YOLOv11改进 | Conv/卷积篇 | 利用ModulatedDeformConv二次创新C3k2(降低网络层数 + 计算量)

​

​

​

import math
from typing import Optional, Tuple, Union
import torch
import torch.nn as nn
from torch.autograd import Function
from torch.autograd.function import once_differentiable
from torch.nn.modules.utils import _pair, _single
import importlib
 
__all__ = ['C3k2_MDConv1', 'C3k2_MDConv2']
 
ext_module  = importlib.import_module('mmcv.' + "_ext")
class ModulatedDeformConv2dFunction(Function):
    @staticmethod
    def symbolic(g, input, offset, mask, weight, bias, stride, padding,
                 dilation, groups, deform_groups):
        input_tensors = [input, offset, mask, weight]
        if bias is not None:
            input_tensors.append(bias)
        return g.op(
            'mmcv::MMCVModulatedDeformConv2d',
            *input_tensors,
            stride_i=stride,
            padding_i=padding,
            dilation_i=dilation,
            groups_i=groups,
            deform_groups_i=deform_groups)
    @staticmethod
    def forward(ctx,
                input: torch.Tensor,
                offset: torch.Tensor,
                mask: torch.Tensor,
                weight: nn.Parameter,
                bias: Optional[nn.Parameter] = None,
                stride: int = 1,
                padding: int = 0,
                dilation: int = 1,
                groups: int = 1,
                deform_groups: int = 1) -> torch.Tensor:
        if input is not None and input.dim() != 4:
            raise ValueError(
                f'Expected 4D tensor as input, got {input.dim()}D tensor \
                  instead.')
        ctx.stride = _pair(stride)
        ctx.padding = _pair(padding)
        ctx.dilation = _pair(dilation)
        ctx.groups = groups
        ctx.deform_groups = deform_groups
        ctx.with_bias = bias is not None
        if not ctx.with_bias:
            bias = input.new_empty(0)  # fake tensor
        # When pytorch version >= 1.6.0, amp is adopted for fp16 mode;
        # amp won't cast the type of model (float32), but "offset" is cast
        # to float16 by nn.Conv2d automatically, leading to the type
        # mismatch with input (when it is float32) or weight.
        # The flag for whether to use fp16 or amp is the type of "offset",
        # we cast weight and input to temporarily support fp16 and amp
        # whatever the pytorch version is.
        input = input.type_as(offset)
        weight = weight.type_as(input)
        bias = bias.type_as(input)  # type: ignore
        ctx.save_for_backward(input, offset, mask, weight, bias)
        output = input.new_empty(
            ModulatedDeformConv2dFunction._output_size(ctx, input, weight))
        ctx._bufs = [input.new_empty(0), input.new_empty(0)]
        ext_module.modulated_deform_conv_forward(
            input,
            weight,
            bias,
            ctx._bufs[0],
            offset,
            mask,
            output,
            ctx._bufs[1],
            kernel_h=weight.size(2),
            kernel_w=weight.size(3),
            stride_h=ctx.stride[0],
            stride_w=ctx.stride[1],
            pad_h=ctx.padding[0],
            pad_w=ctx.padding[1],
            dilation_h=ctx.dilation[0],
            dilation_w=ctx.dilation[1],
            group=ctx.groups,
            deformable_group=ctx.deform_groups,
            with_bias=ctx.with_bias)
        return output
    @staticmethod
    @once_differentiable
    def backward(ctx, grad_output: torch.Tensor) -> tuple:
        input, offset, mask, weight, bias = ctx.saved_tensors
        grad_input = torch.zeros_like(input)
        grad_offset = torch.zeros_like(offset)
        grad_mask = torch.zeros_like(mask)
        grad_weight = torch.zeros_like(weight)
        grad_bias = torch.zeros_like(bias)
        grad_output = grad_output.contiguous()
        ext_module.modulated_deform_conv_backward(
            input,
            weight,
            bias,
            ctx._bufs[0],
            offset,
            mask,
            ctx._bufs[1],
            grad_input,
            grad_weight,
            grad_bias,
            grad_offset,
            grad_mask,
            grad_output,
            kernel_h=weight.size(2),
            kernel_w=weight.size(3),
            stride_h=ctx.stride[0],
            stride_w=ctx.stride[1],
            pad_h=ctx.padding[0],
            pad_w=ctx.padding[1],
            dilation_h=ctx.dilation[0],
            dilation_w=ctx.dilation[1],
            group=ctx.groups,
            deformable_group=ctx.deform_groups,
            with_bias=ctx.with_bias)
        if not ctx.with_bias:
            grad_bias = None
        return (grad_input, grad_offset, grad_mask, grad_weight, grad_bias,
                None, None, None, None, None)
    @staticmethod
    def _output_size(ctx, input, weight):
        channels = weight.size(0)
        output_size = (input.size(0), channels)
        for d in range(input.dim() - 2):
            in_size = input.size(d + 2)
            pad = ctx.padding[d]
