卷积神经网络

• 模型

import tensorflow as tf
print(tf.__version__)
from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint
from tensorflow.keras.models import load_model

# 回调函数
filepath = 'best_model.h5'
callbacks_list = [
  EarlyStopping(
  monitor='val_acc',
  patience=3,
  ),
  ModelCheckpoint(
  filepath=filepath,
  monitor='val_acc',
  save_best_only=True,
  save_weights_only=False
  )
]

# 数据加载
mnist = tf.keras.datasets.mnist
(training_images, training_labels), (test_images, test_labels) = mnist.load_data()

# 数据预处理
# 数据维度预处理
training_images=training_images.reshape(60000, 28, 28, 1)
test_images = test_images.reshape(10000, 28, 28, 1)
# 归一化
training_images=training_images / 255.0
test_images=test_images/255.0

# 定义模型
model = tf.keras.models.Sequential([
  tf.keras.layers.Conv2D(32, (3,3), activation='relu', input_shape=(28, 28, 1)),
  tf.keras.layers.MaxPooling2D(2, 2),
  tf.keras.layers.Flatten(),
  tf.keras.layers.Dense(128, activation='relu'),
  tf.keras.layers.Dense(10, activation='softmax')
])

# 编译and训练
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
model.fit(training_images, training_labels, epochs=10, validation_data=(test_images, test_labels), callbacks=callbacks_list)

# 加载最优模型
model = load_model(filepath)

# 评价
test_loss, test_acc = model.evaluate(test_images, test_labels)
print(test_acc)

# 使用模型预测
classifications = model.predict(test_images)
print(classifications[0])
print(test_labels[0])

# 查看
model.summary()

• 将卷积网络中间层显示出来

import matplotlib.pyplot as plt
from tensorflow.keras import models

f, axarr = plt.subplots(3,4)
FIRST_IMAGE=0
SECOND_IMAGE=7
THIRD_IMAGE=26
CONVOLUTION_NUMBER = 1

layer_outputs = [layer.output for layer in model.layers]
activation_model = tf.keras.models.Model(inputs = model.input, outputs = layer_outputs)

for x in range(0,4):
  f1 = activation_model.predict(test_images[FIRST_IMAGE].reshape(1, 28, 28, 1))[x]
  axarr[0,x].imshow(f1[0, : , :, CONVOLUTION_NUMBER], cmap='inferno')
  axarr[0,x].grid(False)
  f2 = activation_model.predict(test_images[SECOND_IMAGE].reshape(1, 28, 28, 1))[x]
  axarr[1,x].imshow(f2[0, : , :, CONVOLUTION_NUMBER], cmap='inferno')
  axarr[1,x].grid(False)
  f3 = activation_model.predict(test_images[THIRD_IMAGE].reshape(1, 28, 28, 1))[x]
  axarr[2,x].imshow(f3[0, : , :, CONVOLUTION_NUMBER], cmap='inferno')
  axarr[2,x].grid(False)