快速实现池化层(tf.layers.max_pooling1d())

这个函数可以快速实现1维池化层

各参数及返回值:

Arguments:

inputs: The tensor over which to pool. Must have rank 3.

pool_size: An integer or tuple/list of a single integer,

representing the size of the pooling window.

strides: An integer or tuple/list of a single integer, specifying the

strides of the pooling operation.

padding: A string. The padding method, either '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.

`channels_last` corresponds to inputs with shape

`(batch, length, channels)` while `channels_first` corresponds to

inputs with shape `(batch, channels, length)`.

name: A string, the name of the layer.

Returns:

The output tensor, of rank 3.


实验:


以上实验参数:batch_size = 2,  seq_len = 3,    embed=1

最后编辑于
©著作权归作者所有,转载或内容合作请联系作者
【社区内容提示】社区部分内容疑似由AI辅助生成,浏览时请结合常识与多方信息审慎甄别。
平台声明:文章内容(如有图片或视频亦包括在内)由作者上传并发布,文章内容仅代表作者本人观点,简书系信息发布平台,仅提供信息存储服务。

推荐阅读更多精彩内容