开始讲解之前推荐一下我的专栏本专栏的内容支持(分类、检测、分割、追踪、关键点检测),专栏目前为限时折扣欢迎大家订阅本专栏本专栏每周更新3-5篇最新机制更有包含我所有改进的文件和交流群提供给大家。一、本文介绍本文给大家带来的最新改进机制是二次创新的机制二次创新是我们发表论文中关键的一环为什么这么说从去年的三月份开始对于图像领域的论文发表其实是变难的了在那之前大家可能搭搭积木的情况下就可以简单的发表一篇论文但是从去年开始单纯的搭积木其实发表论文变得越来越难所以这个时候就需要二次创新以此来迷惑审稿人彰显大家的工作量所以二次创新是非常重要的一点因为二次创新出来的模块其实基本上就可以算作一个全新的模块了本文内容经过YOLOv26专栏很多读者反应效果很好同时本文含如何二次创新的思路。欢迎大家订阅我的专栏一起学习YOLO专栏链接YOLOv26有效涨点专栏包含Conv、注意力机制、主干/Backbone、损失函数、优化器、后处理等改进机制目录一、本文介绍二、如何进行二次创新三、iEMA的核心代码四、添加教程4.1 修改一4.2 修改二4.3 修改三4.4 修改四4.5 修改五4.6 修改六五、正式训练5.1 yaml文件5.1.1 yaml文件15.1.2 yaml文件25.2 训练代码5.3 训练过程截图五、本文总结二、如何进行二次创新这里给大家介绍以下如何进行二次创新。我的视频中说过二次创新主要分为两种本文介绍的是另外一种。组合为一种全新的结构 其他模块(可以是卷积也可以是注意力机制也可以是重参数化模块)iRMB主要提出了一种倒置残差的结构然后其中涉及到一种Transformer注意力机制因为创新注意力机制是十分困难的事情大家都是炼丹师所以这肯定不现实但是借鉴其中的结构还是一个比较容易的事情所以我们借鉴了iRMB其中倒置残差结构结合一种即插即用的EMA注意力机制(也可以替换其它的注意力机制)形成一个新的模块iEMA也是一种创新对于写论文来说总比你单用iRMB或者EMA要好对吧最起码工作量的方面我们是堆叠上去了。三、iEMA的核心代码使用方式看章节四import math import torch import torch.nn as nn from functools import partial from einops import rearrange from timm.models._efficientnet_blocks import SqueezeExcite from timm.models.layers import DropPath __all__ [iEMA, C2PSAiEMA] class EMA(nn.Module): def __init__(self, channels, factor32): super(EMA, self).__init__() self.groups factor assert channels // self.groups 0 self.softmax nn.Softmax(-1) self.agp nn.AdaptiveAvgPool2d((1, 1)) self.pool_h nn.AdaptiveAvgPool2d((None, 1)) self.pool_w nn.AdaptiveAvgPool2d((1, None)) self.gn nn.GroupNorm(channels // self.groups, channels // self.groups) self.conv1x1 nn.Conv2d(channels // self.groups, channels // self.groups, kernel_size1, stride1, padding0) self.conv3x3 nn.Conv2d(channels // self.groups, channels // self.groups, kernel_size3, stride1, padding1) def forward(self, x): b, c, h, w x.size() group_x x.reshape(b * self.groups, -1, h, w) # b*g,c//g,h,w x_h self.pool_h(group_x) x_w self.pool_w(group_x).permute(0, 1, 3, 2) hw self.conv1x1(torch.cat([x_h, x_w], dim2)) x_h, x_w torch.split(hw, [h, w], dim2) x1 self.gn(group_x * x_h.sigmoid() * x_w.permute(0, 1, 3, 2).sigmoid()) x2 self.conv3x3(group_x) x11 self.softmax(self.agp(x1).reshape(b * self.groups, -1, 1).permute(0, 2, 1)) x12 x2.reshape(b * self.groups, c // self.groups, -1) # b*g, c//g, hw x21 self.softmax(self.agp(x2).reshape(b * self.groups, -1, 1).permute(0, 2, 1)) x22 x1.reshape(b * self.groups, c // self.groups, -1) # b*g, c//g, hw weights (torch.matmul(x11, x12) torch.matmul(x21, x22)).reshape(b * self.groups, 1, h, w) return (group_x * weights.sigmoid()).reshape(b, c, h, w) inplace True class LayerNorm2d(nn.Module): def __init__(self, normalized_shape, eps1e-6, elementwise_affineTrue): super().