Keras + mnist + 测试自己的图像。错误的预测

通过测试 mnist 自己的测试图像，它工作得很好，但是一旦我使用来自外部 mnist 的图像，它就会预测错误。我什至尝试从 mnist 数据集中复制其中一张图像，但它仍然无法预测正确的数字（即使在 mnist 数据集中完全相同的图像是可以（预测）的）。

有人能看到我做错了什么吗？我猜图像的尺寸或形状有些问题。

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import Dense, Conv2D, Dropout, Flatten, MaxPooling2D
import cv2 as cv

(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()

x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)
x_test = x_test.reshape(x_test.shape[0], 28, 28, 1)
input_shape = (28, 28, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
# Normalizing the RGB codes by dividing it to the max RGB value.
x_train /= 255
x_test /= 255

# -------------------------- CREATE MODEL ------------------------------
'''
model = Sequential()
model.add(Conv2D(28, kernel_size=(3,3), input_shape=input_shape))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten()) # Flattening the 2D arrays for fully connected layers
model.add(Dense(128, activation=tf.nn.relu))
model.add(Dropout(0.2))
model.add(Dense(10,activation=tf.nn.softmax))

# ----------------------------------------------------------------------

model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])
model.fit(x=x_train,y=y_train, epochs=1)

# ----------------------------------------------------------------------
'''
model = tf.keras.models.load_model("C:/Users/A551110/PycharmProjects/keras_mnist/venv/mnistv2.model")
file = "C:/Users/A551110/Documents/images/7.png"
model.evaluate(x_test, y_test)

image = cv.imread(file, cv.IMREAD_GRAYSCALE)
image = cv.resize(image, (28,28))
image = 255-image          #inverts image. Always gets read inverted.

plt.imshow(image.reshape(28, 28),cmap='Greys')
plt.show()
pred = model.predict(image.reshape(1, 28, 28, 1), batch_size=1)

print(pred.argmax())

我试过了pred = model.predict(image.reshape(1, 28, 28, 1)),

也pred = model.predict_classes(image.reshape(1, 28, 28, 1))

我预测的数字。 mnist 数据集中的上一张（预测正确）和下一张复制并放入（预测错误） https://i.stack.imgur.com/cBPLN.png

我想到了。我没有用这段代码得到正确的标准化值。

image = cv.imread(file, cv.IMREAD_GRAYSCALE)
image = cv.resize(image, (28,28))
image = 255-image     

相反，我必须用底部的划分（这里在底部）来纠正它，我错误地把它放在了图像 = 255-图像在早期的尝试中。这是错误之一，同时还缺少将类型转换为float32这使得正常化以及其间的重塑成为可能。

image = cv.imread(file, cv.IMREAD_GRAYSCALE)
image = cv.resize(file, (28, 28))
image = image.astype('float32')
image = image.reshape(1, 28, 28, 1)
image = 255-image
image /= 255