# 使用 Keras 的用于 MNIST 的 LeNet CNN 让我们重新审视具有相同数据集的相同 LeNet 架构，以在 Keras 中构建和训练 CNN 模型： 1. 导入所需的 Keras 模块： ```py import keras from keras.models import Sequential from keras.layers import Conv2D,MaxPooling2D, Dense, Flatten, Reshape from keras.optimizers import SGD ``` 1. 定义每个层的过滤器数量： ```py n_filters=[32,64] ``` 1. 定义其他超参数： ```py learning_rate = 0.01 n_epochs = 10 batch_size = 100 ``` 1. 定义顺序模型并添加层以将输入数据重新整形为形状`(n_width,n_height,n_depth)`： ```py model = Sequential() model.add(Reshape(target_shape=(n_width,n_height,n_depth), input_shape=(n_inputs,)) ) ``` 1. 使用 4 x 4 内核过滤器，`SAME`填充和`relu`激活添加第一个卷积层： ```py model.add(Conv2D(filters=n_filters[0],kernel_size=4, padding='SAME',activation='relu') ) ``` 1. 添加区域大小为 2 x 2 且步长为 2 x 2 的池化层： ```py model.add(MaxPooling2D(pool_size=(2,2),strides=(2,2))) ``` 1. 以与添加第一层相同的方式添加第二个卷积和池化层： ```py model.add(Conv2D(filters=n_filters[1],kernel_size=4, padding='SAME',activation='relu') ) model.add(MaxPooling2D(pool_size=(2,2),strides=(2,2))) ``` 1. 添加层以展平第二个层的输出和 1024 个神经元的完全连接层，以处理展平的输出： ```py model.add(Flatten()) model.add(Dense(units=1024, activation='relu')) ``` 1. 使用`softmax`激活添加最终输出层： ```py model.add(Dense(units=n_outputs, activation='softmax')) ``` 1. 使用以下代码查看模型摘要： ```py model.summary() ``` 该模型描述如下： ```py Layer (type) Output Shape Param # ================================================================= reshape_1 (Reshape) (None, 28, 28, 1) 0 _________________________________________________________________ conv2d_1 (Conv2D) (None, 28, 28, 32) 544 _________________________________________________________________ max_pooling2d_1 (MaxPooling2 (None, 14, 14, 32) 0 _________________________________________________________________ conv2d_2 (Conv2D) (None, 14, 14, 64) 32832 _________________________________________________________________ max_pooling2d_2 (MaxPooling2 (None, 7, 7, 64) 0 _________________________________________________________________ flatten_1 (Flatten) (None, 3136) 0 _________________________________________________________________ dense_1 (Dense) (None, 1024) 3212288 _________________________________________________________________ dense_2 (Dense) (None, 10) 10250 ================================================================= Total params: 3,255,914 Trainable params: 3,255,914 Non-trainable params: 0 _________________________________________________________________ ``` 1. 编译，训练和评估模型： ```py model.compile(loss='categorical_crossentropy', optimizer=SGD(lr=learning_rate), metrics=['accuracy']) model.fit(X_train, Y_train,batch_size=batch_size, epochs=n_epochs) score = model.evaluate(X_test, Y_test) print('\nTest loss:', score[0]) print('Test accuracy:', score[1]) ``` 我们得到以下输出： ```py Epoch 1/10 55000/55000 [===================] - 267s - loss: 0.8854 - acc: 0.7631 Epoch 2/10 55000/55000 [===================] - 272s - loss: 0.2406 - acc: 0.9272 Epoch 3/10 55000/55000 [===================] - 267s - loss: 0.1712 - acc: 0.9488 Epoch 4/10 55000/55000 [===================] - 295s - loss: 0.1339 - acc: 0.9604 Epoch 5/10 55000/55000 [===================] - 278s - loss: 0.1112 - acc: 0.9667 Epoch 6/10 55000/55000 [===================] - 279s - loss: 0.0957 - acc: 0.9714 Epoch 7/10 55000/55000 [===================] - 316s - loss: 0.0842 - acc: 0.9744 Epoch 8/10 55000/55000 [===================] - 317s - loss: 0.0758 - acc: 0.9773 Epoch 9/10 55000/55000 [===================] - 285s - loss: 0.0693 - acc: 0.9790 Epoch 10/10 55000/55000 [===================] - 217s - loss: 0.0630 - acc: 0.9804 Test loss: 0.0628845927377 Test accuracy: 0.9785 ``` 准确性的差异可归因于我们在这里使用 SGD 优化器这一事实，它没有实现我们用于 TensorFlow 模型的`AdamOptimizer`提供的一些高级功能。