🏡 我的环境：

• 语言环境：Python3.10.11
• 编译器：Jupyter Notebook
• 深度学习框架：TensorFlow2.4.1
• 显卡（GPU）：NVIDIA GeForce RTX 4070

🥂 相关教程：

• 编译器教程：【新手入门深度学习 | 1-2：编译器Jupyter Notebook】
• 深度学习环境配置教程：【新手入门深度学习 | 1-1：配置深度学习环境】
• 一个深度学习小白需要的所有资料我都放这里了：【新手入门深度学习 | 目录】

建议你学习本文之前先看看下面这篇入门文章，以便你可以更好的理解本文：🍨 新手入门深度学习 | 2-1：图像数据建模流程示例

强烈建议大家使用Jupyter Notebook编译器打开源码，你接下来的操作将会非常便捷的！

• 如果你是深度学习小白，阅读本文前建议先学习一下 📖《新手入门深度学习》
• 如果你有一定基础，但是缺乏实战经验，可通过 📖《深度学习100例》 补齐基础
• 另外，我们正在通过 🔥365天深度学习训练营🔥 抱团学习，营内为大家提供系统的学习教案与专业的指导、非常良好的学习氛围，欢迎你的加入

一、前期工作

1. 设置GPU

如果使用的是CPU可以忽略这步

import tensorflow as tf

gpus = tf.config.list_physical_devices("GPU")

if gpus:
    tf.config.experimental.set_memory_growth(gpus[0], True)  #设置GPU显存用量按需使用
    tf.config.set_visible_devices([gpus[0]],"GPU")

2. 导入数据

from tensorflow       import keras
from tensorflow.keras import layers,models
import numpy             as np
import matplotlib.pyplot as plt
import os,PIL,pathlib

data_dir = "./49-data/"
data_dir = pathlib.Path(data_dir)

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

print("图片总数为：",image_count)

图片总数为： 1200

二、数据预处理

1. 加载数据

使用image_dataset_from_directory方法将磁盘中的数据加载到tf.data.Dataset中

batch_size = 32
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.jpg>0.2,
    subset="training",
    seed=123,
    image_size=(img_height, img_width),
    batch_size=batch_size)

Found 1200 files belonging to 4 classes.
Using 960 files for training.

"""
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=123,
    image_size=(img_height, img_width),
    batch_size=batch_size)

Found 1200 files belonging to 4 classes.
Using 240 files for validation.

我们可以通过class_names输出数据集的标签。标签将按字母顺序对应于目录名称。

class_names = train_ds.class_names
print(class_names)

['Dark', 'Green', 'Light', 'Medium']

2. 可视化数据

plt.figure(figsize=(10, 4))  # 图形的宽为10高为5

for images, labels in train_ds.take(1):
    for i in range(10):
        
        ax = plt.subplot(2, 5, i + 1)  

        plt.imshow(images[i].numpy().astype("uint8"))
        plt.title(class_names[labels[i]])
        
        plt.axis("off")

for image_batch, labels_batch in train_ds:
    print(image_batch.shape)
    print(labels_batch.shape)
    break

(32, 224, 224, 3)
(32,)

3. 配置数据集

• shuffle() ：打乱数据，关于此函数的详细介绍可以参考：zhuanlan.zhihu.com/p/42417456
• prefetch() ：预取数据，加速运行，其详细介绍可以参考我前两篇文章，里面都有讲解。
• cache() ：将数据集缓存到内存当中，加速运行

AUTOTUNE = tf.data.AUTOTUNE

train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds   = val_ds.cache().prefetch(buffer_size=AUTOTUNE)

normalization_layer = layers.experimental.preprocessing.Rescaling(1./255)

train_ds = train_ds.map(lambda x, y: (normalization_layer(x), y))
val_ds   = val_ds.map(lambda x, y: (normalization_layer(x), y))

image_batch, labels_batch = next(iter(val_ds))
first_image = image_batch[0]

# 查看归一化后的数据
print(np.min(first_image), np.max(first_image))

0.0 1.0

三、构建VGG-16网络

在官方模型与自建模型之间进行二选一就可以了，选着一个注释掉另外一个。

VGG优缺点分析：

• VGG优点

VGG的结构非常简洁，整个网络都使用了同样大小的卷积核尺寸（3x3）和最大池化尺寸（2x2）。

• VGG缺点

1)训练时间过长，调参难度大。2)需要的存储容量大，不利于部署。例如存储VGG-16权重值文件的大小为500多MB，不利于安装到嵌入式系统中。

1. 官方模型

官网模型调用这块我放到后面几篇文章中，下面主要讲一下VGG-16

# model = tf.keras.applications.VGG16(weights='imagenet')
# model.summary()

2. 自建模型

from tensorflow.keras import layers, models, Input
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Flatten, Dropout