            kernel = ctx.dilation[d] * (weight.size(d + 2) - 1) + 1
            stride_ = ctx.stride[d]
            output_size += ((in_size + (2 * pad) - kernel) // stride_ + 1, )
        if not all(map(lambda s: s > 0, output_size)):
            raise ValueError(
                'convolution input is too small (output would be ' +
                'x'.join(map(str, output_size)) + ')')
        return output_size
modulated_deform_conv2d = ModulatedDeformConv2dFunction.apply
class ModulatedDeformConv2d(nn.Module):
    def __init__(self,
                 in_channels: int,
                 out_channels: int,
                 kernel_size: Union[int, Tuple[int]],
                 stride: int = 1,
                 padding: int = 1,
                 dilation: int = 1,
                 groups: int = 1,
                 deform_groups: int = 1,
                 bias: Union[bool, str] = True):
        super().__init__()
        self.in_channels = in_channels
        self.out_channels = out_channels
        self.kernel_size = _pair(kernel_size)
        self.stride = _pair(stride)
        self.padding = _pair(padding)
        self.dilation = _pair(dilation)
        self.groups = groups
        self.deform_groups = deform_groups
        # enable compatibility with nn.Conv2d
        self.transposed = False
        self.output_padding = _single(0)
        self.weight = nn.Parameter(
            torch.Tensor(out_channels, in_channels // groups,
                         *self.kernel_size))
        if bias:
            self.bias = nn.Parameter(torch.Tensor(out_channels))
        else:
            self.register_parameter('bias', None)
        self.init_weights()
    def init_weights(self):
        n = self.in_channels
        for k in self.kernel_size:
            n *= k
        stdv = 1. / math.sqrt(n)
        self.weight.data.uniform_(-stdv, stdv)
        if self.bias is not None:
            self.bias.data.zero_()
    def forward(self, x: torch.Tensor, offset: torch.Tensor,
                mask: torch.Tensor) -> torch.Tensor:
        return modulated_deform_conv2d(x, offset, mask, self.weight, self.bias,
                                       self.stride, self.padding,
                                       self.dilation, self.groups,
                                       self.deform_groups)
class ModulatedDeformConv2dPack(ModulatedDeformConv2d):
    """A ModulatedDeformable Conv Encapsulation that acts as normal Conv
    layers.
    Args:
        in_channels (int): Same as nn.Conv2d.
        out_channels (int): Same as nn.Conv2d.
        kernel_size (int or tuple[int]): Same as nn.Conv2d.
        stride (int): Same as nn.Conv2d, while tuple is not supported.
        padding (int): Same as nn.Conv2d, while tuple is not supported.
        dilation (int): Same as nn.Conv2d, while tuple is not supported.
        groups (int): Same as nn.Conv2d.
        bias (bool or str): If specified as `auto`, it will be decided by the
            norm_cfg. Bias will be set as True if norm_cfg is None, otherwise
            False.
    """
    _version = 2
    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)
        self.conv_offset = nn.Conv2d(
            self.in_channels,
            self.deform_groups * 3 * self.kernel_size[0] * self.kernel_size[1],
            kernel_size=self.kernel_size,
            stride=self.stride,
            padding=self.padding,
            dilation=self.dilation,
            bias=True)
        self.init_weights()
    def init_weights(self) -> None:
        super().init_weights()
        if hasattr(self, 'conv_offset'):
            self.conv_offset.weight.data.zero_()
            self.conv_offset.bias.data.zero_()
    def forward(self, x: torch.Tensor) -> torch.Tensor:  # type: ignore
        out = self.conv_offset(x)
        o1, o2, mask = torch.chunk(out, 3, dim=1)
        offset = torch.cat((o1, o2), dim=1)
        mask = torch.sigmoid(mask)
        return modulated_deform_conv2d(x, offset, mask, self.weight, self.bias,
                                       self.stride, self.padding,
                                       self.dilation, self.groups,
                                       self.deform_groups)
    def _load_from_state_dict(self, state_dict, prefix, local_metadata, strict,
                              missing_keys, unexpected_keys, error_msgs):
        version = local_metadata.get('version', None)
        if version is None or version < 2:
            # the key is different in early versions
            # In version < 2, ModulatedDeformConvPack
            # loads previous benchmark models.
            if (prefix + 'conv_offset.weight' not in state_dict
                    and prefix[:-1] + '_offset.weight' in state_dict):
                state_dict[prefix + 'conv_offset.weight'] = state_dict.pop(
                    prefix[:-1] + '_offset.weight')
            if (prefix + 'conv_offset.bias' not in state_dict
                    and prefix[:-1] + '_offset.bias' in state_dict):
                state_dict[prefix +
