CNN实战

最新推荐文章于 2025-09-26 20:56:34 发布

原创最新推荐文章于 2025-09-26 20:56:34 发布 · 1.6k 阅读

8 ·

CC 4.0 BY-SA版权

AI_算法专栏收录该内容

14 篇文章

订阅专栏

本文介绍了一种基于卷积神经网络(CNN)的猫狗图片识别模型的构建过程，模型使用Keras库实现，通过预处理图片数据，构建CNN模型，并在训练集上进行训练，最终在测试集上达到了较高的预测准确率。

学习笔记，自慕课网
**

CNN

在这里插入图片描述

基于dataset\training_set数据，根据提供的结构，建立CNN模型，识别图片中的猫/狗，计算预测准确率：
1.识别图片中的猫/狗、计算dataset\test_set测试数据预测准确率
2.从网站下载猫/狗图片，对其进行预测

1. Load data

#load the data
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale=1./255)

training_set = train_datagen.flow_from_directory('./dataset/training_set',target_size=(50,50),batch_size=32,class_mode='binary')

batch_size是代表从图片库里拿出32张图片
target_size是统一大小

2. 确认输入数据标签

#确认输入数据标签
training_set.class_indices

在这里插入图片描述

3. CNN Model开启

#set up the cnn model
from keras.models import Sequential
from keras.layers import Conv2D, MaxPool2D, Flatten, Dense

model = Sequential()
#卷积层
model.add(Conv2D(32,(3,3),input_shape=(50,50,3),activation='relu')) #输入图片
#池化层
model.add(MaxPool2D(pool_size=(2,2)))
#卷积层
model.add(Conv2D(32,(3,3),activation='relu'))
#池化层
model.add(MaxPool2D(pool_size=(2,2)))
#flattening layer
model.add(Flatten())
#FC layer
model.add(Dense(units=128,activation='relu'))
model.add(Dense(units=1,activation='sigmoid'))

4. 优化器使用

#configure the model
model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])
model.summary()

在这里插入图片描述

5. 模型训练

20次迭代，损失函数一直在下降
在这里插入图片描述

6. 模型训练数据准确率

#accuracy on the training data
accuracy_train = model.evaluate_generator(training_set)
print(accuracy_train)

7. 模型测试数据准确率

#accuracy on the test data
test_set = train_datagen.flow_from_directory('./dataset/test_set',target_size=(50,50),batch_size=32,class_mode='binary')

accuracy_test = model.evaluate_generator(test_set)
print(accuracy_test)

网上下载一张图片实测一下：

8. 测试网上一张dog的图片来预测看看

#load single image
from keras.preprocessing.image import load_img, img_to_array
pic_dog = 'dog.jpg'
pic_dog = load_img(pic_dog,target_size=(50,50))
pic_dog = img_to_array(pic_dog)
pic_dog = pic_dog/255
pic_dog = pic_dog.reshape(1,50,50,3)
result = model.predict_classes(pic_dog)
print(result)
pic_cat = 'cat1.jpg'
pic_cat = load_img(pic_cat,target_size=(50,50))
pic_cat = img_to_array(pic_cat)
pic_cat = pic_cat/255
pic_cat = pic_cat.reshape(1,50,50,3)
result = model.predict_classes(pic_cat)
print(result)
training_set.class_indices

9. 进行图片分类

# make prediction on multiple images
import matplotlib as mlp
font2 = {'family' : 'SimHei',
'weight' : 'normal',
'size'   : 20,
}
mlp.rcParams['font.family'] = 'SimHei'
mlp.rcParams['axes.unicode_minus'] = False
from matplotlib import pyplot as plt
from matplotlib.image import imread
from keras.preprocessing.image import load_img
from keras.preprocessing.image import img_to_array
from keras.models import load_model
a = [i for i in range(1,10)]
fig = plt.figure(figsize=(10,10))
for i in a:
    img_name = str(i)+'.jpg'
    img_ori = load_img(img_name, target_size=(50, 50))
    img = img_to_array(img_ori)
    img = img.astype('float32')/255
    img = img.reshape(1,50,50,3)
    result = model.predict_classes(img)
    img_ori = load_img(img_name, target_size=(250, 250))
    plt.subplot(3,3,i)
    plt.imshow(img_ori)
    plt.title('预测为：狗狗' if result[0][0] == 1 else '预测为：猫咪')
plt.show()

