T4周：猴痘病识别

>- **🍨 本文为[🔗365天深度学习训练营](https://mp.weixin.qq.com/s/0dvHCaOoFnW8SCp3JpzKxg) 中的学习记录博客**
>- **🍖 原作者：[K同学啊](https://mtyjkh.blog.csdn.net/)**

1. 设置GPU

如果使用的是CPU可以忽略这步

from tensorflow       import keras
from tensorflow.keras import layers,models
import os, PIL, pathlib
import matplotlib.pyplot as plt
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")
    
gpus

 2. 导入数据

data_dir = "./45-data/"

data_dir = pathlib.Path(data_dir)

3. 查看数据

image_count = len(list(data_dir.glob('*/*.jpg')))

print("图片总数为：",image_count)

图片总数为： 2142 

4.加载数据

使用image_dataset_from_directory方法将磁盘中的数据加载到tf.data.Dataset中

测试集与验证集的关系：

1. 验证集并没有参与训练过程梯度下降过程的，狭义上来讲是没有参与模型的参数训练更新的。
2. 但是广义上来讲，验证集存在的意义确实参与了一个“人工调参”的过程，我们根据每一个epoch训练之后模型在valid data上的表现来决定是否需要训练进行early stop，或者根据这个过程模型的性能变化来调整模型的超参数，如学习率，batch_size等等。
3. 因此，我们也可以认为，验证集也参与了训练，但是并没有使得模型去overfit验证集

batch_size = 32
img_height = 224
img_width = 224

"""
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(
    data_dir,
    validation_split=0.2,
    subset="training",
    seed=123,
    image_size=(img_height, img_width),
    batch_size=batch_size)

Found 2142 files belonging to 2 classes.
Using 1714 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(
    data_dir,
    validation_split=0.2,
    subset="validation",
    seed=123,
    image_size=(img_height, img_width),
    batch_size=batch_size)

Found 2142 files belonging to 2 classes.
Using 428 files for validation.

class_names = train_ds.class_names
print(class_names)

['Monkeypox', 'Others']

5. 可视化数据

plt.figure(figsize=(20, 10))

for images, labels in train_ds.take(1):
    for i in range(20):
        ax = plt.subplot(5, 10, i + 1)

        plt.imshow(images[i].numpy().astype("uint8"))
        plt.title(class_names[labels[i]])
        
        plt.axis("off")

 

6. 再次检查数据

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

(32, 224, 224, 3)
(32,)

7. 配置数据集

AUTOTUNE = tf.data.AUTOTUNE

train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)

8.构建CNN网络

num_classes = 2

"""
关于卷积核的计算不懂的可以参考文章：https://blog.csdn.net/qq_38251616/article/details/114278995

layers.Dropout(0.4) 作用是防止过拟合，提高模型的泛化能力。
在上一篇文章花朵识别中，训练准确率与验证准确率相差巨大就是由于模型过拟合导致的

关于Dropout层的更多介绍可以参考文章：https://mtyjkh.blog.csdn.net/article/details/115826689
"""

model = models.Sequential([
    layers.experimental.preprocessing.Rescaling(1./255, input_shape=(img_height, img_width, 3)),
    
    layers.Conv2D(16, (3, 3), activation='relu', input_shape=(img_height, img_width, 3)), # 卷积层1，卷积核3*3  
    layers.AveragePooling2D((2, 2)),               # 池化层1，2*2采样
    layers.Conv2D(32, (3, 3), activation='relu'),  # 卷积层2，卷积核3*3
    layers.AveragePooling2D((2, 2)),               # 池化层2，2*2采样
    layers.Dropout(0.3),  
    layers.Conv2D(64, (3, 3), activation='relu'),  # 卷积层3，卷积核3*3
    layers.Dropout(0.3),  
    
    layers.Flatten(),                       # Flatten层，连接卷积层与全连接层
    layers.Dense(128, activation='relu'),   # 全连接层，特征进一步提取
    layers.Dense(num_classes)               # 输出层，输出预期结果
])

model.summary()  # 打印网络结构

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
rescaling (Rescaling)        (None, 224, 224, 3)       0         
_________________________________________________________________
conv2d (Conv2D)              (None, 222, 222, 16)      448       
_________________________________________________________________
average_pooling2d (AveragePo (None, 111, 111, 16)      0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 109, 109, 32)      4640      
_________________________________________________________________
average_pooling2d_1 (Average (None, 54, 54, 32)        0         
_________________________________________________________________
dropout (Dropout)            (None, 54, 54, 32)        0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 52, 52, 64)        18496     
_________________________________________________________________
dropout_1 (Dropout)          (None, 52, 52, 64)        0         
_________________________________________________________________
flatten (Flatten)            (None, 173056)            0         
_________________________________________________________________
dense (Dense)                (None, 128)               22151296  
_________________________________________________________________
dense_1 (Dense)              (None, 2)                 258       
=================================================================
Total params: 22,175,138
Trainable params: 22,175,138
Non-trainable params: 0
_________________________________________________________________

9.编译

# 设置优化器
opt = tf.keras.optimizers.Adam(learning_rate=1e-4)

model.compile(optimizer=opt,
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

10.训练模型

from tensorflow.keras.callbacks import ModelCheckpoint

epochs = 50

checkpointer = ModelCheckpoint('best_model.h5',
                                monitor='val_accuracy',
                                verbose=1,
                                save_best_only=True,
                                save_weights_only=True)

history = model.fit(train_ds,
                    validation_data=val_ds,
                    epochs=epochs,
                    callbacks=[checkpointer])

Epoch 1/50
54/54 [==============================] - 4s 18ms/step - loss: 0.6969 - accuracy: 0.5408 - val_loss: 0.6763 - val_accuracy: 0.6098

Epoch 00001: val_accuracy improved from -inf to 0.60981, saving model to best_model.h5
Epoch 2/50
54/54 [==============================] - 1s 12ms/step - loss: 0.6672 - accuracy: 0.5858 - val_loss: 0.6423 - val_accuracy: 0.6612

......

Epoch 00047: val_accuracy did not improve from 0.87850
Epoch 48/50
54/54 [==============================] - 1s 12ms/step - loss: 0.0953 - accuracy: 0.9691 - val_loss: 0.4090 - val_accuracy: 0.8715

Epoch 00048: val_accuracy did not improve from 0.87850
Epoch 49/50
54/54 [==============================] - 1s 12ms/step - loss: 0.0699 - accuracy: 0.9819 - val_loss: 0.3922 - val_accuracy: 0.8832

Epoch 00049: val_accuracy improved from 0.87850 to 0.88318, saving model to best_model.h5
Epoch 50/50
54/54 [==============================] - 1s 12ms/step - loss: 0.0714 - accuracy: 0.9772 - val_loss: 0.4151 - val_accuracy: 0.8785

Epoch 00050: val_accuracy did not improve from 0.88318

 11. Loss与Accuracy图

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

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

epochs_range = range(epochs)

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()

 

12. 指定图片进行预测

# 加载效果最好的模型权重
model.load_weights('best_model.h5')

from PIL import Image
import numpy as np

# img = Image.open("./45-data/Monkeypox/M06_01_04.jpg")  #这里选择你需要预测的图片
img = Image.open("./45-data/Others/NM15_02_11.jpg")  #这里选择你需要预测的图片
image = tf.image.resize(img, [img_height, img_width])

img_array = tf.expand_dims(image, 0) 

predictions = model.predict(img_array) # 这里选用你已经训练好的模型
print("预测结果为：",class_names[np.argmax(predictions)])

预测结果为： Others