深度学习CNN--眼睛姿态识别联练习

​
​

活动地址：CSDN21天学习挑战赛
这里就讲述整个识别流程，提炼出几个和以往发表文章不同的进行表述，相关识别文章参考连接

1、混淆矩阵
混淆矩阵通常用于评价训练模型的好坏，这里简单的列举一个二分类的例子，有类别A和B，预测结果正确且为A的数量记为TA，预测结果正确且为B的数量记作TB，那预测错误且为A的为FA，预测错误且为B的记为FB，这样就做成了一个混淆矩阵。混淆矩阵展示效果如下可以直观的看出预测结果及数量。

下面是混淆矩阵的代码

from sklearn.metrics import confusion_matrix
import seaborn as sns
import pandas as pd

# 定义一个绘制混淆矩阵图的函数
def plot_cm(labels, predictions):
    
    # 生成混淆矩阵
    conf_numpy = confusion_matrix(labels, predictions)
    # 将矩阵转化为 DataFrame
    conf_df = pd.DataFrame(conf_numpy, index=class_names ,columns=class_names)  
    
    plt.figure(figsize=(8,7))
    
    sns.heatmap(conf_df, annot=True, fmt="d", cmap="BuPu")
    
    plt.title('混淆矩阵',fontsize=15)
    plt.ylabel('真实值',fontsize=14)
    plt.xlabel('预测值',fontsize=14)
val_pre   = []
val_label = []

for images, labels in val_ds:#这里可以取部分验证数据（.take(1)）生成混淆矩阵
    for image, label in zip(images, labels):
        # 需要给图片增加一个维度
        img_array = tf.expand_dims(image, 0) 
        # 使用模型预测图片中的人物
        prediction = model.predict(img_array)

        val_pre.append(class_names[np.argmax(prediction)])
        val_label.append(class_names[label])
plot_cm(val_label, val_pre)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33

下面是眼睛识别的混淆矩阵结果

2、常用网络结构调用方法
tensorflow自带许多程度的神经网络，可以通过函数进行调用，下面以VGG16模型调用为例代码如下

model = tf.keras.applications.VGG16()
# 打印模型信息
model.summary()

1
2
3
4

下面列举出可以直接调用的网络模型：

3、眼睛数据集连接如下：
链接：https://pan.baidu.com/s/12Waf0no8vKHhqUK8RzGmUA
提取码：n2v0
里面有四个文件：


4、最后给出完整代码参考

import matplotlib.pyplot as plt
# 支持中文
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False  # 用来正常显示负号

import os,PIL

# 设置随机种子尽可能使结果可以重现
import numpy as np
np.random.seed(1)

# 设置随机种子尽可能使结果可以重现
import tensorflow as tf
tf.random.set_seed(1)

import pathlib
data_dir = "H:\python_project\python辅助算法\data\\017_Eye_dataset"

data_dir = pathlib.Path(data_dir)
image_count = len(list(data_dir.glob('*/*')))

print("图片总数为：",image_count)
# 预处理数据
batch_size = 64
img_height = 224
img_width = 224
"""
关于image_dataset_from_directory()的详细介绍可以参考文章：https://mtyjkh.blog.csdn.net/article/details/117018789
"""
train_ds = tf.keras.preprocessing.image_dataset_from_directory(
    data_dir,
    validation_split=0.2,
    subset="training",
    seed=12,
    image_size=(img_height, img_width),
    batch_size=batch_size)
"""
关于image_dataset_from_directory()的详细介绍可以参考文章：https://mtyjkh.blog.csdn.net/article/details/117018789
"""
val_ds = tf.keras.preprocessing.image_dataset_from_directory(
    data_dir,
    validation_split=0.2,
    subset="validation",
    seed=12,
    image_size=(img_height, img_width),
    batch_size=batch_size)
class_names = train_ds.class_names
print(class_names)
# 配置数据集
AUTOTUNE = tf.data.AUTOTUNE

train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds   = val_ds.cache().prefetch(buffer_size=AUTOTUNE)
# 调用模型
model = tf.keras.applications.VGG16()
# 打印模型信息
model.summary()
# 设置初始学习率
initial_learning_rate = 1e-4

lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(
        initial_learning_rate,
        decay_steps=20,      # 敲黑板！！！这里是指 steps，不是指epochs
        decay_rate=0.96,     # lr经过一次衰减就会变成 decay_rate*lr
        staircase=True)

# 将指数衰减学习率送入优化器
optimizer = tf.keras.optimizers.Adam(learning_rate=lr_schedule)
# 编译
model.compile(optimizer=optimizer,
              loss     ='sparse_categorical_crossentropy',
              metrics  =['accuracy'])
epochs = 10
# 训练
history = model.fit(
    train_ds,
    validation_data=val_ds,
    epochs=epochs
)
# 训练过程存储在history里面
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']

loss = history.history['loss']
val_loss = history.history['val_loss']

epochs_range = range(epochs)
# 展示训练结果
plt.figure(figsize=(12, 4))
plt.subplot(1, 2, 1)

plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss, label='Training Loss')
plt.plot(epochs_range, val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

from sklearn.metrics import confusion_matrix
import seaborn as sns
import pandas as pd


