Shortcuts

DeiT3

class mmpretrain.models.backbones.DeiT3(arch='base', img_size=224, patch_size=16, in_channels=3, out_indices=-1, drop_rate=0.0, drop_path_rate=0.0, qkv_bias=True, norm_cfg={'eps': 1e-06, 'type': 'LN'}, final_norm=True, out_type='cls_token', with_cls_token=True, use_layer_scale=True, interpolate_mode='bicubic', patch_cfg={}, layer_cfgs={}, init_cfg=None)[source]

DeiT3 backbone.

A PyTorch implement of : DeiT III: Revenge of the ViT

The differences between DeiT3 & VisionTransformer:

  1. Use LayerScale.

  2. Concat cls token after adding pos_embed.

Parameters:
  • arch (str | dict) –

    DeiT3 architecture. If use string, choose from ‘small’, ‘base’, ‘medium’, ‘large’ and ‘huge’. 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.

  • out_indices (Sequence | int) – Output from which stages. Defaults to -1, means the last stage.

  • 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 "cls_token".

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

  • use_layer_scale (bool) – Whether to use layer_scale in DeiT3. Defaults to True.

  • 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.

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