10 7
3 18 10 109 431 84 191 121 19 9 8
4 21 3 72 32 770 19 64 10 8 1
5 10 2 66 109 69 656 59 20 5 4
6 5 1 35 26 24 17 887 2 2 1
7 15 0 57 15 121 65 12 701 4 10
8 43 17 25 5 13 8 13 0 858 18
9 37 70 25 10 6 7 12 10 25 798