图片分类python

要用Python进行图片分类，可以使用深度学习框架进行模型训练和分类。常用的深度学习框架有TensorFlow、PyTorch和Keras等。以下是一个基于TensorFlow的图片分类示例代码：

import tensorflow as tf
import numpy as np
import os

# 加载数据和标签
def load_data():
    train_path = "./train/"
    test_path = "./test/"
    categories = os.listdir(train_path)
    categories.sort()
    num_classes = len(categories)
    train_data = []
    train_labels = []
    test_data = []
    test_labels = []
    for index, category in enumerate(categories):
        train_label = np.zeros(num_classes)
        train_label[index] = 1
        test_label = np.zeros(num_classes)
        test_label[index] = 1
        for img in os.listdir(train_path+category):
            img_path = os.path.join(train_path, category, img)
            img = tf.keras.preprocessing.image.load_img(img_path, target_size=(224, 224))
            img = tf.keras.preprocessing.image.img_to_array(img)
            train_data.append(img)
            train_labels.append(train_label)
        for img in os.listdir(test_path+category):
            img_path = os.path.join(test_path, category, img)
            img = tf.keras.preprocessing.image.load_img(img_path, target_size=(224, 224))
            img = tf.keras.preprocessing.image.img_to_array(img)
            test_data.append(img)
            test_labels.append(test_label)

    train_data = np.array(train_data)
    train_labels = np.array(train_labels)
    test_data = np.array(test_data)
    test_labels = np.array(test_labels)

    return train_data, train_labels, test_data, test_labels, num_classes

# 构建模型
def build_model(num_classes):
    base_model = tf.keras.applications.MobileNetV2(input_shape=(224, 224, 3), include_top=False, weights='imagenet')
    x = tf.keras.layers.GlobalAveragePooling2D()(base_model.output)
    x = tf.keras.layers.Dense(1024, activation='relu')(x)
    x = tf.keras.layers.Dropout(0.5)(x)
    output = tf.keras.layers.Dense(num_classes, activation='softmax')(x)
    model = tf.keras.models.Model(inputs=base_model.input, outputs=output)

    return model

# 训练模型
def train_model(train_data, train_labels, num_classes):
    model = build_model(num_classes)
    model.compile(optimizer=tf.keras.optimizers.Adam(lr=0.001), loss='categorical_crossentropy', metrics=['accuracy'])
    model.fit(train_data, train_labels, epochs=10, batch_size=32)
    model.save('./model.h5')

# 测试模型
def test_model(test_data, test_labels):
    model = tf.keras.models.load_model('./model.h5')
    loss, accuracy = model.evaluate(test_data, test_labels)
    print('Test Loss:', loss)
    print('Test Accuracy:', accuracy)

if __name__ == '__main__':
    train_data, train_labels, test_data, test_labels, num_classes = load_data()
    train_model(train_data, train_labels, num_classes)
    test_model(test_data, test_labels)

这个示例代码使用了MobileNetV2模型进行特征提取，并添加了一些全连接层进行分类。在训练时，使用了Adam优化器和交叉熵损失函数。在测试时，加载了已经训练好的模型，计算了测试数据的损失和准确率。代码中的数据集路径需要根据实际情况进行修改。