Keras(十九)卷积神经网络实战

本文将介绍：

• 如何实现tensorflow动态按需分配GPU
• 实现卷积神经网络实战代码

一、实现tensorflow动态按需分配GPU

关于tf动态分配内存可参考文章https://blog.csdn.net/TFATS/article/details/113978075

import matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
import tensorflow as tf
from tensorflow import keras


# 1,实现tensorflow动态按需分配GPU
from tensorflow.compat.v1 import ConfigProto
from tensorflow.compat.v1 import InteractiveSession
config = ConfigProto()
config.gpu_options.allow_growth = True
session = InteractiveSession(config=config)


# 打印使用的python库的版本信息
print(tf.__version__)
print(sys.version_info)
for module in mpl, np, pd, sklearn, tf, keras:
    print(module.__name__, module.__version__)

二，实现卷积神经网络实战代码

1，从tf.keras.datasets中取数据

fashion_mnist = keras.datasets.fashion_mnist
(x_train_all, y_train_all), (x_test, y_test) = fashion_mnist.load_data()
x_valid, x_train = x_train_all[:5000], x_train_all[5000:]
y_valid, y_train = y_train_all[:5000], y_train_all[5000:]

print(x_valid.shape, y_valid.shape)
print(x_train.shape, y_train.shape)
print(x_test.shape, y_test.shape)

2，将数据整合为标准化数据

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
# 整合数据为1通道数据
x_train_scaled = scaler.fit_transform(
    x_train.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28, 1)
x_valid_scaled = scaler.transform(
    x_valid.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28, 1)
x_test_scaled = scaler.transform(
    x_test.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28, 1)

3，构建CNN模型

model = keras.models.Sequential()
model.add(keras.layers.Conv2D(filters=32, kernel_size=3,# 32个神经元;卷积核尺寸为3
                              padding='same',   # padding填充像素至与原来相同
                              activation='selu',    # 或者使用relu激活函数
                              input_shape=(28, 28, 1))) # 输入层为1通道28*28的图像
model.add(keras.layers.Conv2D(filters=32, kernel_size=3,
                              padding='same',
                              activation='selu'))
model.add(keras.layers.MaxPool2D(pool_size=2))
model.add(keras.layers.Conv2D(filters=64, kernel_size=3,
                              padding='same',
                              activation='selu'))
model.add(keras.layers.Conv2D(filters=64, kernel_size=3,
                              padding='same',
                              activation='selu'))
model.add(keras.layers.MaxPool2D(pool_size=2))
model.add(keras.layers.Conv2D(filters=128, kernel_size=3,
                              padding='same',
                              activation='selu'))
model.add(keras.layers.Conv2D(filters=128, kernel_size=3,
                              padding='same',
                              activation='selu'))
model.add(keras.layers.MaxPool2D(pool_size=2))
model.add(keras.layers.Flatten())
model.add(keras.layers.Dense(128, activation='selu'))
model.add(keras.layers.Dense(10, activation="softmax"))

model.compile(loss="sparse_categorical_crossentropy",# 损失函数
              optimizer = "sgd",    # 优化器
              metrics = ["accuracy"])   # 其他衡量指标

4，查看模型层级和参数

model.summary()

5，定义callback 并 训练模型

logdir = './cnn-relu-callbacks'
if not os.path.exists(logdir):
    os.mkdir(logdir)
output_model_file = os.path.join(logdir,
                                 "fashion_mnist_model.h5")

callbacks = [
    keras.callbacks.TensorBoard(logdir),
    keras.callbacks.ModelCheckpoint(output_model_file,
                                    save_best_only = True),
    keras.callbacks.EarlyStopping(patience=5, min_delta=1e-3),
]
history = model.fit(x_train_scaled, y_train,epochs=10,
                    validation_data=(x_valid_scaled, y_valid),
                    callbacks = callbacks)

6，打印训练曲线

def plot_learning_curves(history):
    pd.DataFrame(history.history).plot(figsize=(8, 5))
    plt.grid(True)
    plt.gca().set_ylim(0, 1)
    plt.show()

plot_learning_curves(history)

7，打印估计器结果

print(model.evaluate(x_test_scaled, y_test, verbose = 0))

三，总结代码

1，总结代码-未做过拟合处理

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
import tensorflow as tf
from tensorflow import keras


