YOLOv11改进 | 检测头篇 | 辅助特征融合模块ASFF改进yolov11检测头（适配YOLOv11版本，全网独家创新）

import copy
import torch
import torch.nn as nn
from ultralytics.utils.tal import dist2bbox, make_anchors
import math
import torch.nn.functional as F
 
__all__ = ['ASFFHead']
 
def autopad(k, p=None, d=1):  # kernel, padding, dilation
    """Pad to 'same' shape outputs."""
    if d > 1:
        k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k]  # actual kernel-size
    if p is None:
        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
    return p
 
 
class Conv(nn.Module):
    """Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)."""
    default_act = nn.SiLU()  # default activation
 
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
        """Initialize Conv layer with given arguments including activation."""
        super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()
 
    def forward(self, x):
        """Apply convolution, batch normalization and activation to input tensor."""
        return self.act(self.bn(self.conv(x)))
 
    def forward_fuse(self, x):
        """Perform transposed convolution of 2D data."""
        return self.act(self.conv(x))
 
 
class DFL(nn.Module):
    """
    Integral module of Distribution Focal Loss (DFL) CSDN:Snu77 .
    Proposed in Generalized Focal Loss https://ieeexplore.ieee.org/document/9792391
    """
 
    def __init__(self, c1=16):
        """Initialize a convolutional layer with a given number of input channels."""
        super().__init__()
        self.conv = nn.Conv2d(c1, 1, 1, bias=False).requires_grad_(False)
        x = torch.arange(c1, dtype=torch.float)
        self.conv.weight.data[:] = nn.Parameter(x.view(1, c1, 1, 1))
        self.c1 = c1
 
    def forward(self, x):
        """Applies a transformer layer on input tensor 'x' and returns a tensor."""
        b, c, a = x.shape  # batch, channels, anchors
        return self.conv(x.view(b, 4, self.c1, a).transpose(2, 1).softmax(1)).view(b, 4, a)
        # return self.conv(x.view(b, self.c1, 4, a).softmax(1)).view(b, 4, a)
 
 
class ASFFV5(nn.Module):
    def __init__(self, level, ch, multiplier=1, rfb=False, vis=False, act_cfg=True):
        """
        CSDN:Snu77
        """
        super(ASFFV5, self).__init__()
        self.level = level
        self.dim = [int(ch[2] * multiplier), int(ch[1] * multiplier),
                    int(ch[0] * multiplier)]
        # print(self.dim)
 
        self.inter_dim = self.dim[self.level]
        if level == 0:
            self.stride_level_1 = Conv(int(ch[1] * multiplier), self.inter_dim, 3, 2)
 
            self.stride_level_2 = Conv(int(ch[0] * multiplier), self.inter_dim, 3, 2)
 
            self.expand = Conv(self.inter_dim, int(
                ch[2] * multiplier), 3, 1)
        elif level == 1:
            self.compress_level_0 = Conv(
                int(ch[2] * multiplier), self.inter_dim, 1, 1)
            self.stride_level_2 = Conv(
                int(ch[0] * multiplier), self.inter_dim, 3, 2)
            self.expand = Conv(self.inter_dim, int(ch[1] * multiplier), 3, 1)
        elif level == 2:
            self.compress_level_0 = Conv(
                int(ch[2] * multiplier), self.inter_dim, 1, 1)
            self.compress_level_1 = Conv(
                int(ch[1] * multiplier), self.inter_dim, 1, 1)
            self.expand = Conv(self.inter_dim, int(
                ch[0] * multiplier), 3, 1)
 
