YOLOv11改进 | 二次创新篇 | 可变形卷积DCNv3 升级动态尺度统一检测头DynamicHead(全网独家首发)

​

​

​

​

import copy
import math
from mmcv.ops import ModulatedDeformConv2d
from ultralytics.nn.modules import DFL
 
from ultralytics.utils.tal import dist2bbox, make_anchors
import warnings
import torch
from torch import nn
import torch.nn.functional as F
from torch.nn.init import xavier_uniform_, constant_
 
 
__all__ = ['DynamicDCNv3Head']
 
def _get_reference_points(spatial_shapes, device, kernel_h, kernel_w, dilation_h, dilation_w, pad_h=0, pad_w=0, stride_h=1, stride_w=1):
    _, H_, W_, _ = spatial_shapes
    H_out = (H_ - (dilation_h * (kernel_h - 1) + 1)) // stride_h + 1
    W_out = (W_ - (dilation_w * (kernel_w - 1) + 1)) // stride_w + 1
 
    ref_y, ref_x = torch.meshgrid(
        torch.linspace(
            # pad_h + 0.5,
            # H_ - pad_h - 0.5,
            (dilation_h * (kernel_h - 1)) // 2 + 0.5,
            (dilation_h * (kernel_h - 1)) // 2 + 0.5 + (H_out - 1) * stride_h,
            H_out,
            dtype=torch.float32,
            device=device),
        torch.linspace(
            # pad_w + 0.5,
            # W_ - pad_w - 0.5,
            (dilation_w * (kernel_w - 1)) // 2 + 0.5,
            (dilation_w * (kernel_w - 1)) // 2 + 0.5 + (W_out - 1) * stride_w,
            W_out,
            dtype=torch.float32,
            device=device))
    ref_y = ref_y.reshape(-1)[None] / H_
    ref_x = ref_x.reshape(-1)[None] / W_
 
    ref = torch.stack((ref_x, ref_y), -1).reshape(
        1, H_out, W_out, 1, 2)
 
    return ref
 
 
def _generate_dilation_grids(spatial_shapes, kernel_h, kernel_w, dilation_h, dilation_w, group, device):
    _, H_, W_, _ = spatial_shapes
    points_list = []
    x, y = torch.meshgrid(
        torch.linspace(
            -((dilation_w * (kernel_w - 1)) // 2),
            -((dilation_w * (kernel_w - 1)) // 2) +
            (kernel_w - 1) * dilation_w, kernel_w,
            dtype=torch.float32,
            device=device),
        torch.linspace(
            -((dilation_h * (kernel_h - 1)) // 2),
            -((dilation_h * (kernel_h - 1)) // 2) +
            (kernel_h - 1) * dilation_h, kernel_h,
            dtype=torch.float32,
            device=device))
 
    points_list.extend([x / W_, y / H_])
    grid = torch.stack(points_list, -1).reshape(-1, 1, 2).\
        repeat(1, group, 1).permute(1, 0, 2)
    grid = grid.reshape(1, 1, 1, group * kernel_h * kernel_w, 2)
 
    return grid
 
 
def dcnv3_core_pytorch(
        input, offset, mask, kernel_h,
        kernel_w, stride_h, stride_w, pad_h,
        pad_w, dilation_h, dilation_w, group,
        group_channels, offset_scale):
    # for debug and test only,
    # need to use cuda version instead
    input = F.pad(
        input,
        [0, 0, pad_h, pad_h, pad_w, pad_w])
    N_, H_in, W_in, _ = input.shape
    _, H_out, W_out, _ = offset.shape
 
    ref = _get_reference_points(
        input.shape, input.device, kernel_h, kernel_w, dilation_h, dilation_w, pad_h, pad_w, stride_h, stride_w)
    grid = _generate_dilation_grids(
        input.shape, kernel_h, kernel_w, dilation_h, dilation_w, group, input.device)
    spatial_norm = torch.tensor([W_in, H_in]).reshape(1, 1, 1, 2).\
        repeat(1, 1, 1, group*kernel_h*kernel_w).to(input.device)
 
    sampling_locations = (ref + grid * offset_scale).repeat(N_, 1, 1, 1, 1).flatten(3, 4) + \
        offset * offset_scale / spatial_norm
 
