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GPUtf.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 keraswarnings.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 pathlibdata_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.AUTOTUNEdef 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, LearningRateSchedulerNO_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 DataFrameconf_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 metricsdef 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   supportAlfred_Sisley       0.76      0.98      0.86        53Edgar_Degas       0.89      0.94      0.92       132Francisco_Goya       0.89      0.69      0.77        70Marc_Chagall       0.85      0.94      0.89        48Pablo_Picasso       0.89      0.74      0.81        90Paul_Gauguin       0.94      0.84      0.89        57
Peter_Paul_Rubens       0.71      0.86      0.78        29Rembrandt       0.66      0.92      0.77        48Titian       0.90      0.72      0.80        65Vincent_van_Gogh       0.88      0.87      0.87       163accuracy                           0.85       755macro avg       0.84      0.85      0.84       755weighted avg       0.86      0.85      0.85       755Loss function: 0.5761227011680603, accuracy: 0.8490065932273865