为什么MNIST CNN的预测出错？

Question

我在MNIST数据集上训练了CNN，训练和验证准确度为~0.99。

我按照Keras documentation of implementing CNN with MNIST dataset给出的示例中的确切步骤进行操作：

import cv2
import numpy as np
import tensorflow.keras as keras
import math

from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K

batch_size = 128
num_classes = 10
epochs = 12

# input image dimensions
img_rows, img_cols = 28, 28

# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()

if K.image_data_format() == 'channels_first':
    x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
    x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
    input_shape = (1, img_rows, img_cols)
else:
    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
    input_shape = (img_rows, img_cols, 1)

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
                activation='relu',
                input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss=keras.losses.categorical_crossentropy,
            optimizer=keras.optimizers.Adadelta(),
            metrics=['accuracy'])

model.fit(x_train, y_train,
        batch_size=batch_size,
        epochs=epochs,
        verbose=1,
        validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

当我测试下面的图像时：

使用以下测试代码：

img = cv2.imread("m9.png", 0)
img = cv2.resize(img, (28,28))
img = img / 255.


prob = model.predict_proba(img.reshape((1,28, 28, 1)))

print(prob)

model.predict_classes(img.reshape((1,28, 28, 1)))

它打印出来的类是array([1])，表示数字1。我无法理解它的原因。我是否试图以不正确的方式进行预测？

完全相同的类array([1])预测数量8如下所示：

看起来我在预测期间犯了错误？我试图了解可能发生的事情，但无法理解。

Answer 1

没有错误，只是你的图像看起来不像MNIST数据集中那些。该数据集不用于训练一般的数字识别算法，它只适用于类似的图像。

在您的情况下，28x28图像中的数字将非常小，因此预测是随机的。

Answer 2

您正在将输入图像的大小调整为28 X 28.而应首先裁剪数字周围的图像，使其看起来像MNIST中的数据集。否则，在调整大小的图像中，数字将占据非常小的部分并且结果将是任意的。