第T9周：猫狗识别2

• 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
• 🍖 原作者：K同学啊 | 接辅导、项目定制

一、前期工作

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)  
    tf.config.set_visible_devices([gpus[0]],"GPU")

print(gpus)

输出
[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 = "./P8/"
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： 3402

二、数据预处理

1.加载数据

batch_size = 64
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)

输出
Found 3403 files belonging to 2 classes.
Using 2723 files for training.

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)

输出
Found 3403 files belonging to 2 classes.
Using 680 files for validation.

class_names = train_ds.class_names
print(class_names)

输出
[‘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

输出
(64, 224, 224, 3)
(64,)# 3.配置数据集

代码知识点

1. tf.data.AUTOTUNE是一个特殊的值，用于在TensorFlow中自动调整数据集的并行处理参数。
2. 定义了preprocess_image函数，它接受两个参数：image和label。这个函数的作用是将输入的图像进行归一化处理，即将像素值除以255，使得像素值的范围在0到1之间。同时，函数返回一个元组，包含归一化后的图像和对应的标签。
3. 分别对训练集（train_ds）和验证集（val_ds）进行映射操作。映射操作使用preprocess_image函数对每个元素进行处理，并使用num_parallel_calls=AUTOTUNE参数来指定并行调用的数量。这样可以在多个CPU核心上并行处理数据，提高数据处理速度。
4. 最后两行代码对训练集和验证集进行了缓存、随机打乱和预取操作。缓存操作将数据集存储在内存中，以便快速访问；随机打乱操作将数据集中的样本随机排列；预取操作则在数据读取时提前加载一部分数据到内存中，以便后续操作能够更快地获取数据。这些操作可以提高数据处理的效率。

AUTOTUNE = tf.data.experimental.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)

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")

输出

三、构建VGG网络

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()

输出

四、编译

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

五、训练模型

这是精简化后的代码

使用 with tqdm() 作为上下文管理器可以简化代码，
并在循环中直接使用 pbar 而不是手动更新进度条。
不需要在循环开始时设置学习率，可以在训练循环开始之前设置它。
可以合并训练和验证的准确性和损失值的计算，以减少重复代码。

from tqdm import tqdm
import tensorflow.keras.backend as K

epochs = 10
lr = 1e-4

history_train_loss = []
history_train_accuracy = []
history_val_loss = []
history_val_accuracy = []

for epoch in range(epochs):
    
    train_loss = []
    train_accuracy = []
    val_loss = []
    val_accuracy = []

    pbar_train = tqdm(total=len(train_ds), desc=f'Epoch {epoch + 1}/{epochs}', mininterval=43, ncols=100)
    pbar_val = tqdm(total=len(val_ds), desc=f'Epoch {epoch + 1}/{epochs}', mininterval=11, ncols=100)
    
    lr = lr * 0.97
    K.set_value(model.optimizer.lr, lr)
    
    for image, label in train_ds:
        history = model.train_on_batch(image, label)
        train_loss.append(history[0])
        train_accuracy.append(history[1])
        pbar_train.set_postfix({"train_loss": "%.4f" % history[0],
                                "train_acc": "%.4f" % history[1],
                                "lr": K.get_value(model.optimizer.lr)})
        pbar_train.update(1)

    history_train_loss.append(np.mean(train_loss))
    history_train_accuracy.append(np.mean(train_accuracy))

    print('开始验证！')

    for image, label in val_ds:
        history = model.test_on_batch(image, label)
        val_loss.append(history[0])
        val_accuracy.append(history[1])
        pbar_val.set_postfix({"val_loss": "%.4f" % history[0],
                              "val_acc": "%.4f" % history[1]})
        pbar_val.update(1)

    history_val_loss.append(np.mean(val_loss))
    history_val_accuracy.append(np.mean(val_accuracy))
    
   
    
    print('结束验证！')
    print("验证loss为：%.4f" % np.mean(val_loss))
    print("验证准确率为：%.4f" % np.mean(val_accuracy))

