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.Conformer¶

class mmcls.models.Conformer(arch='tiny', patch_size=16, base_channels=64, mlp_ratio=4.0, qkv_bias=True, with_cls_token=True, drop_path_rate=0.0, norm_eval=True, frozen_stages=0, out_indices=- 1, init_cfg=None)[源代码]¶

Conformer backbone.

A PyTorch implementation of : Conformer: Local Features Coupling Global Representations for Visual Recognition

参数

arch (str | dict) – Conformer architecture. Defaults to ‘tiny’.
patch_size (int) – The patch size. Defaults to 16.
base_channels (int) – The base number of channels in CNN network. Defaults to 64.
mlp_ratio (float) – The expansion ratio of FFN network in transformer block. Defaults to 4.
with_cls_token (bool) – Whether use class token or not. Defaults to True.
drop_path_rate (float) – stochastic depth rate. Defaults to 0.
out_indices (Sequence | int) – Output from which stages. Defaults to -1, means the last stage.
init_cfg (dict, optional) – Initialization config dict. Defaults to None.