                           'conv_offset.bias'] = state_dict.pop(prefix[:-1] +
                                                                '_offset.bias')
        super()._load_from_state_dict(state_dict, prefix, local_metadata,
                                      strict, missing_keys, unexpected_keys,
                                      error_msgs)
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 Bottleneck_MDConv(nn.Module):
    # Standard bottleneck with DCN
    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):  # ch_in, ch_out, shortcut, groups, kernels, expand
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, k[0], 1)
        self.cv2 = ModulatedDeformConv2dPack(c_, c2, 3)
        self.add = shortcut and c1 == c2
    def forward(self, x):
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
class Bottleneck(nn.Module):
    """Standard bottleneck."""
    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):
        """Initializes a standard bottleneck module with optional shortcut connection and configurable parameters."""
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, k[0], 1)
        self.cv2 = Conv(c_, c2, k[1], 1, g=g)
        self.add = shortcut and c1 == c2
    def forward(self, x):
        """Applies the YOLO FPN to input data."""
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
class C2f(nn.Module):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):
        """Initializes a CSP bottleneck with 2 convolutions and n Bottleneck blocks for faster processing."""
        super().__init__()
        self.c = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
        self.cv2 = Conv((2 + n) * self.c, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.ModuleList(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n))
    def forward(self, x):
        """Forward pass through C2f layer."""
        y = list(self.cv1(x).chunk(2, 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))
    def forward_split(self, x):
        """Forward pass using split() instead of chunk()."""
        y = list(self.cv1(x).split((self.c, self.c), 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))
class C3(nn.Module):
    """CSP Bottleneck with 3 convolutions."""
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        """Initialize the CSP Bottleneck with given channels, number, shortcut, groups, and expansion values."""
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(2 * c_, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, k=((1, 1), (3, 3)), e=1.0) for _ in range(n)))
    def forward(self, x):
        """Forward pass through the CSP bottleneck with 2 convolutions."""
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))
class C3k(C3):
    """C3k is a CSP bottleneck module with customizable kernel sizes for feature extraction in neural networks."""
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, k=3):
        """Initializes the C3k module with specified channels, number of layers, and configurations."""
        super().__init__(c1, c2, n, shortcut, g, e)
        c_ = int(c2 * e)  # hidden channels
        # self.m = nn.Sequential(*(RepBottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
class C3kMDConv(C3):
    """C3k is a CSP bottleneck module with customizable kernel sizes for feature extraction in neural networks."""
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, k=3):
        """Initializes the C3k module with specified channels, number of layers, and configurations."""
        super().__init__(c1, c2, n, shortcut, g, e)
        c_ = int(c2 * e)  # hidden channels
        # self.m = nn.Sequential(*(RepBottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
        self.m = nn.Sequential(*(Bottleneck_MDConv(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
class C3k2_MDConv1(C2f):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""
    def __init__(self, c1, c2, n=1, c3k=False, e=0.5, g=1, shortcut=True):
        """Initializes the C3k2 module, a faster CSP Bottleneck with 2 convolutions and optional C3k blocks."""
        super().__init__(c1, c2, n, shortcut, g, e)
        self.m = nn.ModuleList(
            C3k(self.c, self.c, 2, shortcut, g) if c3k else Bottleneck_MDConv(self.c, self.c, shortcut, g)for _ in range(n)
        )
        # 解析利用MLLABlock替换Bottneck
class C3k2_MDConv2(C2f):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""
    def __init__(self, c1, c2, n=1, c3k=False, e=0.5, g=1, shortcut=True):
        """Initializes the C3k2 module, a faster CSP Bottleneck with 2 convolutions and optional C3k blocks."""
        super().__init__(c1, c2, n, shortcut, g, e)
        self.m = nn.ModuleList(
            C3kMDConv(self.c, self.c, 2, shortcut, g) if c3k else Bottleneck(self.c, self.c, shortcut, g) for _ in
            range(n)
        )
        # 解析利用MLLABlock替换C3k中的Bottneck
if __name__ == '__main__':
    x1 = torch.randn(1, 32, 16, 16)
    x2 = torch.randn(1, 32, 16, 16)
    model = ModulatedDeformConv2dPack(32, 16, 3, 2, 1)
    x = model(x1)
    print(x.shape)

