备注

您正在阅读 MMClassification 0.x 版本的文档。MMClassification 0.x 会在 2022 年末被切换为次要分支。建议您升级到 MMClassification 1.0 版本，体验更多新特性和新功能。请查阅 MMClassification 1.0 的安装教程、迁移教程以及更新日志。

mmcls.models.utils.ConditionalPositionEncoding¶

class mmcls.models.utils.ConditionalPositionEncoding(in_channels, embed_dims=768, stride=1, init_cfg=None)[源代码]¶

The Conditional Position Encoding (CPE) module.

The CPE is the implementation of ‘Conditional Positional Encodings for Vision Transformers <https://arxiv.org/abs/2102.10882>’_.

参数

in_channels (int) – Number of input channels.
embed_dims (int) – The feature dimension. Default: 768.
stride (int) – Stride of conv layer. Default: 1.