可以用于毕设参考！请勿过度借鉴

AI 2年前 (2022) admin

614 0 0

大家好，我是K同学啊！

今天和大家分享一个本科毕设实战项目（基于深度学习的交通标志识别算法对比研究），项目中我将使用VGG16、InceptionV3、DenseNet121、MobileNetV2 等四个模型进行对比分析（文中提供了每一个模型的算法框架图），最后可以自选图片进行预测，最后的识别效果高达 99.2%。结果如下：

文章目录

一、导入数据

二、定义模型

1. VGG16模型

2. InceptionV3模型

3. DenseNet121算法模型

4. MobileNetV2算法模型

三、结果分析

1. 准确率对比分析

2. 损失函数对比分析

3. 混淆矩阵

4. 评估指标生成

四、指定图片进行预测

一、导入数据

"""
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(
    "./1-data/",
    validation_split=0.2,
    subset="training",
    seed=12,
    image_size=(img_height, img_width),
    batch_size=batch_size)

Found 1308 files belonging to 14 classes.
Using 1047 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(
    "./1-data/",
    validation_split=0.2,
    subset="validation",
    seed=12,
    image_size=(img_height, img_width),
    batch_size=batch_size)

Found 1308 files belonging to 14 classes.
Using 261 files for validation.

class_names = train_ds.class_names
print(class_names)

['15', '16', '17', '20', '22', '23', '24', '26', '27', '28', '29', '30', '31', '32']

train_ds

<BatchDataset shapes: ((None, 224, 224, 3), (None,)), types: (tf.float32, tf.int32)>

AUTOTUNE = tf.data.AUTOTUNE

# 归一化
def train_preprocessing(image,label):
    return (image/255.0,label)

train_ds = (
    train_ds.cache()
    .map(train_preprocessing)    # 这里可以设置预处理函数
    .prefetch(buffer_size=AUTOTUNE)
)

val_ds = (
    val_ds.cache()
    .map(train_preprocessing)    # 这里可以设置预处理函数
    .prefetch(buffer_size=AUTOTUNE)
)

plt.figure(figsize=(10, 8))  # 图形的宽为10高为5

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[int(labels[i])])

plt.show()

二、定义模型

1. VGG16模型

# 加载预训练模型
vgg16_base_model = tf.keras.applications.vgg16.VGG16(weights='imagenet',
                                                            include_top=False,
                                                            # input_tensor=tf.keras.Input(shape=(img_width, img_height, 3)),
                                                            input_shape=(img_width, img_height, 3),
                                                            pooling='max')
for layer in vgg16_base_model.layers:
    layer.trainable = False
    
X = vgg16_base_model.output
X = Dropout(0.4)(X)

output = Dense(len(class_names), activation='softmax')(X)
vgg16_model = Model(inputs=vgg16_base_model.input, outputs=output)

vgg16_model.compile(optimizer="adam",
                loss='sparse_categorical_crossentropy',
                metrics=['accuracy'])
# vgg16_model.summary()

vgg16_history  = vgg16_model.fit(train_ds, epochs=epochs, verbose=1, validation_data=val_ds)

Epoch 1/10
33/33 [==============================] - 8s 113ms/step - loss: 2.7396 - accuracy: 0.2531 - val_loss: 1.4678 - val_accuracy: 0.6092
Epoch 2/10
33/33 [==============================] - 2s 45ms/step - loss: 1.5873 - accuracy: 0.5091 - val_loss: 0.8500 - val_accuracy: 0.8046
Epoch 3/10
33/33 [==============================] - 2s 45ms/step - loss: 1.0996 - accuracy: 0.6495 - val_loss: 0.5299 - val_accuracy: 0.9272
Epoch 4/10
33/33 [==============================] - 2s 45ms/step - loss: 0.7349 - accuracy: 0.7947 - val_loss: 0.3765 - val_accuracy: 0.9349
Epoch 5/10
33/33 [==============================] - 2s 45ms/step - loss: 0.5373 - accuracy: 0.8481 - val_loss: 0.2888 - val_accuracy: 0.9502
Epoch 6/10
33/33 [==============================] - 2s 45ms/step - loss: 0.4326 - accuracy: 0.8892 - val_loss: 0.2422 - val_accuracy: 0.9617
Epoch 7/10
33/33 [==============================] - 2s 45ms/step - loss: 0.3350 - accuracy: 0.9198 - val_loss: 0.2068 - val_accuracy: 0.9693
Epoch 8/10
33/33 [==============================] - 2s 45ms/step - loss: 0.2821 - accuracy: 0.9398 - val_loss: 0.1713 - val_accuracy: 0.9885
Epoch 9/10
33/33 [==============================] - 2s 45ms/step - loss: 0.2489 - accuracy: 0.9456 - val_loss: 0.1589 - val_accuracy: 0.9847
Epoch 10/10
33/33 [==============================] - 2s 48ms/step - loss: 0.2146 - accuracy: 0.9608 - val_loss: 0.1511 - val_accuracy: 0.9885

