class C3k2(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(self.c, self.c, shortcut, g) for _ in range(n)
        )
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 PSABlock(nn.Module):
    """
    PSABlock class implementing a Position-Sensitive Attention block for neural networks.
    This class encapsulates the functionality for applying multi-head attention and feed-forward neural network layers
    with optional shortcut connections.
    Attributes:
        attn (Attention): Multi-head attention module.
        ffn (nn.Sequential): Feed-forward neural network module.
        add (bool): Flag indicating whether to add shortcut connections.
    Methods:
        forward: Performs a forward pass through the PSABlock, applying attention and feed-forward layers.
    Examples:
        Create a PSABlock and perform a forward pass
        >>> psablock = PSABlock(c=128, attn_ratio=0.5, num_heads=4, shortcut=True)
        >>> input_tensor = torch.randn(1, 128, 32, 32)
        >>> output_tensor = psablock(input_tensor)
    """
    def __init__(self, c, attn_ratio=0.5, num_heads=4, shortcut=True) -> None:
        """Initializes the PSABlock with attention and feed-forward layers for enhanced feature extraction."""
        super().__init__()
        self.attn = Attention(c, attn_ratio=attn_ratio, num_heads=num_heads)
        self.ffn = nn.Sequential(Conv(c, c * 2, 1), Conv(c * 2, c, 1, act=False))
        self.add = shortcut
    def forward(self, x):
        """Executes a forward pass through PSABlock, applying attention and feed-forward layers to the input tensor."""
        x = x + self.attn(x) if self.add else self.attn(x)
        x = x + self.ffn(x) if self.add else self.ffn(x)
        return x
class C2PSA(nn.Module):
    """
    C2PSA module with attention mechanism for enhanced feature extraction and processing.
    This module implements a convolutional block with attention mechanisms to enhance feature extraction and processing
    capabilities. It includes a series of PSABlock modules for self-attention and feed-forward operations.
    Attributes:
        c (int): Number of hidden channels.
        cv1 (Conv): 1x1 convolution layer to reduce the number of input channels to 2*c.
        cv2 (Conv): 1x1 convolution layer to reduce the number of output channels to c.
        m (nn.Sequential): Sequential container of PSABlock modules for attention and feed-forward operations.
    Methods:
        forward: Performs a forward pass through the C2PSA module, applying attention and feed-forward operations.
    Notes:
        This module essentially is the same as PSA module, but refactored to allow stacking more PSABlock modules.
    Examples:
        >>> c2psa = C2PSA(c1=256, c2=256, n=3, e=0.5)
        >>> input_tensor = torch.randn(1, 256, 64, 64)
        >>> output_tensor = c2psa(input_tensor)
    """
    def __init__(self, c1, c2, n=1, e=0.5):
        """Initializes the C2PSA module with specified input/output channels, number of layers, and expansion ratio."""
        super().__init__()
        assert c1 == c2
        self.c = int(c1 * e)
        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
        self.cv2 = Conv(2 * self.c, c1, 1)
        self.m = nn.Sequential(*(PSABlock(self.c, attn_ratio=0.5, num_heads=self.c // 64) for _ in range(n)))
    def forward(self, x):
        """Processes the input tensor 'x' through a series of PSA blocks and returns the transformed tensor."""
        a, b = self.cv1(x).split((self.c, self.c), dim=1)
        b = self.m(b)
        return self.cv2(torch.cat((a, b), 1))
class C2fPSA(C2f):
    """
    C2fPSA module with enhanced feature extraction using PSA blocks.
    This class extends the C2f module by incorporating PSA blocks for improved attention mechanisms and feature extraction.
    Attributes:
        c (int): Number of hidden channels.
        cv1 (Conv): 1x1 convolution layer to reduce the number of input channels to 2*c.
        cv2 (Conv): 1x1 convolution layer to reduce the number of output channels to c.
        m (nn.ModuleList): List of PSA blocks for feature extraction.
    Methods:
        forward: Performs a forward pass through the C2fPSA module.
        forward_split: Performs a forward pass using split() instead of chunk().
    Examples:
        >>> import torch
        >>> from ultralytics.models.common import C2fPSA
        >>> model = C2fPSA(c1=64, c2=64, n=3, e=0.5)
        >>> x = torch.randn(1, 64, 128, 128)
        >>> output = model(x)
        >>> print(output.shape)
    """
    def __init__(self, c1, c2, n=1, e=0.5):
        """Initializes the C2fPSA module, a variant of C2f with PSA blocks for enhanced feature extraction."""
        assert c1 == c2
        super().__init__(c1, c2, n=n, e=e)
        self.m = nn.ModuleList(PSABlock(self.c, attn_ratio=0.5, num_heads=self.c // 64) for _ in range(n))

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
        )

-------------------------------   YOLO11   ----------------------------------
# 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
-------------------------------   YOLOv8   ----------------------------------
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 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=yolov8n.yaml' will call yolov8.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers,  3157200 parameters,  3157184 gradients,   8.9 GFLOPs
  s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPs
  m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPs
  l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
  x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs

import warnings
warnings.filterwarnings('ignore')
from ultralytics import YOLO
if __name__ == '__main__':
    model = YOLO('ultralytics/cfg/models/11/yolo11-EMA_attention.yaml')
    #model.load('yolov8n.pt') # loading pretrain weights
    model.train(data='data/NEU-DET.yaml',
                cache=False,
                imgsz=640,
                epochs=200,
                batch=8,
                close_mosaic=10,
                device='0',
                optimizer='SGD', # using SGD
                project='runs/train',
                name='exp',
                )

YOLO11n summary (fused): 238 layers, 2,583,322 parameters, 0 gradients, 6.3 GFLOPs
                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 21/21 [00:07<00:00,  2.93it/s]
                   all        324        747      0.765      0.679      0.768      0.433
               crazing         47        104      0.678      0.337      0.508       0.22
             inclusion         71        190      0.775      0.705       0.79      0.398
               patches         59        149      0.808      0.859      0.927      0.636
        pitted_surface         61         93       0.81      0.667      0.779      0.483
       rolled-in_scale         56        117      0.684      0.593       0.67      0.317
             scratches         54         94      0.833      0.915      0.934      0.544