基于卷积神经网络的猫狗识别代码

以下是一个基于卷积神经网络的猫狗识别的Python代码示例，基于TensorFlow框架实现：

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

# 定义模型
def model_fn(features, labels, mode):
    # 输入层
    input_layer = tf.reshape(features["x"], [-1, 128, 128, 3])

    # 卷积层1
    conv1 = tf.layers.conv2d(
        inputs=input_layer,
        filters=32,
        kernel_size=[5, 5],
        padding="same",
        activation=tf.nn.relu)

    # 池化层1
    pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2)

    # 卷积层2
    conv2 = tf.layers.conv2d(
        inputs=pool1,
        filters=64,
        kernel_size=[5, 5],
        padding="same",
        activation=tf.nn.relu)

    # 池化层2
    pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)

    # 全连接层
    pool2_flat = tf.reshape(pool2, [-1, 32 * 32 * 64])
    dense = tf.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu)
    dropout = tf.layers.dropout(inputs=dense, rate=0.4, training=mode == tf.estimator.ModeKeys.TRAIN)

    # 输出层
    logits = tf.layers.dense(inputs=dropout, units=2)

    predictions = {
        "classes": tf.argmax(input=logits, axis=1),
        "probabilities": tf.nn.softmax(logits, name="softmax_tensor")
    }

    if mode == tf.estimator.ModeKeys.PREDICT:
        return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions)

    loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)

    if mode == tf.estimator.ModeKeys.TRAIN:
        optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001)
        train_op = optimizer.minimize(loss=loss, global_step=tf.train.get_global_step())
        return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op)

    eval_metric_ops = {
        "accuracy": tf.metrics.accuracy(labels=labels, predictions=predictions["classes"])
    }

    return tf.estimator.EstimatorSpec(mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)


# 加载数据
def load_data(data_dir):
    images = []
    labels = []

    for file in os.listdir(data_dir):
        if file.endswith(".jpg"):
            file_path = os.path.join(data_dir, file)
            image = cv2.imread(file_path)
            image = cv2.resize(image, (128, 128))
            images.append(image)

            if "cat" in file:
                labels.append(0)
            elif "dog" in file:
                labels.append(1)

    return np.array(images), np.array(labels)


# 主函数
def main(argv):
    # 加载训练数据和测试数据
    train_images, train_labels = load_data("train")
    test_images, test_labels = load_data("test")

    # 创建Estimator
    classifier = tf.estimator.Estimator(model_fn=model_fn)

    # 创建输入函数
    train_input_fn = tf.estimator.inputs.numpy_input_fn(
        x={"x": train_images},
        y=train_labels,
        batch_size=100,
        num_epochs=None,
        shuffle=True)

    test_input_fn = tf.estimator.inputs.numpy_input_fn(
        x={"x": test_images},
        y=test_labels,
        num_epochs=1,
        shuffle=False)

    # 训练模型
    classifier.train(input_fn=train_input_fn, steps=1000)

    # 评估模型
    eval_result = classifier.evaluate(input_fn=test_input_fn)
    print("Test set accuracy: {accuracy:0.3f}".format(**eval_result))

if __name__ == "__main__":
    tf.app.run(main=main)

这个代码示例中，我们使用了一个包含两个卷积层、两个池化层和一个全连接层的卷积神经网络模型来进行猫狗识别。我们使用了128 * 128的图像作为输入，并使用了随机梯度下降进行优化。我们使用了一个包含训练集和测试集的数据集来进行训练和测试。在训练结束后，我们评估了模型在测试集上的准确率。