2. InceptionV3模型

# 加载预训练模型
InceptionV3_base_model = tf.keras.applications.inception_v3.InceptionV3(weights='imagenet',
                                                            include_top=False,
                                                            input_shape=(img_width, img_height, 3),
                                                            pooling='max')
for layer in InceptionV3_base_model.layers:
    layer.trainable = False
    
X = InceptionV3_base_model.output
X = Dropout(0.4)(X)

output = Dense(len(class_names), activation='softmax')(X)
InceptionV3_model = Model(inputs=InceptionV3_base_model.input, outputs=output)

InceptionV3_model.compile(optimizer="adam",
                loss='sparse_categorical_crossentropy',
                metrics=['accuracy'])
# InceptionV3_model.summary()

InceptionV3_history  = InceptionV3_model.fit(train_ds, epochs=epochs, verbose=1, validation_data=val_ds)

Epoch 1/10
33/33 [==============================] - 5s 82ms/step - loss: 3.1642 - accuracy: 0.4040 - val_loss: 0.6005 - val_accuracy: 0.8352
Epoch 2/10
33/33 [==============================] - 1s 34ms/step - loss: 0.7241 - accuracy: 0.8042 - val_loss: 0.2476 - val_accuracy: 0.9234
Epoch 3/10
33/33 [==============================] - 1s 34ms/step - loss: 0.3558 - accuracy: 0.8949 - val_loss: 0.2323 - val_accuracy: 0.9425
Epoch 4/10
33/33 [==============================] - 1s 35ms/step - loss: 0.2435 - accuracy: 0.9226 - val_loss: 0.1599 - val_accuracy: 0.9617
Epoch 5/10
33/33 [==============================] - 1s 34ms/step - loss: 0.1444 - accuracy: 0.9551 - val_loss: 0.1246 - val_accuracy: 0.9617
Epoch 6/10
33/33 [==============================] - 1s 34ms/step - loss: 0.1508 - accuracy: 0.9522 - val_loss: 0.1231 - val_accuracy: 0.9732
Epoch 7/10
33/33 [==============================] - 1s 35ms/step - loss: 0.0793 - accuracy: 0.9761 - val_loss: 0.0853 - val_accuracy: 0.9885
Epoch 8/10
33/33 [==============================] - 1s 35ms/step - loss: 0.0636 - accuracy: 0.9809 - val_loss: 0.1223 - val_accuracy: 0.9732
Epoch 9/10
33/33 [==============================] - 1s 35ms/step - loss: 0.0503 - accuracy: 0.9857 - val_loss: 0.0769 - val_accuracy: 0.9923
Epoch 10/10
33/33 [==============================] - 1s 34ms/step - loss: 0.0346 - accuracy: 0.9904 - val_loss: 0.1066 - val_accuracy: 0.9923

3. DenseNet121算法模型

可以用于毕设参考！请勿过度借鉴

# 加载预训练模型
DenseNet121_base_model = tf.keras.applications.densenet.DenseNet121(weights='imagenet',
                                                            include_top=False,
                                                            input_shape=(img_width, img_height, 3),
                                                            pooling='max')
for layer in DenseNet121_base_model.layers:
    layer.trainable = False
    
X = DenseNet121_base_model.output
X = Dropout(0.4)(X)

output = Dense(len(class_names), activation='softmax')(X)
DenseNet121_model = Model(inputs=DenseNet121_base_model.input, outputs=output)

DenseNet121_model.compile(optimizer="adam",
                loss='sparse_categorical_crossentropy',
                metrics=['accuracy'])
# model.summary()

DenseNet121_history  = DenseNet121_model.fit(train_ds, epochs=epochs, verbose=1, validation_data=val_ds)

