Pyramid Encoder

class vformer.encoder.pyramid.PVTEncoder(dim, num_heads, mlp_ratio, depth, qkv_bias, qk_scale, p_dropout, attn_dropout, drop_path, activation, use_dwconv, sr_ratio, linear=False, drop_path_mode='batch')[source]
Parameters
  • dim (int) – Dimension of the input tensor

  • num_heads (int) – Number of attention heads

  • mlp_ratio – Ratio of MLP hidden dimension to embedding dimension

  • depth (int) – Number of attention layers in the encoder

  • qkv_bias (bool) – Whether to add a bias vector to the q,k, and v matrices

  • qk_scale (float, optional) – Override default qk scale of head_dim ** -0.5 in Spatial Attention if set

  • p_dropout (float) – Dropout probability

  • attn_dropout (float) – Dropout probability

  • drop_path (tuple(float)) – List of stochastic drop rate

  • activation (nn.Module) – Activation layer

  • use_dwconv (bool) – Whether to use depth-wise convolutions in overlap-patch embedding

  • sr_ratio (float) – Spatial Reduction ratio

  • linear (bool) – Whether to use linear Spatial attention, default is `False`.

  • drop_path_mode (str) – Mode for StochasticDepth <https://pytorch.org/vision/main/generated/torchvision.ops.stochastic_depth.html>_ , must be one of {``batch` or row}

forward(x, **kwargs)[source]

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class vformer.encoder.pyramid.PVTFeedForward(dim, hidden_dim=None, out_dim=None, activation=<class 'torch.nn.modules.activation.GELU'>, p_dropout=0.0, linear=False, use_dwconv=False, **kwargs)[source]
Parameters
  • dim (int) – Dimension of the input tensor

  • hidden_dim (int, optional) – Dimension of hidden layer

  • out_dim (int, optional) – Dimension of output tensor

  • activation (nn.Module) – Activation Layer, default is nn.GELU

  • p_dropout (float) – Dropout probability/rate, default is 0.0

  • linear (bool) – Whether to use linear Spatial attention,default is False

  • use_dwconv (bool) – Whether to use Depth-wise convolutions, default is False

  • kernel_size_dwconv (int) – kernel_size parameter for 2D convolution used in Depth wise convolution

  • stride_dwconv (int) – stride parameter for 2D convolution used in Depth wise convolution

  • padding_dwconv (int) – padding parameter for 2D convolution used in Depth wise convolution

  • bias_dwconv (bool) – bias parameter for 2D convolution used in Depth wise convolution

forward(x, **kwargs)[source]
Parameters
  • x (torch.Tensor) – Input tensor

  • H (int) – Height of image patch

  • W (int) – Width of image patch

Returns

Returns output tensor

Return type

torch.Tensor