__init__() self.norm nn.LayerNorm(normalized_shape, eps, elementwise_affine) def forward(self, x): x rearrange(x, b c h w - b h w c).contiguous() x self.norm(x) x rearrange(x, b h w c - b c h w).contiguous() return x def get_norm(norm_layerin_1d): eps 1e-6 norm_dict { none: nn.Identity, in_1d: partial(nn.InstanceNorm1d, epseps), in_2d: partial(nn.InstanceNorm2d, epseps), in_3d: partial(nn.InstanceNorm3d, epseps), bn_1d: partial(nn.BatchNorm1d, epseps), bn_2d: partial(nn.BatchNorm2d, epseps), # bn_2d: partial(nn.SyncBatchNorm, epseps), bn_3d: partial(nn.BatchNorm3d, epseps), gn: partial(nn.GroupNorm, epseps), ln_1d: partial(nn.LayerNorm, epseps), ln_2d: partial(LayerNorm2d, epseps), } return norm_dict[norm_layer] def get_act(act_layerrelu): act_dict { none: nn.Identity, relu: nn.ReLU, relu6: nn.ReLU6, silu: nn.SiLU } return act_dict[act_layer] class ConvNormAct(nn.Module): def __init__(self, dim_in, dim_out, kernel_size, stride1, dilation1, groups1, biasFalse, skipFalse, norm_layerbn_2d, act_layerrelu, inplaceTrue, drop_path_rate0.): super(ConvNormAct, self).__init__() self.has_skip skip and dim_in dim_out padding math.ceil((kernel_size - stride) / 2) self.conv nn.Conv2d(dim_in, dim_out, kernel_size, stride, padding, dilation, groups, bias) self.norm get_norm(norm_layer)(dim_out) self.act get_act(act_layer)(inplaceinplace) self.drop_path DropPath(drop_path_rate) if drop_path_rate else nn.Identity() def forward(self, x): shortcut x x self.conv(x) x self.norm(x) x self.act(x) if self.has_skip: x self.drop_path(x) shortcut return x class iEMA(nn.Module): def __init__(self, dim_in, norm_inTrue, has_skipTrue, exp_ratio1.0, norm_layerbn_2d, act_layerrelu, v_projTrue, dw_ks3, stride1, dilation1, se_ratio0.0, attn_sTrue, qkv_biasFalse, drop0., drop_path0.): super().__init__() dim_out dim_in self.norm get_norm(norm_layer)(dim_in) if norm_in else nn.Identity() dim_mid int(dim_in * exp_ratio) self.has_skip (dim_in dim_out and stride 1) and has_skip self.attn_s attn_s if self.attn_s: self.ema EMA(dim_in) else: if v_proj: self.v ConvNormAct(dim_in, dim_mid, kernel_size1, biasqkv_bias, norm_layernone, act_layeract_layer, inplaceinplace) else: self.v nn.Identity() self.conv_local ConvNormAct(dim_mid, dim_mid, kernel_sizedw_ks, stridestride, dilationdilation, groupsdim_mid, norm_layerbn_2d, act_layersilu, inplaceinplace) self.se SqueezeExcite(dim_mid, rd_ratiose_ratio, act_layerget_act(act_layer)) if se_ratio 0.0 else nn.Identity() self.proj_drop nn.Dropout(drop) self.proj ConvNormAct(dim_mid, dim_out, kernel_size1, norm_layernone, act_layernone, inplaceinplace) self.drop_path DropPath(drop_path) if drop_path else nn.Identity() def forward(self, x): shortcut x x self.norm(x) if self.attn_s: x self.ema(x) else: x self.v(x) x x self.se(self.conv_local(x)) if self.has_skip else self.se(self.conv_local(x)) x self.proj_drop(x) x self.proj(x) x (shortcut self.drop_path(x)) if self.has_skip else x return x def autopad(k, pNone, d1): # 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, k1, s1, pNone, g1, d1, actTrue): Initialize Conv layer with given arguments including activation. super().__init__() self.conv nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groupsg, dilationd, biasFalse) 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 def __init__(self, c, attn_ratio0.5, num_heads4, shortcutTrue) - None: Initializes the PSABlock with attention and feed-forward layers for enhanced feature extraction. super().