​

# 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_MDConv1, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2_MDConv1, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2_MDConv1, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2_MDConv1, [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_MDConv1, [512, False]] # 13
 
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2_MDConv1, [256, False]] # 16 (P3/8-small)
 
  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2_MDConv1, [512, False]] # 19 (P4/16-medium)
 
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2_MDConv1, [1024, True]] # 22 (P5/32-large)
 
  - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

# 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_MDConv2, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2_MDConv2, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2_MDConv2, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2_MDConv2, [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_MDConv2, [512, False]] # 13
 
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2_MDConv2, [256, False]] # 16 (P3/8-small)
 
  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2_MDConv2, [512, False]] # 19 (P4/16-medium)
 
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2_MDConv2, [1024, True]] # 22 (P5/32-large)
 
  - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

# 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, ModulatedDeformConv2dPack, [128, 3, 2]] # 1-P2/4
  - [-1, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, ModulatedDeformConv2dPack, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, ModulatedDeformConv2dPack, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, ModulatedDeformConv2dPack, [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, ModulatedDeformConv2dPack, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
 
  - [-1, 1, ModulatedDeformConv2dPack, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
 
  - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

import warnings
warnings.filterwarnings('ignore')
from ultralytics import YOLO
 
if __name__ == '__main__':
    model = YOLO('yolov8-MLLA.yaml')
    # 如何切换模型版本, 上面的ymal文件可以改为 yolov8s.yaml就是使用的v8s,
    # 类似某个改进的yaml文件名称为yolov8-XXX.yaml那么如果想使用其它版本就把上面的名称改为yolov8l-XXX.yaml即可（改的是上面YOLO中间的名字不是配置文件的）！
    # model.load('yolov8n.pt') # 是否加载预训练权重,科研不建议大家加载否则很难提升精度
    model.train(data=r"C:\Users\Administrator\PycharmProjects\yolov5-master\yolov5-master\Construction Site Safety.v30-raw-images_latestversion.yolov8\data.yaml",
                # 如果大家任务是其它的'ultralytics/cfg/default.yaml'找到这里修改task可以改成detect, segment, classify, pose
                cache=False,
                imgsz=640,
                epochs=150,
                single_cls=False,  # 是否是单类别检测
                batch=16,
                close_mosaic=0,
                workers=0,
                device='0',
                optimizer='SGD', # using SGD
                # resume='runs/train/exp21/weights/last.pt', # 如过想续训就设置last.pt的地址
                amp=True,  # 如果出现训练损失为Nan可以关闭amp
                project='runs/train',
                name='exp',
                )