定义模块class BasicBlock(layers.Layer): expansion = 1 def __init__(self, in_channels, out_channels, stride=1): super(BasicBlock, self).__init__() # 1. BasicBlock模块中的共有2个卷积;BasicBlock模块中的第1个卷积层; self.conv1 = regularized_padded_conv(out_channels, kernel_size=3, strides=stride) self.bn1 = layers.BatchNormalization() # 2. 第2个；第1个卷积如果做stride就会有一个下采样，在这个里面就不做下采样了。这一块始终保持size一致，把stride固定为1 self.conv2 = regularized_padded_conv(out_channels, kernel_size=3, strides=1) self.bn2 = layers.BatchNormalization() # 3. 判断stride是否等于1,如果为1就是没有降采样。 if stride != 1 or in_channels != self.expansion * out_channels: self.shortcut = Sequential([regularized_padded_conv(self.expansion * out_channels, kernel_size=1, strides=stride), layers.BatchNormalization()]) else: self.shortcut = lambda x, _: x self.max= layers.GlobalMaxPooling2D(kernel_size=2, stride=2) def call(self, inputs, training=False): out = self.conv1(inputs) out = self.bn1(out, training=training) out = tf.nn.relu(out) out = self.conv2(out) out = self.bn2(out, training=training) out = out + self.shortcut(inputs, training) out = self.pool(out) out = tf.nn.relu(out) return out后，如何嗲用

可以通过以下步骤来调用定义的 BasicBlock 模块：

1. 首先，需要导入相关库，包括 `tensorflow` 和 `keras`。

2. 创建一个 BasicBlock 实例对象，需要指定输入通道数 `in_channels` 和输出通道数 `out_channels`，同时可以选择是否设置卷积步长 `stride`。

3. 将输入数据传递给 BasicBlock 实例对象的 `call` 方法进行前向计算，可以选择是否设置训练标志 `training`。

下面是一个示例代码：

import tensorflow as tf
from tensorflow.keras import layers, Sequential

# 定义 BasicBlock 模块
class BasicBlock(layers.Layer):
    expansion = 1
    def __init__(self, in_channels, out_channels, stride=1):
        super(BasicBlock, self).__init__()
        # 1. BasicBlock模块中的共有2个卷积;BasicBlock模块中的第1个卷积层;
        self.conv1 = layers.Conv2D(out_channels, kernel_size=3, strides=stride, padding='same')
        self.bn1 = layers.BatchNormalization()
        # 2. 第2个；第1个卷积如果做stride就会有一个下采样，在这个里面就不做下采样了。这一块始终保持size一致，把stride固定为1
        self.conv2 = layers.Conv2D(out_channels, kernel_size=3, strides=1, padding='same')
        self.bn2 = layers.BatchNormalization()
        # 3. 判断stride是否等于1,如果为1就是没有降采样。
        if stride != 1 or in_channels != self.expansion * out_channels:
            self.shortcut = Sequential([
                layers.Conv2D(self.expansion * out_channels, kernel_size=1, strides=stride, padding='same'),
                layers.BatchNormalization()
            ])
        else:
            self.shortcut = lambda x, _: x
        self.pool = layers.GlobalMaxPooling2D(pool_size=2, strides=2)

    def call(self, inputs, training=False):
        out = self.conv1(inputs)
        out = self.bn1(out, training=training)
        out = tf.nn.relu(out)

        out = self.conv2(out)
        out = self.bn2(out, training=training)

        out = out + self.shortcut(inputs, training)
        out = self.pool(out)
        out = tf.nn.relu(out)

        return out

# 创建 BasicBlock 实例对象
basic_block = BasicBlock(in_channels=3, out_channels=64, stride=1)

# 构造输入数据
inputs = tf.ones((1, 224, 224, 3))

# 进行前向计算
outputs = basic_block(inputs, training=False)