行业知识
深度学习Week15——利用TensorFlow实现猫狗识别2
2026-11-12 05:49:09
来源：互联网转载
文章目录
深度学习Week15——利用TensorFlow实现猫狗识别2—数据增强
一、前言
二、我的环境
三、前期工作
1、配置环境
2、导入数据
四、数据预处理
1、加载数据
2、可视化数据
3、检查数据
4、配置数据集
五、构建VGG-16模型
1、设置动态学习率
2、早停与保存最佳模型参数
五、编译模型
六、训练模型
七、预测与评估
1、Accuracy图
2、指定图像预测
八、数据增强
一、前言
- 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
本篇内容分为两个部分，前面部分是学习K同学给的算法知识点以及复现，后半部分是自己的拓展与未解决的问题
本期学习内容较少，代码与上周类似，主要是理解了上周未解决的小bug，并尝试通过上下翻转使数据增强，下周系统学习数据增强函数并自己实现一个增强函数
二、我的环境
- 电脑系统：Windows 10
- 语言环境：Python 3.8.0
- 编译器：Pycharm2023.2.3
深度学习环境：TensorFlow
显卡及显存：RTX 3060 8G
三、前期工作
1、导入库并配置环境
import tensorflow as tfgpus = 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')]
这一步与pytorch第一步类似，我们在写神经网络程序前无论是选择pytorch还是tensorflow都应该配置好gpu环境（如果有gpu的话）
2、 导入数据
导入所有猫狗图片数据，依次分别为训练集图片(train_images)、训练集标签(train_labels)、测试集图片(test_images)、测试集标签(test_labels)，数据集来源于K同学啊
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 warningswarnings.filterwarnings('ignore')data_dir = "/home/mw/input/dogcat3675/365-7-data"data_dir = pathlib.Path(data_dir)image_count = len(list(data_dir.glob('*/*')))print("图片总数为：",image_count)#查看第一张图片：图片总数为： 3400
四、数据预处理
1、加载数据
batch_size = 64img_height = 224img_width = 224
使用image_dataset_from_directory方法将磁盘中的数据加载到tf.data.Dataset中
tf.keras.preprocessing.image_dataset_from_directory()会将文件夹中的数据加载到tf.data.Dataset中，且加载的同时会打乱数据。
- class_names
- validation_split: 0和1之间的可选浮点数，可保留一部分数据用于验证。
- subset: training或validation之一。仅在设置validation_split时使用。
- seed: 用于shuffle和转换的可选随机种子。
- batch_size: 数据批次的大小。默认值：32
- image_size: 从磁盘读取数据后将其重新调整大小。默认：（256，256）。由于管道处理的图像批次必须具有相同的大小，因此该参数必须提供。
"""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)
输出：
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)
输出：
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_namesprint(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
(64, 224, 224, 3)
(64,)
Image_batch是形状的张量（64,224,224,3）。这是一批形状224x224x3的64张图片（最后一维指的是彩色通道RGB。
Label_batch是形状（64，）的张量，这些标签对应64张图片
3、配置数据集
- shuffle():打乱数据
- prefetch():预取数据，加速运行
- cache()：将数据集缓存到内存当中，加速运行
如果不使用prefetch()，CPU 和 GPU/TPU 在大部分时间都处于空闲状态：
使用prefetch()可显著减少空闲时间：
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)
4. 数据可视化
plt.figure(figsize=(12, 10)) # 图形的宽为15高为10for 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")五 、构建VGG-16模型
- 输入层：
输入层负责接收原始数据，将数据传递到网络中的第一层。
- 卷积层：
卷积层使用卷积核对输入数据进行滤波操作，以提取图像中的特征。
- 池化层：
池化层用于对卷积层的输出进行下采样，以减少数据的维度和计算量。
- 全连接层：
全连接层起到“特征提取器”的作用，将前面层的特征表示映射到输出层。
- 输出层：
输出层负责输出模型的预测结果。
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
from tensorflow.keras import layers, models, Inputfrom tensorflow.keras.models import Modelfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Flatten, Dropoutdef 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 modelmodel=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: 138,357,544Trainable params: 138,357,544Non-trainable params: 0_________________________________________________________________
自己构建VGG-16模型
首先，导入了必要的模块：layers, models, tensorflow.keras库的模块，用于构建神经网络模型。
其次，定义函数VGG16(nb_classes, input_shape)，接受两个参数：类别：nb_classes和形状 input_shape 表示输入数据的形状。
通过Input函数创建了一个输入张量input_tensor，形状为input_shape按照VGG16的结构，定义卷积层和池化层：
使用 ReLU 作为激活函数，让卷积层分布在不同的block中，每个block中有若干个卷积层，每个block之间有一个池化层。每个卷积层后面跟着一个池化层，通过MaxPooling2D函数实现。
在所有卷积和池化层之后，添加了全连接层：
通过Flatten层将卷积层输出的特征图展平成一维向量。
然后通过两个Dense层定义包含4096个神经元的全连接层，每个层包含4096个神经元，并使用 ReLU 作为激活函数。
六、编译模型
具体函数解释参考第八周博客或者K同学啊的博客！
- 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'])
七、训练模型
from tqdm import tqdmimport tensorflow.keras.backend as Kepochs = 10lr = 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)七、预测
1、Accuracy图与Loss图
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()结果：
2. 指定数据预测
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5plt.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")八、数据增强
我们使用tf.keras.layers.experimental.preprocessing.RandomFlip：水平和垂直随机翻转每个图像来增强数据，来生成大量的不同但相关的图像。这些变换使模型在训练过程中能够看到更多的变化，从而增强其对不同情况下的泛化能力，同时可以学习到更为普遍的特征，从而降低过拟合的风险