# 1,实现tensorflow动态按需分配GPU
from tensorflow.compat.v1 import ConfigProto
from tensorflow.compat.v1 import InteractiveSession
config = ConfigProto()
config.gpu_options.allow_growth = True
session = InteractiveSession(config=config)


# 打印使用的python库的版本信息
print(tf.__version__)
print(sys.version_info)
for module in mpl, np, pd, sklearn, tf, keras:
    print(module.__name__, module.__version__)

    
# 2,从tf.keras.datasets中取数据
fashion_mnist = keras.datasets.fashion_mnist
(x_train_all, y_train_all), (x_test, y_test) = fashion_mnist.load_data()
x_valid, x_train = x_train_all[:5000], x_train_all[5000:]
y_valid, y_train = y_train_all[:5000], y_train_all[5000:]

print(x_valid.shape, y_valid.shape)
print(x_train.shape, y_train.shape)
print(x_test.shape, y_test.shape)

# 3,将数据整合为标准化数据
from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
# 整合数据为1通道数据
x_train_scaled = scaler.fit_transform(
    x_train.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28, 1)
x_valid_scaled = scaler.transform(
    x_valid.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28, 1)
x_test_scaled = scaler.transform(
    x_test.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28, 1)

# 4,构建CNN模型
model = keras.models.Sequential()
model.add(keras.layers.Conv2D(filters=32, kernel_size=3,# 32个神经元;卷积核尺寸为3
                              padding='same',   # padding填充像素至与原来相同
                              activation='selu',    # 或者使用relu激活函数
                              input_shape=(28, 28, 1))) # 输入层为1通道28*28的图像
model.add(keras.layers.Conv2D(filters=32, kernel_size=3,
                              padding='same',
                              activation='selu'))
model.add(keras.layers.MaxPool2D(pool_size=2))
model.add(keras.layers.Conv2D(filters=64, kernel_size=3,
                              padding='same',
                              activation='selu'))
model.add(keras.layers.Conv2D(filters=64, kernel_size=3,
                              padding='same',
                              activation='selu'))
model.add(keras.layers.MaxPool2D(pool_size=2))
model.add(keras.layers.Conv2D(filters=128, kernel_size=3,
                              padding='same',
                              activation='selu'))
model.add(keras.layers.Conv2D(filters=128, kernel_size=3,
                              padding='same',
                              activation='selu'))
model.add(keras.layers.MaxPool2D(pool_size=2))
model.add(keras.layers.Flatten())
model.add(keras.layers.Dense(128, activation='selu'))
model.add(keras.layers.Dense(10, activation="softmax"))

model.compile(loss="sparse_categorical_crossentropy",# 损失函数
              optimizer = "sgd",    # 优化器
              metrics = ["accuracy"])   # 其他衡量指标

# 5,查看模型层级和参数
model.summary()

# 6,定义callback 并 训练模型
logdir = './cnn-relu-callbacks'
if not os.path.exists(logdir):
    os.mkdir(logdir)
output_model_file = os.path.join(logdir,
                                 "fashion_mnist_model.h5")

callbacks = [
    keras.callbacks.TensorBoard(logdir),
    keras.callbacks.ModelCheckpoint(output_model_file,
                                    save_best_only = True),
    keras.callbacks.EarlyStopping(patience=5, min_delta=1e-3),
]
history = model.fit(x_train_scaled, y_train,epochs=10,
                    validation_data=(x_valid_scaled, y_valid),
                    callbacks = callbacks)

# 7,打印训练曲线
def plot_learning_curves(history):
    pd.DataFrame(history.history).plot(figsize=(8, 5))
    plt.grid(True)
    plt.gca().set_ylim(0, 1)
    plt.show()

plot_learning_curves(history)

# 8,打印估计器结果
print(model.evaluate(x_test_scaled, y_test, verbose = 0))

# ---output------
[0.3523516479730606, 0.9085]

训练曲线图如下：
我们从图中可以看到，训练过程中已经出现了过拟合的现象。

2，总结代码-过拟合处理

添加了如下改动：

• set_seed - 使多次对比训练中，随机参数初始化为固定值。
• L2正则化 - 解决过拟合问题
• Dropout - 解决过拟合问题

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import regularizers

my_seed = 666
np.random.seed(my_seed)
import random 
random.seed(my_seed)
import tensorflow as tf
tf.random.set_seed(my_seed)

