第38周：猫狗识别 (Tensorflow实战第八周)

前言

一、前期工作

1.1 设置GPU

1.2 导入数据

输出

二、数据预处理

2.1 加载数据

2.2 再次检查数据

2.3 配置数据集

2.4 可视化数据

三、构建VGG-16网络

3.1 VGG-16网络介绍

3.2 搭建VGG-16模型

四、编译

五、训练模型

六、模型评估

七、预测

总结

前言

🍨 本文为中的学习记录博客
🍖 原作者：

说在前面

1）本周任务：了解model.train_on_batch()并运用；了解tqdm，并使用tqdm实现可视化进度条；

2）运行环境：Python3.6、Pycharm2020、tensorflow2.4.0

一、前期工作

1.1 设置GPU

代码如下：

python">import os
os.environ["CUDA_VISIBLE_DEVICES"]="0"
os.environ["TF_CPP_MIN_LOG_LEVEL"]='3' # 忽略 Error
#隐藏警告
import warnings
warnings.filterwarnings('ignore')
# 1.1 设置GPU
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")
# 打印显卡信息，确认GPU可用
print(gpus)

输出：[PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU')]

⚠️⚠️⚠️前期我没有使用GPU就采用的CPU训练速度很慢，虽然安装了tensorflow-gpu但还是用的CPU因为我的cudnn和cudatoolkit之前没配置成功，然后我补充安装。这里出线会打印很多关于gpu调用的日志信息，会很影响我们对训练过程和打印信息的关注度，这里我在import tensorflow之前先通过下面的设置来控制打印的内容

import os
os.environ["CUDA_VISIBLE_DEVICES"]="0"
os.environ["TF_CPP_MIN_LOG_LEVEL"]='3'

TF_CPP_MIN_LOG_LEVEL 取值 0 ： 0也是默认值，输出所有信息
TF_CPP_MIN_LOG_LEVEL 取值 1 ：屏蔽通知信息
TF_CPP_MIN_LOG_LEVEL 取值 2 ：屏蔽通知信息和警告信息
TF_CPP_MIN_LOG_LEVEL 取值 3 ：屏蔽通知信息、警告信息和报错信息
参考自：https://blog.csdn.net/xiaoqiaoliushuiCC/article/details/124435241

1.2 导入数据

代码如下：

python"># 1.2 导入数据
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,pathlib
data_dir = "./data"
data_dir = pathlib.Path(data_dir)
image_count = len(list(data_dir.glob('*/*')))
print("图片总数为：",image_count)

输出

图片总数为： 3400

二、数据预处理

2.1 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，tf.keras.preprocessing.image_dataset_from_directory()：是 TensorFlow 的 Keras 模块中的一个函数，用于从目录中创建一个图像数据集（dataset）。这个函数可以以更方便的方式加载图像数据，用于训练和评估神经网络模型

测试集与验证集的关系：

验证集并没有参与训练过程梯度下降过程的，狭义上来讲是没有参与模型的参数训练更新的。
但是广义上来讲，验证集存在的意义确实参与了一个“人工调参”的过程，我们根据每一个epoch训练之后模型在valid data上的表现来决定是否需要训练进行early stop，或者根据这个过程模型的性能变化来调整模型的超参数，如学习率，batch_size等等。因此，我们也可以认为，验证集也参与了训练，但是并没有使得模型去overfit验证集
因此，我们也可以认为，验证集也参与了训练，但是并没有使得模型去overfit验证集

代码如下：

python"># 二、数据预处理
# 2.1 加载数据
batch_size = 8
img_height = 224
img_width = 224
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)
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)

输出如下：

['cat', 'dog']

2.2 再次检查数据

代码如下：

python"># 2.2 再次检查数据
for image_batch, labels_batch in train_ds:print(image_batch.shape)print(labels_batch.shape)break

输出：

(8, 224, 224, 3)
(8,)

2.3 配置数据集

代码如下：

python"># 2.3 配置数据集
AUTOTUNE = tf.data.AUTOTUNEdef preprocess_image(image,label):return (image/255.0,label)
# 归一化处理
train_ds = train_ds.map(preprocess_image, num_parallel_calls=AUTOTUNE)
val_ds = val_ds.map(preprocess_image, num_parallel_calls=AUTOTUNE)
train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)

