Tensorflow入门实战 T04-猴痘识别

本篇文章主要：tensorflow

运行环境：本地cpu

运行epoch：50

1、tensorflow官网

tensorflow的官网教程。初学者的 TensorFlow 2.0 教程 | TensorFlow Core

官网上有图像分类的相关详细描述还有代码示例。

2、完整代码展示

from tensorflow import keras
from 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")

# 导入数据
data_dir = "/Users/MsLiang/Documents/mySelf_project/pythonProject_pytorch/learn_demo/P_model/p04_houdou/data"
data_dir = pathlib.Path(data_dir)
image_count = len(list(data_dir.glob('*/*.jpg')))
print("图片总数为：", image_count)  # 2142

Monkeypox = list(data_dir.glob('Monkeypox/*.jpg'))
im = PIL.Image.open(str(Monkeypox[0]))
# im.show()

# 数据处理
batch_size = 32
img_height = 224
img_width = 224

"""
   【训练数据】，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(
    data_dir,
    validation_split=0.2,
    subset="training",
    seed=123,
    image_size=(img_height, img_width),
    batch_size=batch_size)

"""
    【测试数据】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
"""
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)

# 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")
plt.show()  # 图片展示

# 再次检查数据 格式
'''
    Image_batch是形状的张量(32,224,224,3) 这是一批形状224x224x3的32张图片（最后一维指的是彩色通道RGB）
'''
for image_batch, labels_batch in train_ds:
    print(image_batch.shape)   # (32, 224, 224, 3)
    print(labels_batch.shape)  # (32,)
    break

# 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)

# 构建神经网络
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([
    keras.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

# 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'])

# 模型训练
from 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])


# 模型评估 （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()


# 预测

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

from PIL import Image
import numpy as np

# img = Image.open("/Users/MsLiang/Documents/mySelf_project/pythonProject_pytorch/learn_demo/P_model/p04_houdou/data/Monkeypox/M01_01_01.jpg")  #这里选择你需要预测的图片
img = Image.open("/Users/MsLiang/Documents/mySelf_project/pythonProject_pytorch/learn_demo/P_model/p04_houdou/data/Others/NM01_01_00.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)])