    P_ = kernel_h * kernel_w
    sampling_grids = 2 * sampling_locations - 1
    # N_, H_in, W_in, group*group_channels -> N_, H_in*W_in, group*group_channels -> N_, group*group_channels, H_in*W_in -> N_*group, group_channels, H_in, W_in
    input_ = input.view(N_, H_in*W_in, group*group_channels).transpose(1, 2).\
        reshape(N_*group, group_channels, H_in, W_in)
    # N_, H_out, W_out, group*P_*2 -> N_, H_out*W_out, group, P_, 2 -> N_, group, H_out*W_out, P_, 2 -> N_*group, H_out*W_out, P_, 2
    sampling_grid_ = sampling_grids.view(N_, H_out*W_out, group, P_, 2).transpose(1, 2).\
        flatten(0, 1)
    # N_*group, group_channels, H_out*W_out, P_
    sampling_input_ = F.grid_sample(
        input_, sampling_grid_, mode='bilinear', padding_mode='zeros', align_corners=False)
 
    # (N_, H_out, W_out, group*P_) -> N_, H_out*W_out, group, P_ -> (N_, group, H_out*W_out, P_) -> (N_*group, 1, H_out*W_out, P_)
    mask = mask.view(N_, H_out*W_out, group, P_).transpose(1, 2).\
        reshape(N_*group, 1, H_out*W_out, P_)
    output = (sampling_input_ * mask).sum(-1).view(N_,
                                                   group*group_channels, H_out*W_out)
 
    return output.transpose(1, 2).reshape(N_, H_out, W_out, -1).contiguous()
 
 
class to_channels_first(nn.Module):
 
    def __init__(self):
        super().__init__()
 
    def forward(self, x):
        return x.permute(0, 3, 1, 2)
 
 
class to_channels_last(nn.Module):
 
    def __init__(self):
        super().__init__()
 
    def forward(self, x):
        return x.permute(0, 2, 3, 1)
 
 
def build_norm_layer(dim,
                     norm_layer,
                     in_format='channels_last',
                     out_format='channels_last',
                     eps=1e-6):
    layers = []
    if norm_layer == 'BN':
        if in_format == 'channels_last':
            layers.append(to_channels_first())
        layers.append(nn.BatchNorm2d(dim))
        if out_format == 'channels_last':
            layers.append(to_channels_last())
    elif norm_layer == 'LN':
        if in_format == 'channels_first':
            layers.append(to_channels_last())
        layers.append(nn.LayerNorm(dim, eps=eps))
        if out_format == 'channels_first':
            layers.append(to_channels_first())
    else:
        raise NotImplementedError(
            f'build_norm_layer does not support {norm_layer}')
    return nn.Sequential(*layers)
 
 
def build_act_layer(act_layer):
    if act_layer == 'ReLU':
        return nn.ReLU(inplace=True)
    elif act_layer == 'SiLU':
        return nn.SiLU(inplace=True)
    elif act_layer == 'GELU':
        return nn.GELU()
 
    raise NotImplementedError(f'build_act_layer does not support {act_layer}')
 
 
def _is_power_of_2(n):
    if (not isinstance(n, int)) or (n < 0):
        raise ValueError(
            "invalid input for _is_power_of_2: {} (type: {})".format(n, type(n)))
 
    return (n & (n - 1) == 0) and n != 0
 
 
class CenterFeatureScaleModule(nn.Module):
    def forward(self,
                query,
                center_feature_scale_proj_weight,
                center_feature_scale_proj_bias):
        center_feature_scale = F.linear(query,
                                        weight=center_feature_scale_proj_weight,
                                        bias=center_feature_scale_proj_bias).sigmoid()
        return center_feature_scale
 
 
class DCNv3_pytorch(nn.Module):
    def __init__(
            self,
            channels=64,
            kernel_size=3,
            dw_kernel_size=None,
            stride=1,
            pad=1,
            dilation=1,
            group=4,
            offset_scale=1.0,
            act_layer='GELU',
            norm_layer='LN',
            center_feature_scale=False):
        """
        DCNv3 Module
        :param channels
        :param kernel_size
        :param stride
        :param pad
        :param dilation
        :param group
        :param offset_scale
        :param act_layer
        :param norm_layer
        """
        super().__init__()
 
