Keras + mnist + 测试自己的图像。糟糕的预测

Question

通过测试 mnist 自己的测试图像可以正常工作，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，完全相同的图像也可以（预测））。

有人能看出我做错了什么吗？我猜图片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pred = model.predict(image.reshape(1, 28, 28, 1))，

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

The digits i was predicting. Upper one from mnist dataset (predicted correctly) and one lower one copied and put in (predicted wrongly)

Answer 1

import cv2
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np

y=cv2.imread("/content/download.png")   #image outside mnist data
y1=cv2.resize(y,(28,28))                #you need to resize it on the bsis pf your  modeL's image shape
plt.imshow(y1)

temp = cv2.cvtColor(y1,cv2.COLOR_BGR2YCrCb)  #since its a three channel image i hav econverted into this so rbg are represented in the luminance one 
temp=255-temp                                #negative image
plt.imshow(temp)

print(temp.shape)

Y = np.zeros((temp.shape[0], temp.shape[1],1), dtype=float)    #array of (28,28,1)
Y[:,:,0] = temp[:, :,0].astype(float) / 255           #fitting the data of temp image in that zeros and normalizing it
yh= model.predict_classes(Y.reshape(1,28,28,1))       #finally the value of image
yh

Answer 2

我想通了。我没有通过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，我不得不用底部的除法来纠正它（这里在底部），我在之前的尝试中错误地把它放在了 image = 255-image 之前。这是错误之一，以及缺少将类型转换为 float32 以使其能够正常化，以及中间的重塑。

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

Answer 3

一些猜测

1) 您对训练和测试数据进行了标准化。我假设您可能忘记在进行预测之前对输入数据进行标准化？

x_train /= 255
x_test /= 255

2) 您是否验证模型已正确加载？保存和加载后，验证它在测试集上仍然执行相同的操作。如果结果不好，说明权重没有正确加载。

3) tf.keras.datasets.mnist.load_data() 提供的数据集是否有任何预处理（在您自己的规范化之外）？如果是这样，您必须在推理之前使用相同的转换对自己的输入数据进行预处理