yolov26改进 | 添加注意力机制篇 | 利用SENetV2改进网络结构 (全网独家改进，含二次创新C2PSA、SPPF)

​

​

import torch import torch.nn as nn __all__ = ['C2PSA_SENetV2', 'SELayerV2', 'SPPFSENetV2'] # 定义SE模块 class SELayer(nn.Module): def __init__(self, channel, reduction=16): super(SELayer, self).__init__() self.avg_pool = nn.AdaptiveAvgPool2d(1) self.fc = nn.Sequential( nn.Linear(channel, channel // reduction, bias=False), nn.ReLU(inplace=True), nn.Linear(channel // reduction, channel, bias=False), nn.Sigmoid() ) def forward(self, x): b, c, _, _ = x.size() y = self.avg_pool(x).view(b, c) y = self.fc(y).view(b, c, 1, 1) return x * y.expand_as(x) # 定义SaE模块 class SELayerV2(nn.Module): def __init__(self, in_channel, reduction=16): super(SELayerV2, self).__init__() assert in_channel >= reduction and in_channel % reduction == 0, 'invalid in_channel in SaElayer' self.reduction = reduction self.cardinality = 4 self.avg_pool = nn.AdaptiveAvgPool2d(1) # cardinality 1 self.fc1 = nn.Sequential( nn.Linear(in_channel, in_channel // self.reduction, bias=False), nn.ReLU(inplace=True) ) # cardinality 2 self.fc2 = nn.Sequential( nn.Linear(in_channel, in_channel // self.reduction, bias=False), nn.ReLU(inplace=True) ) # cardinality 3 self.fc3 = nn.Sequential( nn.Linear(in_channel, in_channel // self.reduction, bias=False), nn.ReLU(inplace=True) ) # cardinality 4 self.fc4 = nn.Sequential( nn.Linear(in_channel, in_channel // self.reduction, bias=False), nn.ReLU(inplace=True) ) self.fc = nn.Sequential( nn.Linear(in_channel // self.reduction * self.cardinality, in_channel, bias=False), nn.Sigmoid() ) def forward(self, x): b, c, _, _ = x.size() y = self.avg_pool(x).view(b, c) y1 = self.fc1(y) y2 = self.fc2(y) y3 = self.fc3(y) y4 = self.fc4(y) y_concate = torch.cat([y1, y2, y3, y4], dim=1) y_ex_dim = self.fc(y_concate).view(b, c, 1, 1) return x * y_ex_dim.expand_as(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 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 = SELayerV2(c) 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_SENetV2(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 SPPFSENetV2(nn.Module): """Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher.""" def __init__(self, c1: int, c2: int, k: int = 5, n: int = 3, shortcut: bool = False): """Initialize the SPPF layer with given input/output channels and kernel size. Args: c1 (int): Input channels. c2 (int): Output channels. k (int): Kernel size. n (int): Number of pooling iterations. shortcut (bool): Whether to use shortcut connection. Notes: This module is equivalent to SPP(k=(5, 9, 13)). """ super().__init__() c_ = c1 // 2 # hidden channels self.cv1 = Conv(c1, c_, 1, 1, act=False) self.cv2 = Conv(c_ * (n + 1), c2, 1, 1) self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2) self.n = n self.add = shortcut and c1 == c2 self.Att = SELayerV2(c1) def forward(self, x: torch.Tensor) -> torch.Tensor: """Apply sequential pooling operations to input and return concatenated feature maps.""" x = self.Att(x) y = [self.cv1(x)] y.extend(self.m(y[-1]) for _ in range(getattr(self, "n", 3))) y = self.cv2(torch.cat(y, 1)) return y + x if getattr(self, "add", False) else y if __name__ == "__main__": # Generating Sample image image_size = (1, 64, 240, 240) image = torch.rand(*image_size) # Model mobilenet_v1 = SPPFSENetV2(64, 64) out = mobilenet_v1(image) print(out.size())

elif m in {此处填写本章代码的名字.}: c2 = ch[f] args = [c2, *args]

# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license # Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs # Model docs: https://docs.ultralytics.com/models/yolo26 # Task docs: https://docs.ultralytics.com/tasks/detect # Parameters nc: 80 # number of classes end2end: True # whether to use end-to-end mode reg_max: 1 # DFL bins scales: # model compound scaling constants, i.e. 'model=yolo26n.yaml' will call yolo26.yaml with scale 'n' # [depth, width, max_channels] n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs # YOLO26n 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, 3, True]] # 9 - [-1, 2, C2PSA_SENetV2, [1024]] # 10 # YOLO26n head head: - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - [-1, 2, C3k2, [512, True]] # 13 - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - [-1, 2, C3k2, [256, True]] # 16 (P3/8-small) - [-1, 1, Conv, [256, 3, 2]] - [[-1, 13], 1, Concat, [1]] # cat head P4 - [-1, 2, C3k2, [512, True]] # 19 (P4/16-medium) - [-1, 1, Conv, [512, 3, 2]] - [[-1, 10], 1, Concat, [1]] # cat head P5 - [-1, 1, C3k2, [1024, True, 0.5, True]] # 22 (P5/32-large) - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license # Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs # Model docs: https://docs.ultralytics.com/models/yolo26 # Task docs: https://docs.ultralytics.com/tasks/detect # Parameters nc: 80 # number of classes end2end: True # whether to use end-to-end mode reg_max: 1 # DFL bins scales: # model compound scaling constants, i.e. 'model=yolo26n.yaml' will call yolo26.yaml with scale 'n' # [depth, width, max_channels] n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs # YOLO26n 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, 3, True]] # 9 - [-1, 2, C2PSA, [1024]] # 10 # YOLO26n head head: - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - [-1, 2, C3k2, [512, True]] # 13 - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - [-1, 2, C3k2, [256, True]] # 16 (P3/8-small) - [-1, 1, Conv, [256, 3, 2]] - [[-1, 13], 1, Concat, [1]] # cat head P4 - [-1, 2, C3k2, [512, True]] # 19 (P4/16-medium) - [-1, 1, Conv, [512, 3, 2]] - [[-1, 10], 1, Concat, [1]] # cat head P5 - [-1, 1, C3k2, [1024, True, 0.5, True]] # 22 (P5/32-large) - [16, 1, SELayerV2, []] # 23 # - [19, 1, SELayerV2, []] # 24 # - [22, 1, SELayerV2, []] # 25 # 此处的使用说法注释: 其中上面的三个注意力机制目前仅使用了23层，如果你想使用24层那么就取消掉代码注释， # 并将下面检测头中的19改为24,如果想使用第25层注意力机制同理，将下面检测头中的22改为25即可。 # 此处用法比较复杂如过不会联系Snu77博主获取视频教程 - [[23, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license # Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs # Model docs: https://docs.ultralytics.com/models/yolo26 # Task docs: https://docs.ultralytics.com/tasks/detect # Parameters nc: 80 # number of classes end2end: True # whether to use end-to-end mode reg_max: 1 # DFL bins scales: # model compound scaling constants, i.e. 'model=yolo26n.yaml' will call yolo26.yaml with scale 'n' # [depth, width, max_channels] n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs # YOLO26n 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, SPPFSENetV2, [1024, 5, 3, True]] # 9 - [-1, 2, C2PSA, [1024]] # 10 # YOLO26n head head: - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - [-1, 2, C3k2, [512, True]] # 13 - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - [-1, 2, C3k2, [256, True]] # 16 (P3/8-small) - [-1, 1, Conv, [256, 3, 2]] - [[-1, 13], 1, Concat, [1]] # cat head P4 - [-1, 2, C3k2, [512, True]] # 19 (P4/16-medium) - [-1, 1, Conv, [512, 3, 2]] - [[-1, 10], 1, Concat, [1]] # cat head P5 - [-1, 1, C3k2, [1024, True, 0.5, 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('模型配置文件地址,也就是5.1你保存到本地文件的地址') # 如何切换模型版本, 上面的ymal文件可以改为 yolo26s.yaml就是使用的26s, # 类似某个改进的yaml文件名称为yolo26-XXX.yaml那么如果想使用其它版本就把上面的名称改为yolo26l-XXX.yaml即可（改的是上面YOLO中间的名字不是配置文件的）！ # model.load('yolo26n.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"数据集文件地址", # 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=20, single_cls=False, # 是否是单类别检测 batch=16, close_mosaic=0, workers=0, device='0', optimizer='MuSGD', # using SGD/MuSGD # resume=, # 这里是填写last.pt地址 amp=True, # 如果出现训练损失为Nan可以关闭amp project='runs/train', name='exp', )