原始論文中的網路結構如下圖:
keras生成的網路結構如下圖:
程式碼如下:
import numpy as np from keras.preprocessing import image from keras.models import Sequential from keras.layers import Dense, Dropout, Flatten, Activation from keras.layers import Conv2D, MaxPooling2D from keras.utils.vis_utils import plot_model from keras.utils import np_utils # 從資料夾影象與標籤檔案載入資料 def create_x(filenum, file_dir): train_x = [] for i in range(filenum): img = image.load_img(file_dir + str(i) + ".bmp", target_size=(28, 28)) img = img.convert('L') x = image.img_to_array(img) train_x.append(x) train_x = np.array(train_x) train_x = train_x.astype('float32') train_x /= 255 return train_x def create_y(classes, filename): train_y = [] file = open(filename, "r") for line in file.readlines(): train_y.append(int(line)) file.close() train_y = np.array(train_y).astype('float32') train_y = np_utils.to_categorical(train_y, classes) return train_y classes = 10 X_train = create_x(55000, './train/') X_test = create_x(10000, './test/') Y_train = create_y(classes, 'train.txt') Y_test = create_y(classes, 'test.txt') # 從網路下載的資料集直接解析資料 ''' from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets("MNIST/", one_hot=True) X_train, Y_train = mnist.train.images, mnist.train.labels X_test, Y_test = mnist.test.images, mnist.test.labels X_train = X_train.astype('float32') X_test = X_test.astype('float32') print(X_train.shape, X_test.shape) X_train = X_train.reshape(X_train.shape[0], 28, 28, 1) X_test = X_test.reshape(X_test.shape[0], 28, 28, 1) print(X_train[0]) ''' model = Sequential() model.add(Conv2D(filters=6, kernel_size=(5, 5), padding='valid', input_shape=(28, 28, 1), activation='tanh')) #C1 model.add(MaxPooling2D(pool_size=(2, 2))) #S2 model.add(Conv2D(filters=16, kernel_size=(5, 5), padding='valid', activation='tanh')) #C3 model.add(MaxPooling2D(pool_size=(2, 2))) #S4 model.add(Flatten()) model.add(Dense(120, activation='tanh')) #C5 model.add(Dense(84, activation='tanh')) #F6 model.add(Dense(10, activation='softmax')) #output model.summary() model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy']) history = model.fit(X_train, Y_train, batch_size=500, epochs=50, verbose=1, validation_data=(X_test, Y_test)) score = model.evaluate(X_test, Y_test, verbose=0) test_result = model.predict(X_test) result = np.argmax(test_result, axis=1) print(result) print('Test score:', score[0]) print('Test accuracy:', score[1]) plot_model(model, to_file='model.png', show_shapes=True, show_layer_names=False)
50次迭代,識別率在97%左右:
相關測試資料可以在這裡下載到。