TensorFlow2实战-系列教程5：猫狗识别2------数据增强

news2024/11/28 19:01:38

🧡💛💚TensorFlow2实战-系列教程总目录

有任何问题欢迎在下面留言
本篇文章的代码运行界面均在Jupyter Notebook中进行
本篇文章配套的代码资源已经上传

猫狗识别1
数据增强
猫狗识别2------数据增强
猫狗识别3------迁移学习

1、猫狗识别任务

import os
import warnings
warnings.filterwarnings("ignore")
import tensorflow as tf
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.preprocessing.image import ImageDataGenerator

base_dir = './data/cats_and_dogs'
train_dir = os.path.join(base_dir, 'train')
validation_dir = os.path.join(base_dir, 'validation')

train_cats_dir = os.path.join(train_dir, 'cats')
train_dogs_dir = os.path.join(train_dir, 'dogs')

validation_cats_dir = os.path.join(validation_dir, 'cats')
validation_dogs_dir = os.path.join(validation_dir, 'dogs')

model = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(32, (3,3), activation='relu', input_shape=(64, 64, 3)),
    tf.keras.layers.MaxPooling2D(2, 2),

    tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),

    tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),

    tf.keras.layers.Flatten(),

    tf.keras.layers.Dense(512, activation='relu'),

    tf.keras.layers.Dense(1, activation='sigmoid')
])

model.compile(loss='binary_crossentropy',
              optimizer=Adam(lr=1e-4),
              metrics=['acc'])

依次是导包、指定数据路径、构建模型、配置训练器等，这些都与前面TensorFlow2实战-系列教程3：猫狗识别1完全一致

2、数据增强

train_datagen = ImageDataGenerator(
      rescale=1./255,
      rotation_range=40,
      width_shift_range=0.2,
      height_shift_range=0.2,
      shear_range=0.2,
      zoom_range=0.2,
      horizontal_flip=True,
      fill_mode='nearest')

test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
        train_dir,  
        target_size=(64, 64),  
        batch_size=20,
        class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
        validation_dir,
        target_size=(64, 64),
        batch_size=20,
        class_mode='binary')

history = model.fit_generator(
      train_generator,
      steps_per_epoch=100,  # 2000 images = batch_size * steps
      epochs=100,
      validation_data=validation_generator,
      validation_steps=50,  # 1000 images = batch_size * steps
      verbose=2)

train_datagen：

这里将rescale重新缩放、旋转、平移变换、剪切变换、缩放、水平翻转、以临近方式填充等多种方式对训练数据进行数据增强
shear_range=0.2 表示图像将在 -0.2 到 +0.2 弧度的范围内随机剪切

test_datagen：

验证数据，没有进行数据增强，这里只进行了归一化操作

train_generator：

从 train_dir 目录加载训练图像，并应用前面定义的数据增强
target_size=(64, 64)：调整图像大小为 64x64 像素
batch_size=20：每批次处理 20 张图像
class_mode='binary'：因为是二分类任务。

validation_generator：

从 validation_dir 目录加载验证图像，只应用缩放

history：

（fit_generator 方法在 TensorFlow 2.2 之后已经被弃用，建议使用 fit 方法替代）
开始训练
validation_data=validation_generator：指定验证数据生成器
verbose=2：用于控制训练过程中输出的详细程度

3、预测效果展示

import matplotlib.pyplot as plt
acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']

epochs = range(len(acc))

plt.plot(epochs, acc, 'b', label='Training accuracy')
plt.plot(epochs, val_acc, 'r', label='Validation accuracy')
plt.title('Training and validation accuracy')
plt.legend()

plt.figure()

plt.plot(epochs, loss, 'b', label='Training Loss')
plt.plot(epochs, val_loss, 'r', label='Validation Loss')
plt.title('Training and validation loss')
plt.legend()

plt.show()

在这里插入图片描述

很显然经过数据增强后的模型表现对比原本效果有显著提升

3、加入Dropout

Dropout就是指定比例，对这一层随机杀死一下神经元，这里我们只需要在构建网络的时候在全连接层加上一层Dropout就可以了：

import os
import warnings
warnings.filterwarnings("ignore")
import tensorflow as tf
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.preprocessing.image import ImageDataGenerator
base_dir = './data/cats_and_dogs'
train_dir = os.path.join(base_dir, 'train')
validation_dir = os.path.join(base_dir, 'validation')

train_cats_dir = os.path.join(train_dir, 'cats')
train_dogs_dir = os.path.join(train_dir, 'dogs')

validation_cats_dir = os.path.join(validation_dir, 'cats')
validation_dogs_dir = os.path.join(validation_dir, 'dogs')
model = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(32, (3,3), activation='relu', input_shape=(64, 64, 3)),
    tf.keras.layers.MaxPooling2D(2, 2),

    tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),

    tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),

    tf.keras.layers.Flatten(),

    tf.keras.layers.Dense(512, activation='relu'),
    tf.keras.layers.Dropout(0.5),
    tf.keras.layers.Dense(1, activation='sigmoid')
])

model.compile(loss='binary_crossentropy',
              optimizer=Adam(lr=1e-4),
              metrics=['acc'])
train_datagen = ImageDataGenerator(
      rescale=1./255,
      rotation_range=40,
      width_shift_range=0.2,
      height_shift_range=0.2,
      shear_range=0.2,
      zoom_range=0.2,
      horizontal_flip=True,
      fill_mode='nearest')

test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
        train_dir,  
        target_size=(64, 64),  
        batch_size=20,
        class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
        validation_dir,
        target_size=(64, 64),
        batch_size=20,
        class_mode='binary')

history = model.fit_generator(
      train_generator,
      steps_per_epoch=100,  # 2000 images = batch_size * steps
      epochs=100,
      validation_data=validation_generator,
      validation_steps=50,  # 1000 images = batch_size * steps
      verbose=2)