Keras：AveragePooling1D 层和 GlobalAveragePooling1D 层的区别

Question

当谈到 Keras 的平均池化层时，我有点困惑。文档说明如下：

AveragePooling1D：时态数据的平均池化。

参数

pool_size: Integer, size of the average pooling windows.
strides: Integer, or None. Factor by which to downscale. E.g. 2 will halve the input. If None, it will default to pool_size.
padding: One of "valid" or "same" (case-insensitive).
data_format: A string, one of channels_last (default) or channels_first. The ordering of the dimensions in the inputs.

channel_last 对应于具有形状（批次、步骤、特征）的输入，而 channels_first 对应于具有形状（批次、特征、步骤）的输入。

输入形状

If data_format='channels_last': 3D tensor with shape: (batch_size, steps, features)
If data_format='channels_first': 3D tensor with shape: (batch_size, features, steps)

输出形状

If data_format='channels_last': 3D tensor with shape: (batch_size, downsampled_steps, features)
If data_format='channels_first': 3D tensor with shape: (batch_size, features, downsampled_steps)

和

GlobalAveragePooling1D：时态数据的全局平均池化操作。

参数

data_format: A string, one of channels_last (default) or channels_first. The ordering of the dimensions in the inputs.

channel_last 对应于具有形状（批次、步骤、特征）的输入，而 channels_first 对应于具有形状（批次、特征、步骤）的输入。

输入形状

If data_format='channels_last': 3D tensor with shape: (batch_size, steps, features)
If data_format='channels_first': 3D tensor with shape: (batch_size, features, steps)

输出形状

具有形状的 2D 张量：（batch_size, features）

我（认为我）确实得到了平均池化的概念，但我真的不明白为什么 GlobalAveragePooling1D 层只是简单地删除了步骤参数。非常感谢您的回答。

Answer 1

GlobalAveragePooling1D是一样AveragePooling1D用pool_size=steps。因此，对于每个特征维度，它在所有时间步长中取平均值。因此输出具有形状(batch_size, 1, features)（如果data_format='channels_last'）。他们只是将第二个（或第三个 if data_format='channels_first'）维度展平，这就是您获得等于 的输出形状的方式 (batch_size, features)。