Epoch 1/10
33/33 [==============================] - 7s 109ms/step - loss: 4.5573 - accuracy: 0.2932 - val_loss: 1.2358 - val_accuracy: 0.6322
Epoch 2/10
33/33 [==============================] - 1s 43ms/step - loss: 2.0711 - accuracy: 0.5482 - val_loss: 0.4970 - val_accuracy: 0.8391
Epoch 3/10
33/33 [==============================] - 1s 41ms/step - loss: 1.2808 - accuracy: 0.6953 - val_loss: 0.2534 - val_accuracy: 0.9042
Epoch 4/10
33/33 [==============================] - 1s 41ms/step - loss: 0.8280 - accuracy: 0.7736 - val_loss: 0.1845 - val_accuracy: 0.9502
Epoch 5/10
33/33 [==============================] - 1s 41ms/step - loss: 0.5928 - accuracy: 0.8300 - val_loss: 0.1211 - val_accuracy: 0.9770
Epoch 6/10
33/33 [==============================] - 1s 41ms/step - loss: 0.4390 - accuracy: 0.8749 - val_loss: 0.1046 - val_accuracy: 0.9808
Epoch 7/10
33/33 [==============================] - 1s 41ms/step - loss: 0.4108 - accuracy: 0.8797 - val_loss: 0.0950 - val_accuracy: 0.9885
Epoch 8/10
33/33 [==============================] - 1s 41ms/step - loss: 0.3137 - accuracy: 0.9102 - val_loss: 0.0662 - val_accuracy: 0.9808
Epoch 9/10
33/33 [==============================] - 1s 41ms/step - loss: 0.2416 - accuracy: 0.9284 - val_loss: 0.0698 - val_accuracy: 0.9885
Epoch 10/10
33/33 [==============================] - 1s 41ms/step - loss: 0.2524 - accuracy: 0.9217 - val_loss: 0.0597 - val_accuracy: 0.9923

4. MobileNetV2算法模型

# 加载预训练模型
MobileNetV2_base_model = tf.keras.applications.mobilenet_v2.MobileNetV2(weights='imagenet',
                                                            include_top=False,
                                                            input_shape=(img_width, img_height, 3),
                                                            pooling='max')
for layer in MobileNetV2_base_model.layers:
    layer.trainable = False
    
X = MobileNetV2_base_model.output
X = Dropout(0.4)(X)

output = Dense(len(class_names), activation='softmax')(X)
MobileNetV2_model = Model(inputs=MobileNetV2_base_model.input, outputs=output)

MobileNetV2_model.compile(optimizer="adam",
                loss='sparse_categorical_crossentropy',
                metrics=['accuracy'])
#MobileNetV2_model.summary()

MobileNetV2_history  = MobileNetV2_model.fit(train_ds, epochs=epochs, verbose=1, validation_data=val_ds)

Epoch 1/10
33/33 [==============================] - 3s 47ms/step - loss: 4.0865 - accuracy: 0.4403 - val_loss: 0.5897 - val_accuracy: 0.8812
Epoch 2/10
33/33 [==============================] - 1s 22ms/step - loss: 1.1042 - accuracy: 0.7536 - val_loss: 0.1841 - val_accuracy: 0.9540
Epoch 3/10
33/33 [==============================] - 1s 22ms/step - loss: 0.6147 - accuracy: 0.8596 - val_loss: 0.1722 - val_accuracy: 0.9770
Epoch 4/10
33/33 [==============================] - 1s 22ms/step - loss: 0.3826 - accuracy: 0.9007 - val_loss: 0.1505 - val_accuracy: 0.9770
Epoch 5/10
33/33 [==============================] - 1s 22ms/step - loss: 0.2290 - accuracy: 0.9370 - val_loss: 0.1408 - val_accuracy: 0.9885
Epoch 6/10
33/33 [==============================] - 1s 22ms/step - loss: 0.1976 - accuracy: 0.9484 - val_loss: 0.1294 - val_accuracy: 0.9923
Epoch 7/10
33/33 [==============================] - 1s 22ms/step - loss: 0.1193 - accuracy: 0.9608 - val_loss: 0.1038 - val_accuracy: 0.9923
Epoch 8/10
33/33 [==============================] - 1s 22ms/step - loss: 0.0859 - accuracy: 0.9675 - val_loss: 0.1140 - val_accuracy: 0.9923
Epoch 9/10
33/33 [==============================] - 1s 22ms/step - loss: 0.0973 - accuracy: 0.9704 - val_loss: 0.1292 - val_accuracy: 0.9923
Epoch 10/10
33/33 [==============================] - 1s 22ms/step - loss: 0.0504 - accuracy: 0.9828 - val_loss: 0.1361 - val_accuracy: 0.9923