        if channels % group != 0:
            raise ValueError(
                f'channels must be divisible by group, but got {channels} and {group}')
        _d_per_group = channels // group
        dw_kernel_size = dw_kernel_size if dw_kernel_size is not None else kernel_size
        # you'd better set _d_per_group to a power of 2 which is more efficient in our CUDA implementation
        if not _is_power_of_2(_d_per_group):
            warnings.warn(
                "You'd better set channels in DCNv3 to make the dimension of each attention head a power of 2 "
                "which is more efficient in our CUDA implementation.")
 
        self.offset_scale = offset_scale
        self.channels = channels
        self.kernel_size = kernel_size
        self.dw_kernel_size = dw_kernel_size
        self.stride = stride
        self.dilation = dilation
        self.pad = pad
        self.group = group
        self.group_channels = channels // group
        self.offset_scale = offset_scale
        self.center_feature_scale = center_feature_scale
 
        self.dw_conv = nn.Sequential(
            nn.Conv2d(
                channels,
                channels,
                kernel_size=dw_kernel_size,
                stride=1,
                padding=(dw_kernel_size - 1) // 2,
                groups=channels),
            build_norm_layer(
                channels,
                norm_layer,
                'channels_first',
                'channels_last'),
            build_act_layer(act_layer))
        self.offset = nn.Linear(
            channels,
            group * kernel_size * kernel_size * 2)
        self.mask = nn.Linear(
            channels,
            group * kernel_size * kernel_size)
        self.input_proj = nn.Linear(channels, channels)
        self.output_proj = nn.Linear(channels, channels)
        self._reset_parameters()
 
        if center_feature_scale:
            self.center_feature_scale_proj_weight = nn.Parameter(
                torch.zeros((group, channels), dtype=torch.float))
            self.center_feature_scale_proj_bias = nn.Parameter(
                torch.tensor(0.0, dtype=torch.float).view((1,)).repeat(group, ))
            self.center_feature_scale_module = CenterFeatureScaleModule()
 
    def _reset_parameters(self):
        constant_(self.offset.weight.data, 0.)
        constant_(self.offset.bias.data, 0.)
        constant_(self.mask.weight.data, 0.)
        constant_(self.mask.bias.data, 0.)
        xavier_uniform_(self.input_proj.weight.data)
        constant_(self.input_proj.bias.data, 0.)
        xavier_uniform_(self.output_proj.weight.data)
        constant_(self.output_proj.bias.data, 0.)
 
    def forward(self, input):
        """
        :param query                       (N, H, W, C)
        :return output                     (N, H, W, C)
        """
        input = input.permute(0, 2, 3, 1)
        N, H, W, _ = input.shape
 
        x = self.input_proj(input)
        x_proj = x
 
        x1 = input.permute(0, 3, 1, 2)
        x1 = self.dw_conv(x1)
        offset = self.offset(x1)
        mask = self.mask(x1).reshape(N, H, W, self.group, -1)
        mask = F.softmax(mask, -1).reshape(N, H, W, -1)
 
        x = dcnv3_core_pytorch(
            x, offset, mask,
            self.kernel_size, self.kernel_size,
            self.stride, self.stride,
            self.pad, self.pad,
            self.dilation, self.dilation,
            self.group, self.group_channels,
            self.offset_scale)
        if self.center_feature_scale:
            center_feature_scale = self.center_feature_scale_module(
                x1, self.center_feature_scale_proj_weight, self.center_feature_scale_proj_bias)
            # N, H, W, groups -> N, H, W, groups, 1 -> N, H, W, groups, _d_per_group -> N, H, W, channels
            center_feature_scale = center_feature_scale[..., None].repeat(
                1, 1, 1, 1, self.channels // self.group).flatten(-2)
            x = x * (1 - center_feature_scale) + x_proj * center_feature_scale
        x = self.output_proj(x).permute(0, 3, 1, 2)
 
        return x
 
 
def _make_divisible(v, divisor, min_value=None):
    if min_value is None:
        min_value = divisor
    new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
    # Make sure that round down does not go down by more than 10%.
    if new_v < 0.9 * v:
        new_v += divisor
    return new_v
 
