卷积神经网络（CNN）：艺术作品识别

一、前言

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

往期精彩内容：

• 卷积神经网络（CNN）实现mnist手写数字识别
• 卷积神经网络（CNN）多种图片分类的实现
• 卷积神经网络（CNN）衣服图像分类的实现
• 卷积神经网络（CNN）鲜花识别
• 卷积神经网络（CNN）天气识别
• 卷积神经网络（VGG-16）识别海贼王草帽一伙
• 卷积神经网络（ResNet-50）鸟类识别
• 卷积神经网络（AlexNet）鸟类识别
• 卷积神经网络(CNN)识别验证码

来自专栏：机器学习与深度学习算法推荐

一、设置GPU

import tensorflow as tf
gpus = tf.config.list_physical_devices("GPU")

if gpus:
    gpu0 = gpus[0] #如果有多个GPU，仅使用第0个GPU
    tf.config.experimental.set_memory_growth(gpu0, True) #设置GPU显存用量按需使用
    tf.config.set_visible_devices([gpu0],"GPU")
    
import matplotlib.pyplot as plt
import os,PIL,pathlib
import numpy as np
import pandas as pd
import warnings
from tensorflow import keras

warnings.filterwarnings("ignore")#忽略警告信息
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

二、导入数据

1. 导入数据

import pathlib

data_dir = "./27-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： 3776

batch_size = 16
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)

Found 3776 files belonging to 10 classes.
Using 3021 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)

Found 3776 files belonging to 10 classes.
Using 755 files for validation.

class_names = train_ds.class_names
print(class_names)

['Alfred_Sisley', 'Edgar_Degas', 'Francisco_Goya', 'Marc_Chagall', 'Pablo_Picasso', 'Paul_Gauguin', 'Peter_Paul_Rubens', 'Rembrandt', 'Titian', 'Vincent_van_Gogh']

2. 检查数据

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

(16, 224, 224, 3)
(16,)

3. 配置数据集

AUTOTUNE = tf.data.AUTOTUNE

def train_preprocessing(image,label):
    return (image/255.0,label)

train_ds = (
    train_ds.cache()
    .shuffle(2000)
    .map(train_preprocessing)    # 这里可以设置预处理函数
#     .batch(batch_size)           # 在image_dataset_from_directory处已经设置了batch_size
    .prefetch(buffer_size=AUTOTUNE)
)

val_ds = (
    val_ds.cache()
    .shuffle(2000)
    .map(train_preprocessing)    # 这里可以设置预处理函数
#     .batch(batch_size)         # 在image_dataset_from_directory处已经设置了batch_size
    .prefetch(buffer_size=AUTOTUNE)
)

4. 数据可视化

plt.figure(figsize=(10, 8))  # 图形的宽为10高为5
plt.suptitle("数据展示")

for images, labels in train_ds.take(1):
    for i in range(15):
        plt.subplot(4, 5, i + 1)
        plt.xticks([])
        plt.yticks([])
        plt.grid(False)

        # 显示图片
        plt.imshow(images[i])
        # 显示标签
        plt.xlabel(class_names[labels[i]-1])

plt.show()

三、构建模型

from tensorflow.keras import layers, models, Input
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Flatten, Dropout,BatchNormalization,Activation

# Load pre-trained model
base_model = keras.applications.ResNet50(weights='imagenet', include_top=False, input_shape=(img_width,img_height,3))

for layer in base_model.layers:
    layer.trainable = True
    
# Add layers at the end
X = base_model.output
X = Flatten()(X)

X = Dense(512, kernel_initializer='he_uniform')(X)
#X = Dropout(0.5)(X)
X = BatchNormalization()(X)
X = Activation('relu')(X)

X = Dense(16, kernel_initializer='he_uniform')(X)
#X = Dropout(0.5)(X)
X = BatchNormalization()(X)
X = Activation('relu')(X)

output = Dense(len(class_names), activation='softmax')(X)

model = Model(inputs=base_model.input, outputs=output)

