import numpy as np import tensorflow as tf from keras.preprocessing.image import ImageDataGenerator import os from PIL import Image from keras.utils import to_categorical from sklearn.model_selection import train_test_split from keras.models import Sequential from keras.layers import Conv2D, MaxPooling2D, Flatten, Dense

img_x = 64 img_y = 64

对读取图片进行预处理

def read_image(imageName): img = Image.open(imageName) img = img.resize((img_x, img_y), Image.ANTIALIAS) number_data = img.getdata() number_data_array = np.array(number_data) number_data_array = number_data_array.astype(float) number_data_normalize = number_data_array / 255

return number_data_normalize

images = [] labels = []

path = os.listdir("./mgh")

for textPath in path: for fn in os.listdir(os.path.join('mgh', textPath)): if fn.endswith('.jpg'): fd = os.path.join('./mgh', textPath, fn) images.append(read_image(fd)) labels.append(textPath) X = np.array(images) y = np.array(labels)

label_mapping = {label: i for i, label in enumerate(np.unique(y))} y = np.array([label_mapping[label] for label in y])

x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=30)

Reshape the data to fit the model

x_train = x_train.reshape(x_train.shape[0], img_x, img_y, 1) x_test = x_test.reshape(x_test.shape[0], img_x, img_y, 1)

Convert labels to categorical

y_train = to_categorical(y_train) y_test = to_categorical(y_test)

Create the model

model = Sequential() model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(img_x, img_y, 1))) model.add(MaxPooling2D((2, 2))) model.add(Conv2D(64, (3, 3), activation='relu')) model.add(MaxPooling2D((2, 2))) model.add(Flatten()) model.add(Dense(64, activation='relu')) model.add(Dense(2, activation='softmax'))

Compile the model

model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

Train the model

model.fit(x_train, y_train, epochs=10, batch_size=32, validation_data=(x_test, y_test))

Evaluate the model

_, accuracy = model.evaluate(x_test, y_test) print('Accuracy: %.2f' % (accuracy100)) _, val_accuracy = model.evaluate(x_test, y_test) print('Validation Accuracy: %.2f' % (val_accuracy100)