RevVisionTransformer

class mmpretrain.models.backbones.RevVisionTransformer(arch='base', img_size=224, patch_size=16, in_channels=3, drop_rate=0.0, drop_path_rate=0.0, qkv_bias=True, norm_cfg={'eps': 1e-06, 'type': 'LN'}, final_norm=True, out_type='avg_featmap', with_cls_token=False, frozen_stages=-1, interpolate_mode='bicubic', patch_cfg={}, layer_cfgs={}, fusion_mode='concat', no_custom_backward=False, init_cfg=None)

Reversible Vision Transformer.

A PyTorch implementation of : Reversible Vision Transformers # noqa: E501

Parameters:

• arch (str | dict) –

  Vision Transformer architecture. If use string, choose from ‘small’, ‘base’, ‘large’, ‘deit-tiny’, ‘deit-small’ and ‘deit-base’. If use dict, it should have below keys:

  • embed_dims (int): The dimensions of embedding.

  • num_layers (int): The number of transformer encoder layers.

  • num_heads (int): The number of heads in attention modules.

  • feedforward_channels (int): The hidden dimensions in feedforward modules.

  Defaults to ‘base’.

• img_size (int | tuple) – The expected input image shape. Because we support dynamic input shape, just set the argument to the most common input image shape. Defaults to 224.

• patch_size (int | tuple) – The patch size in patch embedding. Defaults to 16.

• in_channels (int) – The num of input channels. Defaults to 3.

• drop_rate (float) – Probability of an element to be zeroed. Defaults to 0.

• drop_path_rate (float) – stochastic depth rate. Defaults to 0.

• qkv_bias (bool) – Whether to add bias for qkv in attention modules. Defaults to True.

• norm_cfg (dict) – Config dict for normalization layer. Defaults to dict(type='LN').

• final_norm (bool) – Whether to add a additional layer to normalize final feature map. Defaults to True.

• out_type (str) –

  The type of output features. Please choose from

  • "cls_token": The class token tensor with shape (B, C).

  • "featmap": The feature map tensor from the patch tokens with shape (B, C, H, W).

  • "avg_featmap": The global averaged feature map tensor with shape (B, C).

  • "raw": The raw feature tensor includes patch tokens and class tokens with shape (B, L, C).

  Defaults to "avg_featmap".

• with_cls_token (bool) – Whether concatenating class token into image tokens as transformer input. Defaults to False.

• frozen_stages (int) – Stages to be frozen (stop grad and set eval mode). -1 means not freezing any parameters. Defaults to -1.

• interpolate_mode (str) – Select the interpolate mode for position embeding vector resize. Defaults to “bicubic”.

• patch_cfg (dict) – Configs of patch embeding. Defaults to an empty dict.

• layer_cfgs (Sequence | dict) – Configs of each transformer layer in encoder. Defaults to an empty dict.

• fusion_mode (str) – The fusion mode of transformer layers. Defaults to ‘concat’.

• no_custom_backward (bool) – Whether to use custom backward. Defaults to False.

• init_cfg (dict, optional) – Initialization config dict. Defaults to None.

static resize_pos_embed(*args, **kwargs)

Interface for backward-compatibility.