2.4 可视化数据

代码如下：

python">plt.figure(figsize=(15, 10))  # 图形的宽为15高为10
for images, labels in train_ds.take(1):for i in range(8):ax = plt.subplot(5, 8, i + 1)plt.imshow(images[i])plt.title(class_names[labels[i]])plt.axis("off")

输出：

三、构建VGG-16网络

3.1 VGG-16网络介绍

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

网络结构图如下（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）

3.2 搭建VGG-16模型

代码如下：

python"># 三、构建VGG-16网络
from tensorflow.keras import layers, models, Input
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Flatten, Dropoutdef VGG16(nb_classes, input_shape):input_tensor = Input(shape=input_shape)# 1st blockx = 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 blockx = 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 blockx = 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 blockx = 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 blockx = 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 connectionx = 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 modelmodel=VGG16(1000, (img_width, img_height, 3))
model.summary()

模型结构打印如下：

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, 1000) 4097000
=================================================================
Total params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0

四、编译

代码如下：

python">model.compile(optimizer="adam",loss='sparse_categorical_crossentropy',metrics=['accuracy'])

五、训练模型

代码如下：

python"># 五、训练模型
from tqdm import tqdm
import tensorflow.keras.backend as Kepochs = 10
lr = 1e-4# 记录训练数据，方便后面的分析
history_train_loss = []
history_train_accuracy = []
history_val_loss = []
history_val_accuracy = []
for epoch in range(epochs):train_total = len(train_ds)val_total = len(val_ds)with tqdm(total=train_total, desc=f'Epoch {epoch + 1}/{epochs}', mininterval=1, ncols=100) as pbar:lr = lr * 0.92K.set_value(model.optimizer.lr, lr)for image, label in train_ds:history = model.train_on_batch(image, label)train_loss = history[0]train_accuracy = history[1]pbar.set_postfix({"loss": "%.4f" % train_loss,"accuracy": "%.4f" % train_accuracy,"lr": K.get_value(model.optimizer.lr)})pbar.update(1)history_train_loss.append(train_loss)history_train_accuracy.append(train_accuracy)print('开始验证！')with tqdm(total=val_total, desc=f'Epoch {epoch + 1}/{epochs}', mininterval=0.3, ncols=100) as pbar:for image, label in val_ds:history = model.test_on_batch(image, label)val_loss = history[0]val_accuracy = history[1]pbar.set_postfix({"loss": "%.4f" % val_loss,"accuracy": "%.4f" % val_accuracy})pbar.update(1)history_val_loss.append(val_loss)history_val_accuracy.append(val_accuracy)print('结束验证！')print("验证loss为：%.4f" % val_loss)print("验证准确率为：%.4f" % val_accuracy)

打印训练过程：

六、模型评估

代码如下：

python">epochs_range = range(epochs)
plt.figure(figsize=(12, 4))
plt.subplot(1, 2, 1)plt.plot(epochs_range, history_train_accuracy, label='Training Accuracy')
plt.plot(epochs_range, history_val_accuracy, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')plt.subplot(1, 2, 2)
plt.plot(epochs_range, history_train_loss, label='Training Loss')
plt.plot(epochs_range, history_val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

训练结果可视化如下：

七、预测

代码如下：

python"># 七、预测
import numpy as np
# 采用加载的模型（new_model）来看预测结果
plt.figure(figsize=(18, 3))  # 图形的宽为18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(1, 8, i + 1)# 显示图片plt.imshow(images[i].numpy())# 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 = model.predict(img_array)plt.title(class_names[np.argmax(predictions)])plt.axis("off")

输出：

1/1 [==============================] - 0s 129ms/step
1/1 [==============================] - 0s 19ms/step
1/1 [==============================] - 0s 18ms/step
1/1 [==============================] - 0s 18ms/step
1/1 [==============================] - 0s 17ms/step
1/1 [==============================] - 0s 18ms/step
1/1 [==============================] - 0s 17ms/step
1/1 [==============================] - 0s 17ms/step

总结

Tensorflow训练过程中打印多余信息的处理，并且引入了进度条的显示方式，更加方便及时查看模型训练过程中的情况，可以及时打印各项指标
修改了以往的model.fit()训练方法，改用model.train_on_batch方法。两种方法的比较：model.fit()：用起来十分简单，对新手非常友好；model.train_on_batch()：封装程度更低，可以玩更多花样
完成了VGG-16基于Tensorflow下的搭建、训练等工作，对比分析了pytorch和tensorflow两个框架下实现同种任务的异同；
完成VGG-16对猫狗图片的高精度识别