""" Swin Transformer Cross Attention A PyTorch impl of : `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows` - https://arxiv.org/pdf/2103.14030 Code/weights from https://github.com/microsoft/Swin-Transformer """ import torch import torch.nn as nn import torch.nn.functional as F import numpy as np from typing import Optional def drop_path_f(x, drop_prob: float = 0., training: bool = False): """Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). This is the same as the DropConnect impl I created for EfficientNet, etc networks, however, the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper... See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for changing the layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use 'survival rate' as the argument. """ if drop_prob == 0. or not training: return x keep_prob = 1 - drop_prob shape = (x.shape[0],) + (1,) * (x.ndim - 1) # work with diff dim tensors, not just 2D ConvNets random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device) random_tensor.floor_() # binarize output = x.div(keep_prob) * random_tensor return output class DropPath(nn.Module): """Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). """ def __init__(self, drop_prob=None): super(DropPath, self).__init__() self.drop_prob = drop_prob def forward(self, x): return drop_path_f(x, self.drop_prob, self.training) def window_partition(x, window_size: int): """ Partition the feature map into non-overlapping windows based on the window size. Args: x: (B, H, W, C) window_size (int): window size(M) Returns: windows: (num_windows*B, window_size, window_size, C) """ B, H, W, C = x.shape x = x.view(B, H // window_size, window_size, W // window_size, window_size, C) # permute: [B, H//Mh, Mh, W//Mw, Mw, C] -> [B, H//Mh, W//Mh, Mw, Mw, C] # view: [B, H//Mh, W//Mw, Mh, Mw, C] -> [B*num_windows, Mh, Mw, C] windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C) return windows def window_reverse(windows, window_size: int, H: int, W: int): """ Restore each window into a feature map. Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size(M) H (int): Height of image W (int): Width of image Returns: x: (B, H, W, C) """ B = int(windows.shape[0] / (H * W / window_size / window_size)) # view: [B*num_windows, Mh, Mw, C] -> [B, H//Mh, W//Mw, Mh, Mw, C] x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1) # permute: [B, H//Mh, W//Mw, Mh, Mw, C] -> [B, H//Mh, Mh, W//Mw, Mw, C] # view: [B, H//Mh, Mh, W//Mw, Mw, C] -> [B, H, W, C] x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1) return x class Mlp(nn.Module): """ MLP as used in Vision Transformer, MLP-Mixer and related networks """ def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.): super().__init__() out_features = out_features or in_features hidden_features = hidden_features or in_features self.fc1 = nn.Linear(in_features, hidden_features) self.act = act_layer() self.drop1 = nn.Dropout(drop) self.fc2 = nn.Linear(hidden_features, out_features) self.drop2 = nn.Dropout(drop) def forward(self, x): x = self.fc1(x) x = self.act(x) x = self.drop1(x) x = self.fc2(x) x = self.drop2(x) return x class WindowCrossAttention(nn.Module): r""" Window based multi-head self attention (W-MSA) module with relative position bias. It supports both of shifted and non-shifted window. Args: dim (int): Number of input channels. window_size (tuple[int]): The height and width of the window. num_heads (int): Number of attention heads. qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True attn_drop (float, optional): Dropout ratio of attention weight. Default: 0.0 proj_drop (float, optional): Dropout ratio of output. Default: 0.0 """ def __init__(self, dim, window_size, num_heads, qkv_bias=True, attn_drop=0., proj_drop=0.): super().