# 定义一个绘制混淆矩阵图的函数
def plot_cm(labels, predictions):
    # 生成混淆矩阵
    conf_numpy = confusion_matrix(labels, predictions)
    # 将矩阵转化为 DataFrame
    conf_df = pd.DataFrame(conf_numpy, index=class_names, columns=class_names)

    plt.figure(figsize=(8, 7))

    sns.heatmap(conf_df, annot=True, fmt="d", cmap="BuPu")

    plt.title('混淆矩阵', fontsize=15)
    plt.ylabel('真实值', fontsize=14)
    plt.xlabel('预测值', fontsize=14)
val_pre   = []
val_label = []

for images, labels in val_ds:#这里可以取部分验证数据（.take(1)）生成混淆矩阵
    for image, label in zip(images, labels):
        # 需要给图片增加一个维度
        img_array = tf.expand_dims(image, 0)
        # 使用模型预测图片中的人物
        prediction = model.predict(img_array)

        val_pre.append(class_names[np.argmax(prediction)])
        val_label.append(class_names[label])
# 保存模型
model.save('model/17_model.h5')
# 加载模型
new_model = tf.keras.models.load_model('model/17_model.h5')
# 采用加载的模型（new_model）来看预测结果

plt.figure(figsize=(10, 5))  # 图形的宽为10高为5
plt.suptitle("预测结果展示")

for images, labels in val_ds.take(1):
    for i in range(8):
        ax = plt.subplot(2, 4, i + 1)

        # 显示图片
        plt.imshow(images[i].numpy().astype("uint8"))

        # 需要给图片增加一个维度
        img_array = tf.expand_dims(images[i], 0)

        # 使用模型预测图片中的人物
        predictions = new_model.predict(img_array)
        plt.title(class_names[np.argmax(predictions)])

        plt.axis("off")

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159

下面给出VGG16的具体参数展示，这个模型参数比较多，有很多种方法可以进行优化

Model: "vgg16"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         [(None, 224, 224, 3)]     0         
_________________________________________________________________
block1_conv1 (Conv2D)        (None, 224, 224, 64)      1792      
_________________________________________________________________
block1_conv2 (Conv2D)        (None, 224, 224, 64)      36928     
_________________________________________________________________
block1_pool (MaxPooling2D)   (None, 112, 112, 64)      0         
_________________________________________________________________
block2_conv1 (Conv2D)        (None, 112, 112, 128)     73856     
_________________________________________________________________
block2_conv2 (Conv2D)        (None, 112, 112, 128)     147584    
_________________________________________________________________
block2_pool (MaxPooling2D)   (None, 56, 56, 128)       0         
_________________________________________________________________
block3_conv1 (Conv2D)        (None, 56, 56, 256)       295168    
_________________________________________________________________
block3_conv2 (Conv2D)        (None, 56, 56, 256)       590080    
_________________________________________________________________
block3_conv3 (Conv2D)        (None, 56, 56, 256)       590080    
_________________________________________________________________
block3_pool (MaxPooling2D)   (None, 28, 28, 256)       0         
_________________________________________________________________
block4_conv1 (Conv2D)        (None, 28, 28, 512)       1180160   
_________________________________________________________________
block4_conv2 (Conv2D)        (None, 28, 28, 512)       2359808   
_________________________________________________________________
block4_conv3 (Conv2D)        (None, 28, 28, 512)       2359808   
_________________________________________________________________
block4_pool (MaxPooling2D)   (None, 14, 14, 512)       0         
_________________________________________________________________
block5_conv1 (Conv2D)        (None, 14, 14, 512)       2359808   
_________________________________________________________________
block5_conv2 (Conv2D)        (None, 14, 14, 512)       2359808   
_________________________________________________________________
block5_conv3 (Conv2D)        (None, 14, 14, 512)       2359808   
_________________________________________________________________
block5_pool (MaxPooling2D)   (None, 7, 7, 512)         0         
_________________________________________________________________
flatten (Flatten)            (None, 25088)             0         
_________________________________________________________________
fc1 (Dense)                  (None, 4096)              102764544 
_________________________________________________________________
fc2 (Dense)                  (None, 4096)              16781312  
_________________________________________________________________
predictions (Dense)          (None, 1000)              4097000   
=================================================================
Total params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53

下面是训练曲线（训练和验证）的代码展示及曲线图：

acc = history.history['accuracy']
val_acc = history.history['val_accuracy']

loss = history.history['loss']
val_loss = history.history['val_loss']

epochs_range = range(epochs)

plt.figure(figsize=(12, 4))
plt.subplot(1, 2, 1)

plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss, label='Training Loss')
plt.plot(epochs_range, val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23