# 1,实现tensorflow动态按需分配GPU
from tensorflow.compat.v1 import ConfigProto
from tensorflow.compat.v1 import InteractiveSession
config = ConfigProto()
config.gpu_options.allow_growth = True
session = InteractiveSession(config=config)


# 打印使用的python库的版本信息
print(tf.__version__)
print(sys.version_info)
for module in mpl, np, pd, sklearn, tf, keras:
    print(module.__name__, module.__version__)

    
# 2,从tf.keras.datasets中取数据
fashion_mnist = keras.datasets.fashion_mnist
(x_train_all, y_train_all), (x_test, y_test) = fashion_mnist.load_data()
x_valid, x_train = x_train_all[:5000], x_train_all[5000:]
y_valid, y_train = y_train_all[:5000], y_train_all[5000:]

print(x_valid.shape, y_valid.shape)
print(x_train.shape, y_train.shape)
print(x_test.shape, y_test.shape)

# 3,将数据整合为标准化数据
from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
# 整合数据为1通道数据
x_train_scaled = scaler.fit_transform(
    x_train.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28, 1)
x_valid_scaled = scaler.transform(
    x_valid.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28, 1)
x_test_scaled = scaler.transform(
    x_test.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28, 1)

# 4,构建CNN模型
model = keras.models.Sequential()
model.add(keras.layers.Conv2D(filters=32, kernel_size=3,# 32个神经元;卷积核尺寸为3
                              padding='same',   # padding填充像素至与原来相同
                              activation='selu',    # 或者使用relu激活函数
                              kernel_regularizer=regularizers.l2(0.01),
                              input_shape=(28, 28, 1))) # 输入层为1通道28*28的图像
model.add(keras.layers.Conv2D(filters=32, kernel_size=3,
                              padding='same',
                              kernel_regularizer=regularizers.l2(0.01),
                              activation='selu'))
model.add(keras.layers.MaxPool2D(pool_size=2))
model.add(keras.layers.Conv2D(filters=64, kernel_size=3, 
                              padding='same',
                               kernel_regularizer=regularizers.l2(0.01),
                              activation='selu'))
model.add(keras.layers.Conv2D(filters=64, kernel_size=3,
                              padding='same',
                               kernel_regularizer=regularizers.l2(0.01),
                              activation='selu'))
model.add(keras.layers.MaxPool2D(pool_size=2))
model.add(keras.layers.Conv2D(filters=128, kernel_size=3,
                              padding='same',
                               kernel_regularizer=regularizers.l2(0.01),
                              activation='selu'))
model.add(keras.layers.Conv2D(filters=128, kernel_size=3,
                              padding='same',
                                kernel_regularizer=regularizers.l2(0.01),
                              activation='selu'))
model.add(keras.layers.MaxPool2D(pool_size=2))
model.add(keras.layers.Flatten())
model.add(keras.layers.Dense(128, activation='selu'))
# model.add(keras.layers.AlphaDropout(rate=0.5))  # 可以比对训练结果决定是否需要加Dropout
model.add(keras.layers.Dense(10, activation="softmax"))

model.compile(loss="sparse_categorical_crossentropy",# 损失函数
              optimizer = "sgd",    # 优化器
              metrics = ["accuracy"])   # 其他衡量指标s

# 5,查看模型层级和参数
model.summary()

# 6,定义callback 并 训练模型
logdir = './cnn-relu-callbacks'
if not os.path.exists(logdir):
    os.mkdir(logdir)
output_model_file = os.path.join(logdir,
                                 "fashion_mnist_model.h5")

callbacks = [
    keras.callbacks.TensorBoard(logdir),
    keras.callbacks.ModelCheckpoint(output_model_file,
                                    save_best_only = True),
    keras.callbacks.EarlyStopping(patience=5, min_delta=1e-3),
]
history = model.fit(x_train_scaled, y_train,epochs=30,
                    validation_data=(x_valid_scaled, y_valid),
                    callbacks = callbacks)

# 7,打印训练曲线
def plot_learning_curves(history):
    pd.DataFrame(history.history).plot(figsize=(8, 5))
    plt.grid(True)
    plt.gca().set_ylim(0, 1)
    plt.show()

plot_learning_curves(history)

# 8,打印估计器结果
print(model.evaluate(x_test_scaled, y_test, verbose = 0))

# ---output-------
[0.3523516479730606, 0.9085]