猫狗识别python代码

好的，以下是一个简单的猫狗识别的Python代码，供您参考：

import tensorflow as tf
import os
import numpy as np
import cv2
import random

# 数据集路径
train_dir = 'train'
test_dir = 'test'

# 图像大小
img_size = 50

# 读取数据集
def read_data(dataset_dir):
    images = []
    labels = []
    # 读取猫的图像
    cat_dir = os.path.join(dataset_dir, 'cat')
    for img_file in os.listdir(cat_dir):
        img_path = os.path.join(cat_dir, img_file)
        img = cv2.imread(img_path)
        img = cv2.resize(img, (img_size, img_size))
        images.append(img)
        labels.append(0)
    # 读取狗的图像
    dog_dir = os.path.join(dataset_dir, 'dog')
    for img_file in os.listdir(dog_dir):
        img_path = os.path.join(dog_dir, img_file)
        img = cv2.imread(img_path)
        img = cv2.resize(img, (img_size, img_size))
        images.append(img)
        labels.append(1)
    # 打乱数据集
    data = list(zip(images, labels))
    random.shuffle(data)
    images, labels = zip(*data)
    # 转换为numpy数组
    images = np.array(images)
    labels = np.array(labels)
    return images, labels

# 构建卷积神经网络模型
def build_model():
    model = tf.keras.models.Sequential([
        tf.keras.layers.Conv2D(32, (3, 3), activation='relu', input_shape=(img_size, img_size, 3)),
        tf.keras.layers.MaxPooling2D((2, 2)),
        tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
        tf.keras.layers.MaxPooling2D((2, 2)),
        tf.keras.layers.Conv2D(128, (3, 3), activation='relu'),
        tf.keras.layers.MaxPooling2D((2, 2)),
        tf.keras.layers.Flatten(),
        tf.keras.layers.Dense(128, activation='relu'),
        tf.keras.layers.Dense(1, activation='sigmoid')
    ])
    model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
    return model

# 训练模型
def train_model(train_images, train_labels, model):
    model.fit(train_images, train_labels, epochs=10, batch_size=32)

# 测试模型
def test_model(test_images, test_labels, model):
    loss, accuracy = model.evaluate(test_images, test_labels)
    print('loss:', loss)
    print('accuracy:', accuracy)

# 主函数
def main():
    # 读取训练集和测试集
    train_images, train_labels = read_data(train_dir)
    test_images, test_labels = read_data(test_dir)
    # 归一化
    train_images = train_images / 255.0
    test_images = test_images / 255.0
    # 构建模型
    model = build_model()
    # 训练模型
    train_model(train_images, train_labels, model)
    # 测试模型
    test_model(test_images, test_labels, model)

if __name__ == '__main__':
    main()

以上代码使用了卷积神经网络（CNN）算法，构建了一个简单的猫狗识别模型，并在训练集和测试集上进行了训练和测试。