Shortcuts

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.

Read the Docs v: latest
Versions
master
latest
1.x
dev-1.x
Downloads
pdf
html
epub
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.