keras 12_绘制网络结构

import numpy as np
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense,Dropout,Convolution2D,MaxPool2D,Flatten
from keras.optimizers import Adam
from keras.utils.vis_utils import plot_model
import matplotlib.pyplot as plt
import tensorflow as tf

config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.Session(config = config)


# 载入数据
(x_train,y_train),(x_test,y_test) = mnist.load_data()
print("x_train.shape:",x_train.shape,"y_train.shape:",y_train.shape)

# 将数据转由（60000,28,28）转换为（60000,784）的格式
# x_train=x_train.reshape(x_train.shape[0],-1)/255.0
# x_test=x_test.reshape(x_test.shape[0],-1)/255.0

x_train=x_train.reshape(-1,28,28,1)/255.0
x_test=x_test.reshape(-1,28,28,1)/255.0


# 将数据格式转换为one-hot编码的格式
y_train=np_utils.to_categorical(y_train,num_classes=10)
y_test=np_utils.to_categorical(y_test,num_classes=10)

# 定义转换模型
model = Sequential()

# 第一个卷积层
# input_shape:输入平面
# filter:卷积核、滤波器个数
# kernel_size：卷积窗口大小
# strides:步长
# padding: padding方式，same/valid
# activation:激活函数
model.add(Convolution2D(
    input_shape=(28,28,1),
    filters=32,
    kernel_size=5,
    strides=1,
    padding="same",
    activation="relu",
    name="conv1"
))

# 第一个池化层
model.add(MaxPool2D(
    pool_size=2,
    strides=2,
    padding="same",
    name="poll1"
))

# 第二个卷积层
model.add(Convolution2D(
    filters=64,
    kernel_size=5,
    strides=1,
    padding="same",
    activation="relu",
    name="conv2"
))

# 第二个池化层
model.add(MaxPool2D(
    pool_size=2,
    strides=2,
    padding="same",
    name="poll2"
))

# 将第二个池化层的输出扁平化1维
model.add(Flatten())
# 第一个全连接层
model.add(Dense(1024,activation="relu"))
# Dropout
model.add(Dropout(0.5))
#第二个全连接层
model.add(Dense(10,activation="softmax"))

# 定义优化器
adam = Adam(lr=0.001)

# 定义优化器
model.compile(optimizer=adam,loss="categorical_crossentropy",metrics=["accuracy"])

# 训练模型
model.fit(x_train,y_train,batch_size=32,epochs=1)

# 模型评估
loss,accuracy = model.evaluate(x_test, y_test)
print("test loss:",loss)
print("test accuracy:",accuracy)


# 打印网络结构
# plot_model(model,to_file="model.png",show_shapes=True,show_layer_names="False",rankdir="TB")
plot_model(model,to_file="model.png",show_shapes=True,show_layer_names="False",rankdir="TB")
plt.figure(figsize=(10,10))
plt.imread("model.png")
plt.axis("off")
plt.show()