/* 基于dataset\training_set数据，根据提供的结构，建立CNN模型，识别图片中的猫/狗，计算预测准确率：
1.识别图片中的猫/狗、计算dataset\test_set测试数据预测准确率
2.从网站下载猫/狗图片，对其进行预测
/*
#load the data
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale=1./255)

training_set = train_datagen.flow_from_directory('./dataset/training_set',target_size=(50,50),batch_size=32,class_mode='binary')

#确认输入数据标签
training_set.class_indices
# {'cats': 0, 'dogs': 1}

#set up the cnn model
from keras.models import Sequential
from keras.layers import Conv2D, MaxPool2D, Flatten, Dense

model = Sequential()
#卷积层
model.add(Conv2D(32,(3,3),input_shape=(50,50,3),activation='relu'))
#池化层
model.add(MaxPool2D(pool_size=(2,2)))
#卷积层
model.add(Conv2D(32,(3,3),activation='relu'))
#池化层
model.add(MaxPool2D(pool_size=(2,2)))
#flattening layer
model.add(Flatten())
#FC layer
model.add(Dense(units=128,activation='relu'))
model.add(Dense(units=1,activation='sigmoid'))

#configure the model
model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])

model.summary()

#train the model
model.fit_generator(training_set,epochs=20)

#accuracy on the training data
accuracy_train = model.evaluate_generator(training_set)
print(accuracy_train)
# [0.00042246864177286625, 1.0]

#accuracy on the test data
test_set = train_datagen.flow_from_directory('./dataset/test_set',target_size=(50,50),batch_size=32,class_mode='binary')

accuracy_test = model.evaluate_generator(test_set)
print(accuracy_test)
# Found 2000 images belonging to 2 classes.
# [0.6088150143623352, 0.7599999904632568]

#load single image
from keras.preprocessing.image import load_img, img_to_array
pic_dog = 'dog.jpg'
pic_dog = load_img(pic_dog,target_size=(50,50))
pic_dog = img_to_array(pic_dog)
pic_dog = pic_dog/255
pic_dog = pic_dog.reshape(1,50,50,3)
result = model.predict_classes(pic_dog)
print(result)
# [[1]]

pic_cat = 'cat1.jpg'
pic_cat = load_img(pic_cat,target_size=(50,50))
pic_cat = img_to_array(pic_cat)
pic_cat = pic_cat/255
pic_cat = pic_cat.reshape(1,50,50,3)
result = model.predict_classes(pic_cat)
print(result)
# [[0]]

# make prediction on multiple images
import matplotlib as mlp
font2 = {'family' : 'SimHei',
'weight' : 'normal',
'size'   : 20,
}
mlp.rcParams['font.family'] = 'SimHei'
mlp.rcParams['axes.unicode_minus'] = False
from matplotlib import pyplot as plt
from matplotlib.image import imread
from keras.preprocessing.image import load_img
from keras.preprocessing.image import img_to_array
from keras.models import load_model
a = [i for i in range(1,10)]
fig = plt.figure(figsize=(10,10))
for i in a:
    img_name = str(i)+'.jpg'
    img_ori = load_img(img_name, target_size=(50, 50))
    img = img_to_array(img_ori)
    img = img.astype('float32')/255
    img = img.reshape(1,50,50,3)
    result = model.predict_classes(img)
    img_ori = load_img(img_name, target_size=(250, 250))
    plt.subplot(3,3,i)
    plt.imshow(img_ori)
    plt.title('预测为：狗狗' if result[0][0] == 1 else '预测为：猫咪')
plt.show()

在这里插入图片描述