卷积神经网络cnn python代码

以下是一个简单的卷积神经网络的 Python 代码示例：

import tensorflow as tf

# 定义卷积神经网络
def cnn_model_fn(features, labels, mode):
    # 输入层
    input_layer = tf.reshape(features["x"], [-1, 28, 28, 1])

    # 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 和 池化层 #2
    conv2 = tf.layers.conv2d(
        inputs=pool1,
        filters=64,
        kernel_size=[5, 5],
        padding="same",
        activation=tf.nn.relu)
    pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)

    # 全连接层
    pool2_flat = tf.reshape(pool2, [-1, 7 * 7 * 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=10)

    predictions = {
        # 生成预测结果
        "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)

    # 计算损失函数
    loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)

    # 配置训练操作
    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)

    # 配置评估操作
    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)

这是一个用 TensorFlow 实现的简单的卷积神经网络，用于 MNIST 手写数字识别任务。它包括两个卷积层、两个池化层和一个全连接层。