深度学习-卷积神经网络

* 数据来源手写数据（kersa）
* 方法：卷积神经网络
* 评估准确率

# 构建卷积层
from keras import layers
from keras import models
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)))
# 这里的Conv2D对输入数据进行卷积，输出的为3D的张量
model.add(layers.MaxPooling2D((2, 2)))
# MaxPooling2D与上述类似
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))

Using TensorFlow backend.

# 添加常规的密集神经网络部分
model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10, activation='softmax'))
# 通过summary来查看构建的卷积神经网络
model.summary()

Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #
=================================================================
conv2d_1 (Conv2D)            (None, 26, 26, 32)        320
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 13, 13, 32)        0
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 11, 11, 64)        18496
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 5, 5, 64)          0
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 3, 3, 64)          36928
_________________________________________________________________
flatten_1 (Flatten)          (None, 576)               0
_________________________________________________________________
dense_1 (Dense)              (None, 64)                36928
_________________________________________________________________
dense_2 (Dense)              (None, 10)                650
=================================================================
Total params: 93,322
Trainable params: 93,322
Non-trainable params: 0
_________________________________________________________________

# 带入数据进行运算
# 这部分内容与之前的文章类似
from keras.datasets import mnist
from keras.utils import to_categorical
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()
train_images = train_images.reshape((60000, 28, 28, 1))
train_images = train_images.astype('float32') / 255
test_images = test_images.reshape((10000, 28, 28, 1))
test_images = test_images.astype('float32') / 255
train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)
model.compile(optimizer='rmsprop',
                loss='categorical_crossentropy',
                metrics=['accuracy'])
model.fit(train_images, train_labels, epochs=5, batch_size=64)

Epoch 1/5
60000/60000 [==============================] - 7s 111us/step - loss: 0.1603 - accuracy: 0.9502
Epoch 2/5
60000/60000 [==============================] - 6s 106us/step - loss: 0.0447 - accuracy: 0.9857
Epoch 3/5
60000/60000 [==============================] - 6s 103us/step - loss: 0.0308 - accuracy: 0.9900
Epoch 4/5
60000/60000 [==============================] - 6s 105us/step - loss: 0.0240 - accuracy: 0.9926
Epoch 5/5
60000/60000 [==============================] - 6s 103us/step - loss: 0.0190 - accuracy: 0.9940





<keras.callbacks.callbacks.History at 0x7f951c0e1390>

# 在测试集评估
test_loss, test_acc = model.evaluate(test_images, test_labels)
test_acc

10000/10000 [==============================] - 0s 48us/step





0.9894000291824341