YOLOv8改进：Gold-YOLO，遥遥领先，超越所有YOLO ，助力小目标检测 | 华为诺亚NeurIPS23

###################### gold-yolo  ####     STRAT   by  AI&CV  ###############################
#gold-yolo Gather-and-Distribute Mechanism
class top_Block(nn.Module):

    def __init__(self, dim, key_dim, num_heads, mlp_ratio=4., attn_ratio=2., drop=0.,
                 drop_path=0.):
        super().__init__()
        self.dim = dim
        self.num_heads = num_heads
        self.mlp_ratio = mlp_ratio

        self.attn = Attention(dim, key_dim=key_dim, num_heads=num_heads, attn_ratio=attn_ratio)

        # NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
        mlp_hidden_dim = int(dim * mlp_ratio)
        self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, drop=drop)

    def forward(self, x1):
        x1 = x1 + self.drop_path(self.attn(x1))
        x1 = x1 + self.drop_path(self.mlp(x1))
        return x1


class TopBasicLayer(nn.Module):
    def __init__(self, embedding_dim, ouc_list, block_num=2, key_dim=8, num_heads=4,
                 mlp_ratio=4., attn_ratio=2., drop=0., attn_drop=0., drop_path=0.):
        super().__init__()
        self.block_num = block_num

        self.transformer_blocks = nn.ModuleList()
        for i in range(self.block_num):
            self.transformer_blocks.append(top_Block(
                embedding_dim, key_dim=key_dim, num_heads=num_heads,
                mlp_ratio=mlp_ratio, attn_ratio=attn_ratio,
                drop=drop, drop_path=drop_path[i] if isinstance(drop_path, list) else drop_path))
        self.conv = nn.Conv2d(embedding_dim, sum(ouc_list), 1)

    def forward(self, x):
        # token * N
        for i in range(self.block_num):
            x = self.transformer_blocks[i](x)
        return self.conv(x)


class AdvPoolFusion(nn.Module):
    def forward(self, x):
        x1, x2 = x
        if torch.onnx.is_in_onnx_export():
            self.pool = onnx_AdaptiveAvgPool2d
        else:
            self.pool = nn.functional.adaptive_avg_pool2d

        N, C, H, W = x2.shape
        output_size = np.array([H, W])
        x1 = self.pool(x1, output_size)

        return torch.cat([x1, x2], 1)

###################### gold-yolo  ####     END   by  AI&CV  ###############################

YOLOv8-goldYOLO summary: 359 layers, 6015123 parameters, 0 gradients, 11.9 GFLOPs
                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 3/3 [00:04<00:00,  1.41s/it]
                   all        171        199      0.871      0.679      0.768      0.461
Speed: 0.3ms preprocess, 3.9ms inference, 0.0ms loss, 1.6ms postprocess per image