__init__() self.dim = dim self.window_size = window_size # [Mh, Mw] self.num_heads = num_heads head_dim = dim // num_heads self.scale = head_dim ** -0.5 # define a parameter table of relative position bias self.relative_position_bias_table = nn.Parameter( torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1), num_heads)) # [2*Mh-1 * 2*Mw-1, nH] # get pair-wise relative position index for each token inside the window coords_h = torch.arange(self.window_size[0]) coords_w = torch.arange(self.window_size[1]) coords = torch.stack(torch.meshgrid([coords_h, coords_w], indexing="ij")) # [2, Mh, Mw] coords_flatten = torch.flatten(coords, 1) # [2, Mh*Mw] # [2, Mh*Mw, 1] - [2, 1, Mh*Mw] relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :] # [2, Mh*Mw, Mh*Mw] relative_coords = relative_coords.permute(1, 2, 0).contiguous() # [Mh*Mw, Mh*Mw, 2] relative_coords[:, :, 0] += self.window_size[0] - 1 # shift to start from 0 relative_coords[:, :, 1] += self.window_size[1] - 1 relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1 relative_position_index = relative_coords.sum(-1) # [Mh*Mw, Mh*Mw] self.register_buffer("relative_position_index", relative_position_index) self.q = nn.Linear(dim, dim, bias=qkv_bias) self.kv = nn.Linear(dim, dim * 2, bias=qkv_bias) self.attn_drop = nn.Dropout(attn_drop) self.proj = nn.Linear(dim, dim) self.proj_drop = nn.Dropout(proj_drop) nn.init.trunc_normal_(self.relative_position_bias_table, std=.02) self.softmax = nn.Softmax(dim=-1) def forward(self, x, kv, mask: Optional[torch.Tensor] = None): """ Args: x: input features with shape of (num_windows*B, Mh*Mw, C) mask: (0/-inf) mask with shape of (num_windows, Wh*Ww, Wh*Ww) or None """ # [batch_size*num_windows, Mh*Mw, total_embed_dim] B_, N, C = x.shape # q(): -> [batch_size*num_windows, Mh*Mw, 1*total_embed_dim] # reshape: -> [batch_size*num_windows, Mh*Mw, 3, num_heads, embed_dim_per_head] # permute: -> [3, batch_size*num_windows, num_heads, Mh*Mw, embed_dim_per_head] q = self.q(x).reshape(B_, N, 1, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4) # [batch_size*num_windows, num_heads, Mh*Mw, embed_dim_per_head] kv = self.kv(kv).reshape(B_, N, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4) k, v = kv.unbind(0) # make torchscript happy (cannot use tensor as tuple) # transpose: -> [batch_size*num_windows, num_heads, embed_dim_per_head, Mh*Mw] # @: multiply -> [batch_size*num_windows, num_heads, Mh*Mw, Mh*Mw] q = q * self.scale attn = (q @ k.transpose(-2, -1)) # relative_position_bias_table.view: [Mh*Mw*Mh*Mw,nH] -> [Mh*Mw,Mh*Mw,nH] relative_position_bias = self.relative_position_bias_table[self.relative_position_index.view(-1)].view( self.window_size[0] * self.window_size[1], self.window_size[0] * self.window_size[1], -1) relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous() # [nH, Mh*Mw, Mh*Mw] attn = attn + relative_position_bias.unsqueeze(0) if mask is not None: # mask: [nW, Mh*Mw, Mh*Mw] nW = mask.shape[0] # num_windows # attn.view: [batch_size, num_windows, num_heads, Mh*Mw, Mh*Mw] # mask.unsqueeze: [1, nW, 1, Mh*Mw, Mh*Mw] attn = attn.view(B_ // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0) attn = attn.view(-1, self.num_heads, N, N) attn = self.softmax(attn) else: attn = self.softmax(attn) attn = self.attn_drop(attn) # @: multiply -> [batch_size*num_windows, num_heads, Mh*Mw, embed_dim_per_head] # transpose: -> [batch_size*num_windows, Mh*Mw, num_heads, embed_dim_per_head] # reshape: -> [batch_size*num_windows, Mh*Mw, total_embed_dim] x = (attn @ v).transpose(1, 2).reshape(B_, N, C) x = self.proj(x) x = self.proj_drop(x) return x class SwinTransformerCABlock(nn.Module): r""" Swin Transformer Cross Attention Block. Args: dim (int): Number of input channels. num_heads (int): Number of attention heads. window_size (int): Window size. shift_size (int): Shift size for SW-MSA. mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True drop (float, optional): Dropout rate. Default: 0.0 attn_drop (float, optional): Attention dropout rate. Default: 0.0 drop_path (float, optional): Stochastic depth rate. Default: 0.0 act_layer (nn.Module, optional): Activation layer. Default: nn.GELU norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm """ def __init__(self, dim, num_heads, window_size=7, shift_size=0, mlp_ratio=4., qkv_bias=True, drop=0., attn_drop=0., drop_path=0., act_layer=nn.GELU, norm_layer=nn.LayerNorm): super().