输出
Epoch 1/10: 100%|███| 86/86 [00:11<00:00, 7.64it/s, train_loss=0.1023, train_acc=0.9688, lr=9.2e-5]
开始验证！
Epoch 1/10: 100%|██████████████████| 22/22 [00:01<00:00, 17.22it/s, val_loss=0.0022, val_acc=1.0000]
结束验证！
验证loss为：0.0730
验证准确率为：0.9673
Epoch 2/10: 100%|██| 86/86 [00:11<00:00, 7.80it/s, train_loss=0.0050, train_acc=1.0000, lr=8.46e-5]
开始验证！
Epoch 2/10: 100%|██████████████████| 22/22 [00:01<00:00, 18.04it/s, val_loss=0.1671, val_acc=0.8750]
结束验证！
验证loss为：0.0382
验证准确率为：0.9830
Epoch 3/10: 100%|██| 86/86 [00:11<00:00, 7.80it/s, train_loss=0.0034, train_acc=1.0000, lr=7.79e-5]
开始验证！
Epoch 3/10: 100%|██████████████████| 22/22 [00:01<00:00, 16.95it/s, val_loss=0.6676, val_acc=0.8750]
结束验证！
验证loss为：0.0675
验证准确率为：0.9801
Epoch 4/10: 100%|██| 86/86 [00:11<00:00, 7.79it/s, train_loss=0.0008, train_acc=1.0000, lr=7.16e-5]
开始验证！
Epoch 4/10: 100%|██████████████████| 22/22 [00:01<00:00, 18.16it/s, val_loss=0.4470, val_acc=0.8750]
结束验证！
验证loss为：0.0327
验证准确率为：0.9901
Epoch 5/10: 100%|██| 86/86 [00:11<00:00, 7.80it/s, train_loss=0.0001, train_acc=1.0000, lr=6.59e-5]
开始验证！
Epoch 5/10: 100%|██████████████████| 22/22 [00:01<00:00, 17.79it/s, val_loss=0.0001, val_acc=1.0000]
结束验证！
验证loss为：0.0127
验证准确率为：0.9972
Epoch 6/10: 100%|██| 86/86 [00:10<00:00, 7.87it/s, train_loss=0.0007, train_acc=1.0000, lr=6.06e-5]
开始验证！
Epoch 6/10: 100%|██████████████████| 22/22 [00:01<00:00, 17.76it/s, val_loss=0.0000, val_acc=1.0000]
结束验证！
验证loss为：0.0211
验证准确率为：0.9972
Epoch 7/10: 100%|██| 86/86 [00:10<00:00, 7.86it/s, train_loss=0.0000, train_acc=1.0000, lr=5.58e-5]
开始验证！
Epoch 7/10: 100%|██████████████████| 22/22 [00:01<00:00, 17.68it/s, val_loss=0.0002, val_acc=1.0000]
结束验证！
验证loss为：0.0187
验证准确率为：0.9986
Epoch 8/10: 100%|██| 86/86 [00:10<00:00, 7.86it/s, train_loss=0.0000, train_acc=1.0000, lr=5.13e-5]
开始验证！
Epoch 8/10: 100%|██████████████████| 22/22 [00:01<00:00, 17.66it/s, val_loss=0.0002, val_acc=1.0000]
结束验证！
验证loss为：0.0182
验证准确率为：0.9986
Epoch 9/10: 100%|██| 86/86 [00:11<00:00, 7.76it/s, train_loss=0.0000, train_acc=1.0000, lr=4.72e-5]
开始验证！
Epoch 9/10: 100%|██████████████████| 22/22 [00:01<00:00, 17.53it/s, val_loss=0.0002, val_acc=1.0000]
结束验证！
验证loss为：0.0186
验证准确率为：0.9986
Epoch 10/10: 100%|█| 86/86 [00:11<00:00, 7.80it/s, train_loss=0.0001, train_acc=1.0000, lr=4.34e-5]
开始验证！
Epoch 10/10: 100%|█████████████████| 22/22 [00:01<00:00, 16.99it/s, val_loss=0.0002, val_acc=1.0000]
结束验证！
验证loss为：0.0186
验证准确率为：0.9986

六、模型评估

epochs_range = range(epochs)

plt.figure(figsize=(14, 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()

输出

七、预测

import numpy as np

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)  
        
        plt.imshow(images[i].numpy())
        
        img_array = tf.expand_dims(images[i], 0) 
        
        predictions = model.predict(img_array)
        plt.title(class_names[np.argmax(predictions)])

        plt.axis("off")

输出