 
class h_swish(nn.Module):
    def __init__(self, inplace=False):
        super(h_swish, self).__init__()
        self.inplace = inplace
 
    def forward(self, x):
        return x * F.relu6(x + 3.0, inplace=self.inplace) / 6.0
 
 
class h_sigmoid(nn.Module):
    def __init__(self, inplace=True, h_max=1):
        super(h_sigmoid, self).__init__()
        self.relu = nn.ReLU6(inplace=inplace)
        self.h_max = h_max
 
    def forward(self, x):
        return self.relu(x + 3) * self.h_max / 6
 
 
class DYReLU(nn.Module):
    def __init__(self, inp, oup, reduction=4, lambda_a=1.0, K2=True, use_bias=True, use_spatial=False,
                 init_a=[1.0, 0.0], init_b=[0.0, 0.0]):
        super(DYReLU, self).__init__()
        self.oup = oup
        self.lambda_a = lambda_a * 2
        self.K2 = K2
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
 
        self.use_bias = use_bias
        if K2:
            self.exp = 4 if use_bias else 2
        else:
            self.exp = 2 if use_bias else 1
        self.init_a = init_a
        self.init_b = init_b
 
        # determine squeeze
        if reduction == 4:
            squeeze = inp // reduction
        else:
            squeeze = _make_divisible(inp // reduction, 4)
        # print('reduction: {}, squeeze: {}/{}'.format(reduction, inp, squeeze))
        # print('init_a: {}, init_b: {}'.format(self.init_a, self.init_b))
 
        self.fc = nn.Sequential(
            nn.Linear(inp, squeeze),
            nn.ReLU(inplace=True),
            nn.Linear(squeeze, oup * self.exp),
            h_sigmoid()
        )
        if use_spatial:
            self.spa = nn.Sequential(
                nn.Conv2d(inp, 1, kernel_size=1),
                nn.BatchNorm2d(1),
            )
        else:
            self.spa = None
 
    def forward(self, x):
        if isinstance(x, list):
            x_in = x[0]
            x_out = x[1]
        else:
            x_in = x
            x_out = x
        b, c, h, w = x_in.size()
        y = self.avg_pool(x_in).view(b, c)
        y = self.fc(y).view(b, self.oup * self.exp, 1, 1)
        if self.exp == 4:
            a1, b1, a2, b2 = torch.split(y, self.oup, dim=1)
            a1 = (a1 - 0.5) * self.lambda_a + self.init_a[0]  # 1.0
            a2 = (a2 - 0.5) * self.lambda_a + self.init_a[1]
 
            b1 = b1 - 0.5 + self.init_b[0]
            b2 = b2 - 0.5 + self.init_b[1]
            out = torch.max(x_out * a1 + b1, x_out * a2 + b2)
        elif self.exp == 2:
            if self.use_bias:  # bias but not PL
                a1, b1 = torch.split(y, self.oup, dim=1)
                a1 = (a1 - 0.5) * self.lambda_a + self.init_a[0]  # 1.0
                b1 = b1 - 0.5 + self.init_b[0]
                out = x_out * a1 + b1
 
            else:
                a1, a2 = torch.split(y, self.oup, dim=1)
                a1 = (a1 - 0.5) * self.lambda_a + self.init_a[0]  # 1.0
                a2 = (a2 - 0.5) * self.lambda_a + self.init_a[1]
                out = torch.max(x_out * a1, x_out * a2)
 
        elif self.exp == 1:
            a1 = y
            a1 = (a1 - 0.5) * self.lambda_a + self.init_a[0]  # 1.0
            out = x_out * a1
 
        if self.spa:
            ys = self.spa(x_in).view(b, -1)
            ys = F.softmax(ys, dim=1).view(b, 1, h, w) * h * w
            ys = F.hardtanh(ys, 0, 3, inplace=True)/3
            out = out * ys
 
        return out
 
 
 
class Conv3x3Norm(torch.nn.Module):
    def __init__(self, in_channels, out_channels, stride):
        super(Conv3x3Norm, self).__init__()
        self.stride = stride
        self.dcnv3 = DCNv3_pytorch(in_channels, kernel_size=3, stride=stride)
        self.dcnv2 = ModulatedDeformConv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1)
        self.bn = nn.GroupNorm(num_groups=16, num_channels=out_channels)
 