__init__() self.dim = dim self.num_heads = num_heads self.window_size = window_size self.shift_size = shift_size self.mlp_ratio = mlp_ratio assert 0 <= self.shift_size < self.window_size, "shift_size must in 0-window_size" self.norm1 = norm_layer(dim) self.attn = WindowCrossAttention( dim, window_size=(self.window_size, self.window_size), num_heads=num_heads, qkv_bias=qkv_bias, attn_drop=attn_drop, proj_drop=drop) self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity() self.norm2 = norm_layer(dim) mlp_hidden_dim = int(dim * mlp_ratio) self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop) def forward(self, x, kv, attn_mask): H, W = self.H, self.W B, L, C = x.shape assert L == H * W, "input feature has wrong size" shortcut = x x = self.norm1(x) x = x.view(B, H, W, C) kv = self.norm1(kv) kv = kv.view(B, H, W, C) # pad feature maps to multiples of window size # Pad the feature map to multiples of the window size. pad_l = pad_t = 0 pad_r = (self.window_size - W % self.window_size) % self.window_size pad_b = (self.window_size - H % self.window_size) % self.window_size x = F.pad(x, (0, 0, pad_l, pad_r, pad_t, pad_b)) kv = F.pad(kv, (0, 0, pad_l, pad_r, pad_t, pad_b)) _, Hp, Wp, _ = x.shape # cyclic shift if self.shift_size > 0: shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2)) shifted_kv = torch.roll(kv, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2)) else: shifted_x = x shifted_kv = kv attn_mask = None # partition windows x_windows = window_partition(shifted_x, self.window_size) # [nW*B, Mh, Mw, C] x_windows = x_windows.view(-1, self.window_size * self.window_size, C) # [nW*B, Mh*Mw, C] kv_windows = window_partition(shifted_kv, self.window_size) # [nW*B, Mh, Mw, C] kv_windows = kv_windows.view(-1, self.window_size * self.window_size, C) # [nW*B, Mh*Mw, C] # W-MSA/SW-MSA attn_windows = self.attn(x_windows, kv_windows, mask=attn_mask) # [nW*B, Mh*Mw, C] # merge windows attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C) # [nW*B, Mh, Mw, C] shifted_x = window_reverse(attn_windows, self.window_size, Hp, Wp) # [B, H', W', C] # reverse cyclic shift if self.shift_size > 0: x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2)) else: x = shifted_x if pad_r > 0 or pad_b > 0: # Remove the padded data from the front. x = x[:, :H, :W, :].contiguous() x = x.view(B, H * W, C) # FFN x = shortcut + self.drop_path(x) x = x + self.drop_path(self.mlp(self.norm2(x))) return x class CrossAttentionLayer(nn.Module): def __init__(self, dim, depth, num_heads, window_size, mlp_ratio=4., qkv_bias=True, drop=0., attn_drop=0., drop_path=0., norm_layer=nn.LayerNorm,): super().__init__() self.dim = dim self.depth = depth self.window_size = window_size self.shift_size = window_size // 2 # build blocks self.blocks = nn.ModuleList([ SwinTransformerCABlock( dim=dim, num_heads=num_heads, window_size=window_size, shift_size=0 if (i % 2 == 0) else self.shift_size, mlp_ratio=mlp_ratio, qkv_bias=qkv_bias, drop=drop, attn_drop=attn_drop, drop_path=drop_path[i] if isinstance(drop_path, list) else drop_path, norm_layer=norm_layer) for i in range(depth)]) def create_mask(self, x, H, W): # calculate attention mask for SW-MSA # Ensure that Hp and Wp are multiples of window_size. Hp = int(np.ceil(H / self.window_size)) * self.window_size Wp = int(np.ceil(W / self.window_size)) * self.window_size # Have the same channel arrangement as the feature map for ease of subsequent window_partition. img_mask = torch.zeros((1, Hp, Wp, 1), device=x.device) # [1, Hp, Wp, 1] h_slices = (slice(0, -self.window_size), slice(-self.window_size, -self.shift_size), slice(-self.shift_size, None)) w_slices = (slice(0, -self.window_size), slice(-self.window_size, -self.shift_size), slice(-self.shift_size, None)) cnt = 0 for h in h_slices: for w in w_slices: img_mask[:, h, w, :] = cnt cnt += 1 mask_windows = window_partition(img_mask, self.window_size) # [nW, Mh, Mw, 1] mask_windows = mask_windows.view(-1, self.window_size * self.window_size) # [nW, Mh*Mw] attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2) # [nW, 1, Mh*Mw] - [nW, Mh*Mw, 1] # [nW, Mh*Mw, Mh*Mw] attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0)) return attn_mask def forward(self, x, kv, H, W): attn_mask = self.create_mask(x, H, W) # [nW, Mh*Mw, Mh*Mw] for blk in self.blocks: blk.H, blk.W = H, W x = blk(x, kv, attn_mask) return x, H, W if __name__ == '__main__': shape = [8, 3, 32, 64, 64] tensor = torch.zeros(shape) _, _, _, H, W = tensor.shape front_plane = tensor.reshape(-1, 32, 64*64).permute(0, 2,1).contiguous() back_plane = torch.zeros(front_plane.shape) model = CrossAttentionLayer( dim=32, depth=2, num_heads=8, window_size=2, ) output = model(front_plane, back_plane, H, W)