第32周：猴痘病识别(Tensorflow实战第四周)

# 一、前期准备
# 1.1 设置GPU
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")
print(gpus)

# 1.2 导入数据
data_dir = "./4-data/"
data_dir = pathlib.Path(data_dir)

# 1.3 查看数据
image_count = len(list(data_dir.glob('*/*.jpg')))
print("图片总数为：", image_count)
Monkeypox = list(data_dir.glob('Monkeypox/*.jpg'))
PIL.Image.open(str(Monkeypox[0]))

# 二、数据预处理
# 2.1 加载数据
batch_size = 32
img_height = 180
img_width = 180
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)
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)
class_names = train_ds.class_names
print(class_names)

# 2.2 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")

# 2.3再次检查数据
for image_batch, labels_batch in train_ds:
    print(image_batch.shape)
    print(labels_batch.shape)
    break

​

​

# cache()：将数据集缓存到内存当中，加速运行
AUTOTUNE = tf.data.AUTOTUNE
train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)

​

# 三、构建CNN网络
num_classes = 4
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.Conv2D(64, (3, 3), activation='relu'),  # 卷积层3，卷积核3*3
    layers.Dropout(0.3),  # 让神经元以一定的概率停止工作，防止过拟合，提高模型的泛化能力。

    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

# 四、编译
# 设置优化器
opt = tf.keras.optimizers.Adam(learning_rate=0.001)
model.compile(optimizer=opt,
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

# 五、训练模型
epochs = 10
history = model.fit(train_ds, validation_data=val_ds, epochs=epochs)

# 六、模型评估
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()