        # when adding rfb, we use half number of channels to save memory
        compress_c = 8 if rfb else 16
        self.weight_level_0 = Conv(
            self.inter_dim, compress_c, 1, 1)
        self.weight_level_1 = Conv(
            self.inter_dim, compress_c, 1, 1)
        self.weight_level_2 = Conv(
            self.inter_dim, compress_c, 1, 1)
 
        self.weight_levels = Conv(
            compress_c * 3, 3, 1, 1)
        self.vis = vis
 
    def forward(self, x):  # l,m,s
        """
        # 128, 256, 512
        512, 256, 128
        from small -> large
        """
        x_level_0 = x[2]  # l
        x_level_1 = x[1]  # m
        x_level_2 = x[0]  # s
        # print('x_level_0: ', x_level_0.shape)
        # print('x_level_1: ', x_level_1.shape)
        # print('x_level_2: ', x_level_2.shape)
        if self.level == 0:
            level_0_resized = x_level_0
            level_1_resized = self.stride_level_1(x_level_1)
            level_2_downsampled_inter = F.max_pool2d(
                x_level_2, 3, stride=2, padding=1)
            level_2_resized = self.stride_level_2(level_2_downsampled_inter)
        elif self.level == 1:
            level_0_compressed = self.compress_level_0(x_level_0)
            level_0_resized = F.interpolate(
                level_0_compressed, scale_factor=2, mode='nearest')
            level_1_resized = x_level_1
            level_2_resized = self.stride_level_2(x_level_2)
        elif self.level == 2:
            level_0_compressed = self.compress_level_0(x_level_0)
            level_0_resized = F.interpolate(
                level_0_compressed, scale_factor=4, mode='nearest')
            x_level_1_compressed = self.compress_level_1(x_level_1)
            level_1_resized = F.interpolate(
                x_level_1_compressed, scale_factor=2, mode='nearest')
            level_2_resized = x_level_2
 
        # print('level: {}, l1_resized: {}, l2_resized: {}'.format(self.level,
        #      level_1_resized.shape, level_2_resized.shape))
        level_0_weight_v = self.weight_level_0(level_0_resized)
        level_1_weight_v = self.weight_level_1(level_1_resized)
        level_2_weight_v = self.weight_level_2(level_2_resized)
        # print('level_0_weight_v: ', level_0_weight_v.shape)
        # print('level_1_weight_v: ', level_1_weight_v.shape)
        # print('level_2_weight_v: ', level_2_weight_v.shape)
 
        levels_weight_v = torch.cat(
            (level_0_weight_v, level_1_weight_v, level_2_weight_v), 1)
        levels_weight = self.weight_levels(levels_weight_v)
        levels_weight = F.softmax(levels_weight, dim=1)
 
        fused_out_reduced = level_0_resized * levels_weight[:, 0:1, :, :] + \
                            level_1_resized * levels_weight[:, 1:2, :, :] + \
                            level_2_resized * levels_weight[:, 2:, :, :]
 
        out = self.expand(fused_out_reduced)
 
        if self.vis:
            return out, levels_weight, fused_out_reduced.sum(dim=1)
        else:
            return out
 
class DWConv(Conv):
    """Depth-wise convolution."""
 
    def __init__(self, c1, c2, k=1, s=1, d=1, act=True):  # ch_in, ch_out, kernel, stride, dilation, activation
        """Initialize Depth-wise convolution with given parameters."""
        super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act)
 
 
 
class ASFFHead(nn.Module):
    """YOLOv8 Detect head for detection models. CSDNSnu77"""
 
    dynamic = False  # force grid reconstruction
    export = False  # export mode
    end2end = False  # end2end
    max_det = 300  # max_det
    shape = None
    anchors = torch.empty(0)  # init
    strides = torch.empty(0)  # init
 
