Press "Enter" to skip to content

365天深度学习训练营 | 第8周:猫狗识别

本站内容均来自兴趣收集,如不慎侵害的您的相关权益,请留言告知,我们将尽快删除.谢谢.

:ice_cream: 本文为 :link:365天深度学习训练营 中的学习记录博客
:icecream: 参考文章:365天深度学习训练营 | 第8周:猫狗识别(训练营内部成员可阅读)
:meat_on_bone: 原作者: K同学啊|接辅导、项目定制

:house_with_garden: 我的环境:

语言环境:Python3.6.5
编译器:jupyter lab
深度学习环境:TensorFlow2.4.1
数据集:参加训练营可获取

这篇文章中我放弃了以往的model.fit()训练方法,改用model.train_on_batch方法。两种方法的比较:

 

model.fit()
model.train_on_batch()

 

此外我也引入了进度条的显示方式,更加方便我们及时查看模型训练过程中的情况,可以及时打印各项指标。

 

:house_with_garden: 我的环境:

语言环境:Python3.6.5
编译器:jupyter notebook
深度学习环境:TensorFlow2.4.1

一、前期工作

 

1. 设置GPU

 

如果使用的是CPU可以注释掉这部分的代码。

 

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)

 

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

 

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
#隐藏警告
import warnings
warnings.filterwarnings('ignore')
data_dir = "./365-7-data"
data_dir = pathlib.Path(data_dir)
image_count = len(list(data_dir.glob('*/*')))
print("图片总数为:",image_count)

 

图片总数为: 3400

 

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

 

batch_size = 8
img_height = 224
img_width = 224

 

TensorFlow版本是2.2.0的同学可能会遇到 module 'tensorflow.keras.preprocessing' has no attribute 'image_dataset_from_directory' 的报错,升级一下TensorFlow就OK了。

 

"""
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)

 

Found 3400 files belonging to 2 classes.
Using 2720 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=12,
    image_size=(img_height, img_width),
    batch_size=batch_size)

 

Found 3400 files belonging to 2 classes.
Using 680 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)

 

['cat', 'dog']

 

2. 再次检查数据

 

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

 

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

 

Image_batch
Label_batch

 

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
def 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)

 

如果报 AttributeError: module 'tensorflow._api.v2.data' has no attribute 'AUTOTUNE' 错误,就将 AUTOTUNE = tf.data.AUTOTUNE 更换为 AUTOTUNE = tf.data.experimental.AUTOTUNE ,这个错误是由于版本问题引起的。

 

4. 可视化数据

 

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")

 

 

三、构建VG-16网络

 

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(3×3)和最大池化尺寸(2×2)。

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。

 

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 fcXpredictions 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

 

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

 

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。
评价函数(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。

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

 

五、训练模型

 

from tqdm import tqdm
import tensorflow.keras.backend as K
epochs = 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)
    
    """
    total:预期的迭代数目
    ncols:控制进度条宽度
    mininterval:进度更新最小间隔,以秒为单位(默认值:0.1)
    """
    with tqdm(total=train_total, desc=f'Epoch {epoch + 1}/{epochs}',mininterval=1,ncols=100) as pbar:
        
        lr = lr*0.92
        K.set_value(model.optimizer.lr, lr)
        for image,label in train_ds:   
            """
            训练模型,简单理解train_on_batch就是:它是比model.fit()更高级的一个用法
            想详细了解 train_on_batch 的同学,
            可以看看我的这篇文章:https://www.yuque.com/mingtian-fkmxf/hv4lcq/ztt4gy
            """
            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)

 

Epoch 1/10: 100%|████████| 340/340 [00:25<00:00, 13.08it/s, loss=0.7219, accuracy=0.3750, lr=9.2e-5]
开始验证!
Epoch 1/10: 100%|█████████████████████| 85/85 [00:02<00:00, 32.83it/s, loss=0.6900, accuracy=0.5000]
结束验证!
验证loss为:0.6900
验证准确率为:0.5000
.......
Epoch 9/10: 100%|█████████████████████| 85/85 [00:02<00:00, 36.35it/s, loss=0.0008, accuracy=1.0000]
结束验证!
验证loss为:0.0008
验证准确率为:1.0000
Epoch 10/10: 100%|██████| 340/340 [00:21<00:00, 15.64it/s, loss=0.0066, accuracy=1.0000, lr=4.34e-5]
开始验证!
Epoch 10/10: 100%|████████████████████| 85/85 [00:02<00:00, 35.65it/s, loss=0.0002, accuracy=1.0000]
结束验证!
验证loss为:0.0002
验证准确率为:1.0000

 

# 这是我们之前的训练方法。
# history = model.fit(
#     train_ds,
#     validation_data=val_ds,
#     epochs=epochs
# )

 

六、模型评估

 

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()

 

 

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")

 

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

 

Be First to Comment

发表回复

您的电子邮箱地址不会被公开。