    def forward(self, input, **kwargs):
        if self.stride == 2:
          x = self.dcnv2(input.contiguous(), **kwargs)
        else:
            x = self.dcnv3(input)
        x = self.bn(x)
        return x
 
class DyConv(nn.Module):
    def __init__(self, in_channels=256, out_channels=256, conv_func=Conv3x3Norm):
        super(DyConv, self).__init__()
 
        self.DyConv = nn.ModuleList()
        self.DyConv.append(conv_func(in_channels, out_channels, 1))
        self.DyConv.append(conv_func(in_channels, out_channels, 1))
        self.DyConv.append(conv_func(in_channels, out_channels, 2))
 
        self.AttnConv = nn.Sequential(
            nn.AdaptiveAvgPool2d(1),
            nn.Conv2d(in_channels, 1, kernel_size=1),
            nn.ReLU(inplace=True))
 
        self.h_sigmoid = h_sigmoid()
        self.relu = DYReLU(in_channels, out_channels)
        self.offset = nn.Conv2d(in_channels, 27, kernel_size=3, stride=1, padding=1)
        self.init_weights()
 
    def init_weights(self):
        for m in self.DyConv.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.normal_(m.weight.data, 0, 0.01)
                if m.bias is not None:
                    m.bias.data.zero_()
        for m in self.AttnConv.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.normal_(m.weight.data, 0, 0.01)
                if m.bias is not None:
                    m.bias.data.zero_()
 
    def forward(self, x):
        next_x = {}
        feature_names = list(x.keys())
        for level, name in enumerate(feature_names):
 
            feature = x[name]
 
            offset_mask = self.offset(feature)
            offset = offset_mask[:, :18, :, :]
            mask = offset_mask[:, 18:, :, :].sigmoid()
            conv_args = dict(offset=offset, mask=mask)
 
            temp_fea = [self.DyConv[1](feature, **conv_args)]
            if level > 0:
                temp_fea.append(self.DyConv[2](x[feature_names[level - 1]], **conv_args))
            if level < len(x) - 1:
                input = x[feature_names[level + 1]]
                temp_fea.append(F.interpolate(self.DyConv[0](input, **conv_args),
                                                    size=[feature.size(2), feature.size(3)]))
            attn_fea = []
            res_fea = []
            for fea in temp_fea:
                res_fea.append(fea)
                attn_fea.append(self.AttnConv(fea))
 
            res_fea = torch.stack(res_fea)
            spa_pyr_attn = self.h_sigmoid(torch.stack(attn_fea))
            mean_fea = torch.mean(res_fea * spa_pyr_attn, dim=0, keepdim=False)
            next_x[name] = self.relu(mean_fea)
 
        return next_x
 
 
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 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 DynamicDCNv3Head(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=()):
        """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()
 
        dyhead_tower = []
        for i in range(self.nl):
            channel = ch[i]
            dyhead_tower.append(
                DyConv(
                    channel,
                    channel,
                    conv_func=Conv3x3Norm,
                )
            )
        self.add_module('dyhead_tower', nn.Sequential(*dyhead_tower))
 
 
        if self.end2end:
            self.one2one_cv2 = copy.deepcopy(self.cv2)
            self.one2one_cv3 = copy.deepcopy(self.cv3)
 
    def forward(self, x):
        tensor_dict = {i: tensor for i, tensor in enumerate(x)}
        x = self.dyhead_tower(tensor_dict)
        x = list(x.values())
        """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, 64, 16, 16)
    image3 = (1, 64, 8, 8)
 
    image1 = torch.rand(image1)
    image2 = torch.rand(image2)
    image3 = torch.rand(image3)
    image = [image1, image2, image3]
    channel = (64, 64, 64)
    # Model
    mobilenet_v1 = DynamicDCNv3Head(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, [256, 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, [256, False]] # 19 (P4/16-medium)
 
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [256, True]] # 22 (P5/32-large)
 
  - [[16, 19, 22], 1, DynamicDCNv3Head, [nc]] # Detect(P3, P4, P5)