    def __init__(self, nc=80, ch=(), multiplier=1, rfb=False):
        """Initializes the YOLOv8 detection layer with specified number of classes and channels."""
        super().__init__()
        self.nc = nc  # number of classes
        self.nl = len(ch)  # number of detection layers
        self.reg_max = 16  # DFL channels (ch[0] // 16 to scale 4/8/12/16/20 for n/s/m/l/x)
        self.no = nc + self.reg_max * 4  # number of outputs per anchor
        self.stride = torch.zeros(self.nl)  # strides computed during build
        c2, c3 = max((16, ch[0] // 4, self.reg_max * 4)), max(ch[0], min(self.nc, 100))  # channels
        self.cv2 = nn.ModuleList(
            nn.Sequential(Conv(x, c2, 3), Conv(c2, c2, 3), nn.Conv2d(c2, 4 * self.reg_max, 1)) for x in ch
        )
        self.cv3 = nn.ModuleList(
            nn.Sequential(
                nn.Sequential(DWConv(x, x, 3), Conv(x, c3, 1)),
                nn.Sequential(DWConv(c3, c3, 3), Conv(c3, c3, 1)),
                nn.Conv2d(c3, self.nc, 1),
            )
            for x in ch
        )
        self.dfl = DFL(self.reg_max) if self.reg_max > 1 else nn.Identity()
 
        self.l0_fusion = ASFFV5(level=0, ch=ch, multiplier=multiplier, rfb=rfb)
        self.l1_fusion = ASFFV5(level=1, ch=ch, multiplier=multiplier, rfb=rfb)
        self.l2_fusion = ASFFV5(level=2, ch=ch, multiplier=multiplier, rfb=rfb)
 
 
        if self.end2end:
            self.one2one_cv2 = copy.deepcopy(self.cv2)
            self.one2one_cv3 = copy.deepcopy(self.cv3)
 
    def forward(self, x):
        x1 = self.l0_fusion(x)
        x2 = self.l1_fusion(x)
        x3 = self.l2_fusion(x)
        x = [x3, x2, x1]
        """Concatenates and returns predicted bounding boxes and class probabilities."""
        if self.end2end:
            return self.forward_end2end(x)
        for i in range(self.nl):
            x[i] = torch.cat((self.cv2[i](x[i]), self.cv3[i](x[i])), 1)
        if self.training:  # Training path
            return x
        y = self._inference(x)
        return y if self.export else (y, x)
 
    def forward_end2end(self, x):
        """
        Performs forward pass of the v10Detect module.
        Args:
            x (tensor): Input tensor.
        Returns:
            (dict, tensor): If not in training mode, returns a dictionary containing the outputs of both one2many and one2one detections.
                           If in training mode, returns a dictionary containing the outputs of one2many and one2one detections separately.
        """
        x_detach = [xi.detach() for xi in x]
        one2one = [
            torch.cat((self.one2one_cv2[i](x_detach[i]), self.one2one_cv3[i](x_detach[i])), 1) for i in range(self.nl)
        ]
        for i in range(self.nl):
            x[i] = torch.cat((self.cv2[i](x[i]), self.cv3[i](x[i])), 1)
        if self.training:  # Training path
            return {"one2many": x, "one2one": one2one}
 
        y = self._inference(one2one)
        y = self.postprocess(y.permute(0, 2, 1), self.max_det, self.nc)
        return y if self.export else (y, {"one2many": x, "one2one": one2one})
 
    def _inference(self, x):
        """Decode predicted bounding boxes and class probabilities based on multiple-level feature maps."""
        # Inference path
        shape = x[0].shape  # BCHW
        x_cat = torch.cat([xi.view(shape[0], self.no, -1) for xi in x], 2)
        if self.dynamic or self.shape != shape:
            self.anchors, self.strides = (x.transpose(0, 1) for x in make_anchors(x, self.stride, 0.5))
            self.shape = shape
 
        if self.export and self.format in {"saved_model", "pb", "tflite", "edgetpu", "tfjs"}:  # avoid TF FlexSplitV ops
            box = x_cat[:, : self.reg_max * 4]
            cls = x_cat[:, self.reg_max * 4 :]
        else:
            box, cls = x_cat.split((self.reg_max * 4, self.nc), 1)
 
