我一直在为我的学校项目开发一个识别数字的程序 . 为此，我使用了Python，Keras和MNIST数据集 . 这是我用来训练它的代码：

import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Convolution2D, MaxPooling2D, Activation, AveragePooling2D
from keras import backend as K
import matplotlib.pyplot as plt
import matplotlib

batch_size = 32
num_classes = 10
epochs = 10

img_rows, img_cols = 28, 28

(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')

y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)


model = Sequential()
model.add(Convolution2D(6, (5, 5), input_shape=input_shape))
model.add(Activation('sigmoid'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(12, (5, 5)))
model.add(Activation('sigmoid'))
model.add(AveragePooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(192))
model.add(Dense(10))
model.add(Activation('sigmoid'))
model.add(Dense(10))
model.add(Activation('softmax'))

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

hist = 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])

model.save('model3.h5')

train_loss = hist.history['loss']
val_loss = hist.history['val_loss']
train_acc = hist.history['acc']
val_acc = hist.history['val_acc']
xc = range(epochs)

plt.figure(1,figsize=(7,5))
plt.plot(xc,train_loss)
plt.plot(xc,val_loss)
plt.xlabel('num of Epochs')
plt.ylabel('loss')
plt.title('train_loss vs val_loss')
plt.grid(True)
plt.legend(['train','val'])
print(plt.style.available) # use bmh, classic,ggplot for big pictures
plt.style.use(['classic'])

plt.figure(2,figsize=(7,5))
plt.plot(xc,train_acc)
plt.plot(xc,val_acc)
plt.xlabel('num of Epochs')
plt.ylabel('accuracy')
plt.title('train_acc vs val_acc')
plt.grid(True)
plt.legend(['train','val'],loc=4)
#print plt.style.available # use bmh, classic,ggplot for big pictures
plt.style.use(['classic'])

plt.show()

我将模型保存在名称model3.h5下 . 然而，在我写的另一个程序中，我试图用模型预测我保存了我在Paint中输入的数字 . 我有10张照片（0-9）并且预测模型预测所有数字都是8号，这当然是错误的 . 但是，在训练期间，准确率接近98.5％，损失小于0.1 . 难道我做错了什么？

这是我运行的代码，用于在看不见的数据上进行预测 . 它将图片大小调整为28列和28行，以便它可以在我的CNN上运行 .

这是我关于卷积神经网络的第一个项目，我不知道“一些额外的技术”可以帮助我在看不见的数据上做得更好 .

我也尝试了一些不同的架构（使用最大池和relu激活函数进行卷积层，然后添加完整连接层）但结果仍然相同 . 我也尝试将它设置为100或200个时代，仍然没有用...

import os, cv2
import numpy as np
import matplotlib.pyplot as plt

from sklearn.utils import shuffle
from sklearn.model_selection import train_test_split

from keras import backend as K
from keras.models import load_model

K.set_image_dim_ordering('tf')

from keras.utils import np_utils
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.optimizers import SGD,RMSprop,adam

PATH = os.getcwd()
data_path = PATH + '\myNumbers'
data_dir_list = os.listdir(data_path) #direktoriji unutra

img_data = []

for file in data_dir_list:
    test_image = cv2.imread(data_path + "\\" + file)
    test_image = cv2.cvtColor(test_image, cv2.COLOR_RGB2GRAY)
    test_image = cv2.resize(test_image,(28,28))
    test_image = np.array(test_image)
    test_image = test_image.astype('float32')
    test_image /= 255
    print (test_image.shape)

    test_image= np.expand_dims(test_image, axis=3)
    test_image= np.expand_dims(test_image, axis=0)
    print (test_image.shape)
    img_data.append(test_image)

model = load_model("model3.h5")

for img in img_data:
    print(model.predict(img))
    print(model.predict_classes(img))
machine-learning neural-network keras conv-neural-network mnist