💖💖>>>加勒比海带，QQ2479200884<<<💖💖
🍀🍀>>>【YOLO魔法搭配&论文投稿咨询】<<<🍀🍀
✨✨>>>学习交流 | 温澜潮生 | 合作共赢 | 共同进步<<<✨✨
📚📚>>>人工智能 | 计算机视觉 | 深度学习Tricks | 第一时间送达<<<📚📚
论文题目：Swin Transformer V2: Scaling Up Capacity and Resolution
论文地址：https://arxiv.org/pdf/2111.09883.pdf
源代码：https://github.com/microsoft/Swin-Transformer
面临问题：
作者提出了将Swin Transformer缩放到30亿个参数的技术 ，并使其能够使用高达1536×1536分辨率的图像进行训练。在很多方面达到了SOTA。
目前，视觉模型尚未像NLP语言模型那样被广泛探索，部分原因是训练和应用中的以下差异:
（1）视觉模型通常在规模上面临不稳定性问题；
（2）许多下游视觉任务需要高分辨率图像，如何有效地将低分辨率预训练的模型转换为高分辨率模型尚未被有效探索,也就是跨窗口分辨率迁移模型时性能下降。
（3）当图像分辨率较高时，GPU显存消耗也是一个问题。
解决思路：
为了解决这些问题，作者提出了几种技术，并在本文中以Swin Transformer进行了说明：
（1）提高大视觉模型稳定性的后归一化（post normalization） 技术和缩放余弦注意力（scaled cosine attention）方法，以提高大型视觉模型的稳定性；
（2）一种对数间隔连续位置偏差技术（log-spaced continuous position bias technique） ，用于有效地将在低分辨率图像中预训练的模型转换为其高分辨率对应模型。
（3）分享节约GPU内存消耗方法，使得训练大分辨率模型可行；
YOLOv5结合Swin Transformer V2 教程:
配置common.py文件：
class WindowAttention(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: Trueqk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if setattn_drop (float, optional): Dropout ratio of attention weight. Default: 0.0proj_drop (float, optional): Dropout ratio of output. Default: 0.0"""def __init__(self, dim, window_size, num_heads, qkv_bias=True, qk_scale=None, attn_drop=0., proj_drop=0.):super().__init__()self.dim = dimself.window_size = window_size # Wh, Wwself.num_heads = num_headshead_dim = dim // num_headsself.scale = qk_scale or head_dim ** -0.5# define a parameter table of relative position biasself.relative_position_bias_table = nn.Parameter(torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1), num_heads)) # 2*Wh-1 * 2*Ww-1, nH# get pair-wise relative position index for each token inside the windowcoords_h = torch.arange(self.window_size[0])coords_w = torch.arange(self.window_size[1])coords = torch.stack(torch.meshgrid([coords_h, coords_w])) # 2, Wh, Wwcoords_flatten = torch.flatten(coords, 1) # 2, Wh*Wwrelative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :] # 2, Wh*Ww, Wh*Wwrelative_coords = relative_coords.permute(1, 2, 0).contiguous() # Wh*Ww, Wh*Ww, 2relative_coords[:, :, 0] += self.window_size[0] - 1 # shift to start from 0relative_coords[:, :, 1] += self.window_size[1] - 1relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1relative_position_index = relative_coords.sum(-1) # Wh*Ww, Wh*Wwself.register_buffer("relative_position_index", relative_position_index)self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)self.attn_drop = nn.Dropout(attn_drop)self.proj = nn.Linear(dim, dim)self.proj_drop = nn.Dropout(proj_drop)trunc_normal_(self.relative_position_bias_table, std=.02)self.softmax = nn.Softmax(dim=-1)def forward(self, x, mask=None):"""Args:x: input features with shape of (num_windows*B, N, C)mask: (0/-inf) mask with shape of (num_windows, Wh*Ww, Wh*Ww) or None"""B_, N, C = x.shapeqkv = self.qkv(x).reshape(B_, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)q, k, v = qkv[0], qkv[1], qkv[2] # make torchscript happy (cannot use tensor as tuple)q = q * self.scaleattn = (q @ k.transpose(-2, -1))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) # Wh*Ww,Wh*Ww,nHrelative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous() # nH, Wh*Ww, Wh*Wwattn = attn + relative_position_bias.unsqueeze(0)if mask is not None:nW = mask.shape[0]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)# print(attn.dtype, v.dtype)x = (attn @ v).transpose(1, 2).reshape(B_, N, C)x = self.proj(x)x = self.proj_drop(x)return xclass Mlp(nn.Module):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_featureshidden_features = hidden_features or in_featuresself.fc1 = nn.Linear(in_features, hidden_features)self.act = act_layer()self.fc2 = nn.Linear(hidden_features, out_features)self.drop = nn.Dropout(drop)def forward(self, x):x = self.fc1(x)x = self.act(x)x = self.drop(x)x = self.fc2(x)x = self.drop(x)return xdef window_partition(x, window_size):"""Args:x: (B, H, W, C)window_size (int): window sizeReturns:windows: (num_windows*B, window_size, window_size, C)"""B, H, W, C = x.shapeassert H % window_size == 0, 'feature map h and w can not divide by window size'x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)return windowsdef window_reverse(windows, window_size, H, W):"""Args:windows: (num_windows*B, window_size, window_size, C)window_size (int): Window sizeH (int): Height of imageW (int): Width of imageReturns:x: (B, H, W, C)"""B = int(windows.shape[0] / (H * W / window_size / window_size))x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)return xclass SwinTransformerLayer(nn.Module):r""" Swin Transformer Layer.Args:dim (int): Number of input channels.input_resolution (tuple[int]): Input resulotion.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: Trueqk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.drop (float, optional): Dropout rate. Default: 0.0attn_drop (float, optional): Attention dropout rate. Default: 0.0drop_path (float, optional): Stochastic depth rate. Default: 0.0act_layer (nn.Module, optional): Activation layer. Default: nn.GELUnorm_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, qk_scale=None, drop=0., attn_drop=0., drop_path=0.,act_layer=nn.GELU, norm_layer=nn.LayerNorm):super().__init__()self.dim = dimself.num_heads = num_headsself.window_size = window_sizeself.shift_size = shift_sizeself.mlp_ratio = mlp_ratio# if min(self.input_resolution) <= self.window_size:# # if window size is larger than input resolution, we don't partition windows# self.shift_size = 0# self.window_size = min(self.input_resolution)assert 0 <= self.shift_size < self.window_size, "shift_size must in 0-window_size"self.norm1 = norm_layer(dim)self.attn = WindowAttention(dim, window_size=to_2tuple(self.window_size), num_heads=num_heads,qkv_bias=qkv_bias, qk_scale=qk_scale, 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)