        if self.export and self.format in {"tflite", "edgetpu"}:
            # Precompute normalization factor to increase numerical stability
            # See https://github.com/ultralytics/ultralytics/issues/7371
            grid_h = shape[2]
            grid_w = shape[3]
            grid_size = torch.tensor([grid_w, grid_h, grid_w, grid_h], device=box.device).reshape(1, 4, 1)
            norm = self.strides / (self.stride[0] * grid_size)
            dbox = self.decode_bboxes(self.dfl(box) * norm, self.anchors.unsqueeze(0) * norm[:, :2])
        else:
            dbox = self.decode_bboxes(self.dfl(box), self.anchors.unsqueeze(0)) * self.strides
 
        return torch.cat((dbox, cls.sigmoid()), 1)
 
    def bias_init(self):
        """Initialize Detect() biases, WARNING: requires stride availability."""
        m = self  # self.model[-1]  # Detect() module
        # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1
        # ncf = math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum())  # nominal class frequency
        for a, b, s in zip(m.cv2, m.cv3, m.stride):  # from
            a[-1].bias.data[:] = 1.0  # box
            b[-1].bias.data[: m.nc] = math.log(5 / m.nc / (640 / s) ** 2)  # cls (.01 objects, 80 classes, 640 img)
        if self.end2end:
            for a, b, s in zip(m.one2one_cv2, m.one2one_cv3, m.stride):  # from
                a[-1].bias.data[:] = 1.0  # box
                b[-1].bias.data[: m.nc] = math.log(5 / m.nc / (640 / s) ** 2)  # cls (.01 objects, 80 classes, 640 img)
 
    def decode_bboxes(self, bboxes, anchors):
        """Decode bounding boxes."""
        return dist2bbox(bboxes, anchors, xywh=not self.end2end, dim=1)
 
    @staticmethod
    def postprocess(preds: torch.Tensor, max_det: int, nc: int = 80):
        """
        Post-processes YOLO model predictions.
        Args:
            preds (torch.Tensor): Raw predictions with shape (batch_size, num_anchors, 4 + nc) with last dimension
                format [x, y, w, h, class_probs].
            max_det (int): Maximum detections per image.
            nc (int, optional): Number of classes. Default: 80.
        Returns:
            (torch.Tensor): Processed predictions with shape (batch_size, min(max_det, num_anchors), 6) and last
                dimension format [x, y, w, h, max_class_prob, class_index].
        """
        batch_size, anchors, _ = preds.shape  # i.e. shape(16,8400,84)
        boxes, scores = preds.split([4, nc], dim=-1)
        index = scores.amax(dim=-1).topk(min(max_det, anchors))[1].unsqueeze(-1)
        boxes = boxes.gather(dim=1, index=index.repeat(1, 1, 4))
        scores = scores.gather(dim=1, index=index.repeat(1, 1, nc))
        scores, index = scores.flatten(1).topk(min(max_det, anchors))
        i = torch.arange(batch_size)[..., None]  # batch indices
        return torch.cat([boxes[i, index // nc], scores[..., None], (index % nc)[..., None].float()], dim=-1)
 
 
 
if __name__ == "__main__":
    # Generating Sample image
    image1 = (1, 64, 32, 32)
    image2 = (1, 128, 16, 16)
    image3 = (1, 256, 8, 8)
 
    image1 = torch.rand(image1)
    image2 = torch.rand(image2)
    image3 = torch.rand(image3)
    image = [image1, image2, image3]
    channel = (64, 128, 256)
    # Model
    mobilenet_v1 = ASFFHead(nc=80, ch=channel)
 
    out = mobilenet_v1(image)
    print(out)

​

        else:
            return 'detect'

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLO11 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
 
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo11n.yaml' will call yolo11.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
  s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
  m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
  l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
  x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs
 
# YOLO11n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
  - [-1, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2, [1024, True]]
  - [-1, 1, SPPF, [1024, 5]] # 9
  - [-1, 2, C2PSA, [1024]] # 10
 
# YOLO11n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 2, C3k2, [512, False]] # 13
 
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
 
  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
 
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
 
  - [[16, 19, 22], 1, ASFFHead, [nc]] # Detect(P3, P4, P5)

​