三、结果分析

1. 准确率对比分析

# 可在原码中进行阅读
plt.show()

2. 损失函数对比分析

# 可在原码中进行阅读
plt.show()

3. 混淆矩阵

# 可在原码中进行阅读
plot_cm(val_label, val_pre)

4. 评估指标生成

support：当前行的类别在测试数据中的样本总量；
precision：被判定为正例（反例）的样本中，真正的正例样本（反例样本）的比例，精度=正确预测的个数(TP)/被预测正确的个数(TP+FP)。
recall：被正确分类的正例（反例）样本，占所有正例（反例）样本的比例，召回率=正确预测的个数(TP)/预测个数(TP+FN)。
f1-score: 精确率和召回率的调和平均值，F1 = 2精度召回率/(精度+召回率)。
accuracy：表示准确率，也即正确预测样本量与总样本量的比值。
macro avg：表示宏平均，表示所有类别对应指标的平均值。
weighted avg：表示带权重平均，表示类别样本占总样本的比重与对应指标的乘积的累加和。

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(InceptionV3_model)

              precision    recall  f1-score   support
          15       1.00      1.00      1.00         2          16       1.00      1.00      1.00        28          17       1.00      1.00      1.00        25          20       1.00      0.33      0.50         3          22       1.00      1.00      1.00         4          23       1.00      1.00      1.00         1          24       1.00      1.00      1.00        16          26       1.00      1.00      1.00        32          27       0.71      1.00      0.83         5          28       1.00      1.00      1.00        90          29       1.00      1.00      1.00         5          30       1.00      1.00      1.00        33          31       1.00      1.00      1.00         8          32       1.00      1.00      1.00         9
    accuracy                           0.99       261   macro avg       0.98      0.95      0.95       261weighted avg       0.99      0.99      0.99       261
Loss function: 0.10659126937389374, accuracy: 0.992337167263031

四、指定图片进行预测

from PIL import Image

img = Image.open("./1-data/17/017_0001.png")
image = tf.image.resize(img, [img_height, img_width])

img_array = tf.expand_dims(image, 0) 

predictions = InceptionV3_model.predict(img_array)
print("预测结果为：",np.argmax(predictions))

预测结果为：11

源码购买链接：

原文始发于微信公众号（K同学啊）：可以用于毕设参考！请勿过度借鉴

版权声明：admin 发表于 2022年3月18日下午2:55。
转载请注明：可以用于毕设参考！请勿过度借鉴 | CTF导航

PortSwigger发布LLM安全课程及靶场

admin

对抗性AI攻击吊打人脸识别-AI黑客大赛凸显AI算法的脆弱性

admin

531

使用KTO进行更好、更便宜、更快速的LLM对齐

admin

[ACM MM2022] 针对真实场景文档信息抽取的查询驱动生成网络

admin

281

成果分享｜Anti-FakeU: 图神经网络推荐模型托攻击防御算法

admin

223

【NLP基础】英文关键词抽取RAKE算法

admin

434

暂无评论

您必须登录才能参与评论！

立即登录

暂无评论...

可以用于毕设参考！请勿过度借鉴

一、导入数据

二、定义模型

1. VGG16模型

2. InceptionV3模型

3. DenseNet121算法模型

4. MobileNetV2算法模型

三、结果分析

1. 准确率对比分析

2. 损失函数对比分析

3. 混淆矩阵

4. 评估指标生成

四、指定图片进行预测

实体识别(3) -命名实体识别实践 BiLSTM-CRF

WSDM2022|阿里联合中科院提出特征协同作用网络CAN用于点击率预估(已开源)

相关文章

暂无评论

相关文章

可以用于毕设参考！请勿过度借鉴

一、导入数据

二、定义模型

1. VGG16模型

2. InceptionV3模型

3. DenseNet121算法模型

4. MobileNetV2算法模型

三、结果分析

1. 准确率对比分析

2. 损失函数对比分析

3. 混淆矩阵

4. 评估指标生成

四、指定图片进行预测

实体识别(3) -命名实体识别实践 BiLSTM-CRF

WSDM2022|阿里联合中科院提出特征协同作用网络CAN用于点击率预估(已开源)

相关文章

暂无评论

广告位

相关文章