def VGG16(nb_classes, input_shape):
    input_tensor = Input(shape=input_shape)
    # 1st block
    x = Conv2D(64, (3,3), activation='relu', padding='same',name='block1_conv1')(input_tensor)
    x = Conv2D(64, (3,3), activation='relu', padding='same',name='block1_conv2')(x)
    x = MaxPooling2D((2,2), strides=(2,2), name = 'block1_pool')(x)
    # 2nd block
    x = Conv2D(128, (3,3), activation='relu', padding='same',name='block2_conv1')(x)
    x = Conv2D(128, (3,3), activation='relu', padding='same',name='block2_conv2')(x)
    x = MaxPooling2D((2,2), strides=(2,2), name = 'block2_pool')(x)
    # 3rd block
    x = Conv2D(256, (3,3), activation='relu', padding='same',name='block3_conv1')(x)
    x = Conv2D(256, (3,3), activation='relu', padding='same',name='block3_conv2')(x)
    x = Conv2D(256, (3,3), activation='relu', padding='same',name='block3_conv3')(x)
    x = MaxPooling2D((2,2), strides=(2,2), name = 'block3_pool')(x)
    # 4th block
    x = Conv2D(512, (3,3), activation='relu', padding='same',name='block4_conv1')(x)
    x = Conv2D(512, (3,3), activation='relu', padding='same',name='block4_conv2')(x)
    x = Conv2D(512, (3,3), activation='relu', padding='same',name='block4_conv3')(x)
    x = MaxPooling2D((2,2), strides=(2,2), name = 'block4_pool')(x)
    # 5th block
    x = Conv2D(512, (3,3), activation='relu', padding='same',name='block5_conv1')(x)
    x = Conv2D(512, (3,3), activation='relu', padding='same',name='block5_conv2')(x)
    x = Conv2D(512, (3,3), activation='relu', padding='same',name='block5_conv3')(x)
    x = MaxPooling2D((2,2), strides=(2,2), name = 'block5_pool')(x)
    # full connection
    x = Flatten()(x)
    x = Dense(4096, activation='relu',  name='fc1')(x)
    x = Dense(4096, activation='relu', name='fc2')(x)
    output_tensor = Dense(nb_classes, activation='softmax', name='predictions')(x)

    model = Model(input_tensor, output_tensor)
    return model

model=VGG16(len(class_names), (img_width, img_height, 3))
model.summary()

Model: "model"
_________________________________________________________________
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, 4)                 16388     
=================================================================
Total params: 134,276,932
Trainable params: 134,276,932
Non-trainable params: 0
_________________________________________________________________

3. 网络结构图

参加了365天深度学习训练营的同学可以在语雀中查看网络结构图

关于卷积的相关知识可以参考文章：mtyjkh.blog.csdn.net/article/det…

结构说明：

• 13个卷积层（Convolutional Layer），分别用blockX_convX表示
• 3个全连接层（Fully connected Layer），分别用fcX与predictions表示
• 5个池化层（Pool layer），分别用blockX_pool表示

VGG-16包含了16个隐藏层（13个卷积层和3个全连接层），故称为VGG-16

四、编译

在准备对模型进行训练之前，还需要再对其进行一些设置。以下内容是在模型的编译步骤中添加的：

• 损失函数（loss）：用于衡量模型在训练期间的准确率。
• 优化器（optimizer）：决定模型如何根据其看到的数据和自身的损失函数进行更新。
• 指标（metrics）：用于监控训练和测试步骤。以下示例使用了准确率，即被正确分类的图像的比率。

# 设置初始学习率
initial_learning_rate = 1e-4

lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(
        initial_learning_rate, 
        decay_steps=30,      # 敲黑板！！！这里是指 steps，不是指epochs
        decay_rate=0.92,     # lr经过一次衰减就会变成 decay_rate*lr
        staircase=True)

# 设置优化器
opt = tf.keras.optimizers.Adam(learning_rate=initial_learning_rate)

model.compile(optimizer=opt,
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

五、训练模型

epochs = 20

history = model.fit(
    train_ds,
    validation_data=val_ds,
    epochs=epochs
)

Epoch 1/20
30/30 [==============================] - 13s 187ms/step - loss: 1.3438 - accuracy: 0.3208 - val_loss: 0.9648 - val_accuracy: 0.6750
Epoch 2/20
30/30 [==============================] - 4s 139ms/step - loss: 0.7589 - accuracy: 0.6052 - val_loss: 0.6280 - val_accuracy: 0.7375
Epoch 3/20
30/30 [==============================] - 4s 136ms/step - loss: 0.6868 - accuracy: 0.6292 - val_loss: 0.7508 - val_accuracy: 0.5125
Epoch 4/20
30/30 [==============================] - 4s 136ms/step - loss: 0.6073 - accuracy: 0.6927 - val_loss: 0.6004 - val_accuracy: 0.5875
 ......
Epoch 18/20
30/30 [==============================] - 4s 137ms/step - loss: 0.0537 - accuracy: 0.9781 - val_loss: 0.1639 - val_accuracy: 0.9667
Epoch 19/20
30/30 [==============================] - 4s 138ms/step - loss: 0.0580 - accuracy: 0.9781 - val_loss: 0.1093 - val_accuracy: 0.9625
Epoch 20/20
30/30 [==============================] - 4s 136ms/step - loss: 0.0765 - accuracy: 0.9740 - val_loss: 0.1346 - val_accuracy: 0.9667

六、模型评估

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()

• 🍨 本文为🔗365天深度学习训练营 中的学习记录博客