四、编译

optimizer = tf.keras.optimizers.Adam(lr=1e-4)

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

五、训练模型

from tensorflow.keras.callbacks import ModelCheckpoint, Callback, EarlyStopping, ReduceLROnPlateau, LearningRateScheduler

NO_EPOCHS = 15
PATIENCE  = 5
VERBOSE   = 1

# 设置动态学习率
# annealer = LearningRateScheduler(lambda x: 1e-3 * 0.99 ** (x+NO_EPOCHS))

# 设置早停
earlystopper = EarlyStopping(monitor='loss', patience=PATIENCE, verbose=VERBOSE)

# 
checkpointer = ModelCheckpoint('best_model.h5',
                                monitor='val_accuracy',
                                verbose=VERBOSE,
                                save_best_only=True,
                                save_weights_only=True)

train_model  = model.fit(train_ds,
                  epochs=NO_EPOCHS,
                  verbose=1,
                  validation_data=val_ds,
                  callbacks=[earlystopper, checkpointer])

六、评估模型

1. Accuracy与Loss图

acc = train_model.history['accuracy']
val_acc = train_model.history['val_accuracy']

loss = train_model.history['loss']
val_loss = train_model.history['val_loss']

epochs_range = range(len(acc))

plt.figure(figsize=(12, 4))
plt.subplot(1, 2, 1)

plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss, label='Training Loss')
plt.plot(epochs_range, val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

2. 混淆矩阵

from sklearn.metrics import confusion_matrix
import seaborn as sns
import pandas as pd

# 定义一个绘制混淆矩阵图的函数
def plot_cm(labels, predictions):
    
    # 生成混淆矩阵
    conf_numpy = confusion_matrix(labels, predictions)
    # 将矩阵转化为 DataFrame
    conf_df = pd.DataFrame(conf_numpy, index=class_names ,columns=class_names)  
    
    plt.figure(figsize=(8,7))
    
    sns.heatmap(conf_df, annot=True, fmt="d", cmap="BuPu")
    
    plt.title('混淆矩阵',fontsize=15)
    plt.ylabel('真实值',fontsize=14)
    plt.xlabel('预测值',fontsize=14)

val_pre   = []
val_label = []

for images, labels in val_ds:#这里可以取部分验证数据（.take(1)）生成混淆矩阵
    for image, label in zip(images, labels):
        # 需要给图片增加一个维度
        img_array = tf.expand_dims(image, 0) 
        # 使用模型预测图片中的人物
        prediction = model.predict(img_array)

        val_pre.append(class_names[np.argmax(prediction)])
        val_label.append(class_names[label])

plot_cm(val_label, val_pre)

3. 各项指标评估

from sklearn import metrics

def test_accuracy_report(model):
    print(metrics.classification_report(val_label, val_pre, target_names=class_names)) 
    score = model.evaluate(val_ds, verbose=0)
    print('Loss function: %s, accuracy:' % score[0], score[1])
    
test_accuracy_report(model)

											precision    recall  f1-score   support

    Alfred_Sisley       0.76      0.98      0.86        53
      Edgar_Degas       0.89      0.94      0.92       132
   Francisco_Goya       0.89      0.69      0.77        70
     Marc_Chagall       0.85      0.94      0.89        48
    Pablo_Picasso       0.89      0.74      0.81        90
     Paul_Gauguin       0.94      0.84      0.89        57
Peter_Paul_Rubens       0.71      0.86      0.78        29
        Rembrandt       0.66      0.92      0.77        48
           Titian       0.90      0.72      0.80        65
 Vincent_van_Gogh       0.88      0.87      0.87       163

         accuracy                           0.85       755
        macro avg       0.84      0.85      0.84       755
     weighted avg       0.86      0.85      0.85       755

Loss function: 0.5761227011680603, accuracy: 0.8490065932273865