data_augmentation = tf.keras.Sequential(tf.keras.layers.experimental.preprocessing.RandomFlip("horizontal_and_vertical"))# Add the image to a batch.image = tf.expand_dims(images[i], 0)plt.figure(figsize=(8, 8))for i in range(9): augmented_image = data_augmentation(image) ax = plt.subplot(3, 3, i + 1) plt.imshow(augmented_image[0]) plt.axis("off")batch_size = 32AUTOTUNE = tf.data.AUTOTUNEdef prepare(ds): ds = ds.map(lambda x, y: (data_augmentation(x, training=True), y), num_parallel_calls=AUTOTUNE) return ds train_ds = prepare(train_ds)from tensorflow.keras import layers, models, Inputfrom tensorflow.keras.models import Modelfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Flatten, Dropoutmodel = tf.keras.Sequential([ layers.Conv2D(16, 3, padding='same', activation='relu'), layers.MaxPooling2D(), layers.Conv2D(32, 3, padding='same', activation='relu'), layers.MaxPooling2D(), layers.Conv2D(64, 3, padding='same', activation='relu'), layers.MaxPooling2D(), layers.Flatten(), layers.Dense(128, activation='relu'), layers.Dense(len(class_names))])model.compile(optimizer='adam', loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), metrics=['accuracy'])epochs=20history = model.fit( train_ds, validation_data=val_ds, epochs=epochs)
Epoch 1/2043/43 [==============================] - 18s 103ms/step - loss: 1.2824 - accuracy: 0.5495 - val_loss: 0.4272 - val_accuracy: 0.8941Epoch 2/2043/43 [==============================] - 3s 55ms/step - loss: 0.3326 - accuracy: 0.8815 - val_loss: 0.1882 - val_accuracy: 0.9309Epoch 3/2043/43 [==============================] - 3s 54ms/step - loss: 0.1614 - accuracy: 0.9488 - val_loss: 0.1493 - val_accuracy: 0.9412Epoch 4/2043/43 [==============================] - 2s 54ms/step - loss: 0.1215 - accuracy: 0.9557 - val_loss: 0.0950 - val_accuracy: 0.9721Epoch 5/2043/43 [==============================] - 3s 54ms/step - loss: 0.0906 - accuracy: 0.9666 - val_loss: 0.0791 - val_accuracy: 0.9691Epoch 6/2043/43 [==============================] - 3s 56ms/step - loss: 0.0614 - accuracy: 0.9768 - val_loss: 0.1131 - val_accuracy: 0.9559Epoch 7/2043/43 [==============================] - 3s 55ms/step - loss: 0.0603 - accuracy: 0.9807 - val_loss: 0.0692 - val_accuracy: 0.9794Epoch 8/2043/43 [==============================] - 3s 55ms/step - loss: 0.0577 - accuracy: 0.9793 - val_loss: 0.0609 - val_accuracy: 0.9779Epoch 9/2043/43 [==============================] - 3s 55ms/step - loss: 0.0511 - accuracy: 0.9825 - val_loss: 0.0546 - val_accuracy: 0.9779Epoch 10/2043/43 [==============================] - 3s 55ms/step - loss: 0.0462 - accuracy: 0.9871 - val_loss: 0.0628 - val_accuracy: 0.9765Epoch 11/2043/43 [==============================] - 3s 55ms/step - loss: 0.0327 - accuracy: 0.9895 - val_loss: 0.0790 - val_accuracy: 0.9721Epoch 12/2043/43 [==============================] - 3s 55ms/step - loss: 0.0242 - accuracy: 0.9938 - val_loss: 0.0580 - val_accuracy: 0.9794Epoch 13/2043/43 [==============================] - 3s 55ms/step - loss: 0.0354 - accuracy: 0.9907 - val_loss: 0.0797 - val_accuracy: 0.9735Epoch 14/2043/43 [==============================] - 3s 55ms/step - loss: 0.0276 - accuracy: 0.9900 - val_loss: 0.0810 - val_accuracy: 0.9691Epoch 15/2043/43 [==============================] - 3s 56ms/step - loss: 0.0243 - accuracy: 0.9931 - val_loss: 0.1063 - val_accuracy: 0.9676Epoch 16/2043/43 [==============================] - 3s 56ms/step - loss: 0.0253 - accuracy: 0.9914 - val_loss: 0.1142 - val_accuracy: 0.9721Epoch 17/2043/43 [==============================] - 3s 56ms/step - loss: 0.0205 - accuracy: 0.9937 - val_loss: 0.0726 - val_accuracy: 0.9706Epoch 18/2043/43 [==============================] - 3s 56ms/step - loss: 0.0154 - accuracy: 0.9948 - val_loss: 0.0741 - val_accuracy: 0.9765Epoch 19/2043/43 [==============================] - 3s 56ms/step - loss: 0.0155 - accuracy: 0.9966 - val_loss: 0.0870 - val_accuracy: 0.9721Epoch 20/2043/43 [==============================] - 3s 55ms/step - loss: 0.0259 - accuracy: 0.9907 - val_loss: 0.1194 - val_accuracy: 0.9721
loss, acc = model.evaluate(test_ds)print("Accuracy", acc)2/2 [==============================] - 0s 15ms/step - loss: 0.0521 - accuracy: 1.0000Accuracy 1.0
- 输入层：
上一篇：连接服务器怎么查记录密码?
下一篇：绝地求生怎么下载？
