train_cnn_v2.py

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from utils import draw_train
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.optimizers import Adam
from keras.layers.normalization import BatchNormalization
from keras.utils import np_utils
from keras.layers import Conv2D, MaxPooling2D
from keras.preprocessing.image import ImageDataGenerator
from sklearn.model_selection import train_test_split
# 参数设置
batch_size=128
n_classes=10
n_epochs=20

img_rows=28
img_cols=28

# 加载数据
data = np.load('input/TibetanMNIST.npz')
X, y = data['image'], data['label']  # (17768, 28, 28)
X = X.reshape(X.shape[0], img_rows,img_cols,1).astype('float32') / 255
X_train, X_test, y_train, y_test_ = train_test_split(X, y, random_state=42)
y_train = np_utils.to_categorical(y_train, num_classes=10)
y_test = np_utils.to_categorical(y_test_, num_classes=10)

# 构建模型
model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=(28,28,1)))
model.add(Activation('relu'))
BatchNormalization(axis=-1)
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2)))

BatchNormalization(axis=-1)
model.add(Conv2D(64,(3, 3)))
model.add(Activation('relu'))
BatchNormalization(axis=-1)
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2)))

model.add(Flatten())

BatchNormalization()
model.add(Dense(512))
model.add(Activation('relu'))
BatchNormalization()
model.add(Dropout(0.2))
model.add(Dense(10))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', optimizer=Adam(), metrics=['accuracy'])
model.summary()

# 训练模型
gen = ImageDataGenerator(rotation_range=8, width_shift_range=0.08, shear_range=0.3,
                         height_shift_range=0.08, zoom_range=0.08)
test_gen = ImageDataGenerator()
train_generator = gen.flow(X_train, y_train, batch_size=64)
test_generator = test_gen.flow(X_test, y_test, batch_size=64)
history=model.fit_generator(train_generator, steps_per_epoch=60000//64, epochs=20,
                    validation_data=test_generator, validation_steps=10000//64)

# 评估模型
evaluation=model.evaluate(X_test,y_test)
print('Summary: Loss over the test dataset: %.4f, Accuracy: %.4f' % (evaluation[0], evaluation[1]))
draw_train(history)


predicted_classes = model.predict_classes(X_test)
correct_indices = np.nonzero(predicted_classes == y_test_)[0]
incorrect_indices = np.nonzero(predicted_classes != y_test_)[0]

plt.figure()
for i, correct in enumerate(correct_indices[:9]):
    plt.subplot(3, 3, i + 1)
    plt.imshow(X_test[correct].reshape(28, 28), cmap='gray', interpolation='none')
    plt.title("Predicted {}, Class {}".format(predicted_classes[correct], y_test_[correct]))
plt.show()

plt.figure()
for i, incorrect in enumerate(incorrect_indices[:9]):
    plt.subplot(3, 3, i + 1)
    plt.imshow(X_test[incorrect].reshape(28, 28), cmap='gray', interpolation='none')
    plt.title("Predicted {}, Class {}".format(predicted_classes[incorrect], y_test_[incorrect]))
plt.show()