__init__() self.attn iEMA(c) self.ffn nn.Sequential(Conv(c, c * 2, 1), Conv(c * 2, c, 1, actFalse)) 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 C2PSAiEMA(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: def __init__(self, c1, c2, n1, e0.5): 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_ratio0.5, num_headsself.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), dim1) b self.m(b) return self.cv2(torch.cat((a, b), 1)) if __name__ __main__: # Generating Sample image image_size (1, 64, 640, 640) image torch.rand(*image_size) # Model model C2PSAiEMA(64, 64) out model(image) print(out.size())四、添加教程下面的步骤如果你不会或者不想麻烦操作可以联系作者获得本专栏添加所有项目文件的源代码可直接训练.4.1 修改一第一还是建立文件我们找到如下ultralytics/nn文件夹下建立一个目录名字呢就是Addmodules文件夹4.2 修改二然后在Addmodules文件夹内建立一个新的py文件将本文章节三中的“核心代码复制粘贴进去。4.3 修改三第二步我们在该目录下创建一个新的py文件名字为__init__.py然后在其内部导入我们的文件如下图所示。4.4 修改四第三步我门中到如下文件ultralytics/nn/tasks.py进行导入和注册我们的模块(此处只需要添加一次即可如果你用我其它的改进机制这里的步骤只需要添加一次)4.5 修改五在ultralytics/nn/tasks.py文件内的parse_model方法函数内位置大概在1500行左右按照图示位置添加即可此处需要自己有一定的判别能力如果不会可联系作者获得视频教程。4.6 修改六在ultralytics/nn/tasks.py文件内的parse_model方法函数内位置大概在1550行左右按照图示位置添加即可此处一定要对应好位置和缩进否则很容易报错。elif m in {此处填写本章代码的名字.}: c2 ch[f] args [c2, *args]五、正式训练5.1 yaml文件5.1.1 yaml文件1训练信息YOLO26-C2PSA-iEMA summary: 271 layers, 2,473,036 parameters, 2,473,036 gradients, 5.8 GFLOPs# 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. modelyolo26n.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, C2PSAiEMA, [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)5.1.2 yaml文件2训练信息YOLO26-Att-iEMA summary: 279 layers, 2,511,116 parameters, 2,511,116 gradients, 5.9 GFLOPs# 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. modelyolo26n.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, iEMA, []] # 23 # - [19, 1, iEMA, []] # 24 # - [22, 1, iEMA, []] # 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)5.2 训练代码大家可以创建一个py文件将我给的代码复制粘贴进去配置好自己的文件路径即可运行。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( datar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 cacheFalse, imgsz640, epochs20, single_clsFalse, # 是否是单类别检测 batch16, close_mosaic0, workers0, device0, optimizerMuSGD, # using SGD/MuSGD # resume, # 这里是填写last.pt地址 ampTrue, # 如果出现训练损失为Nan可以关闭amp projectruns/train, nameexp, )5.3 训练过程截图五、本文总结到此本文的正式分享内容就结束了在这里给大家推荐我的YOLOv26改进有效涨点专栏本专栏目前为新开的平均质量分98分后期我会根据各种最新的前沿顶会进行论文复现也会对一些老的改进机制进行补充如果大家觉得本文帮助到你了订阅本专栏关注后续更多的更新~专栏链接YOLOv26有效涨点专栏包含Conv、注意力机制、主干/Backbone、损失函数、优化器、后处理等改进机制
yolov26改进 | 独家创新篇 | 结合iRMB和EMA形成全新的iEMA机制（全网独家创新，教你如何二次创新）
开始讲解之前推荐一下我的专栏本专栏的内容支持(分类、检测、分割、追踪、关键点检测),专栏目前为限时折扣欢迎大家订阅本专栏本专栏每周更新3-5篇最新机制更有包含我所有改进的文件和交流群提供给大家。一、本文介绍本文给大家带来的最新改进机制是二次创新的机制二次创新是我们发表论文中关键的一环为什么这么说从去年的三月份开始对于图像领域的论文发表其实是变难的了在那之前大家可能搭搭积木的情况下就可以简单的发表一篇论文但是从去年开始单纯的搭积木其实发表论文变得越来越难所以这个时候就需要二次创新以此来迷惑审稿人彰显大家的工作量所以二次创新是非常重要的一点因为二次创新出来的模块其实基本上就可以算作一个全新的模块了本文内容经过YOLOv26专栏很多读者反应效果很好同时本文含如何二次创新的思路。欢迎大家订阅我的专栏一起学习YOLO专栏链接YOLOv26有效涨点专栏包含Conv、注意力机制、主干/Backbone、损失函数、优化器、后处理等改进机制目录一、本文介绍二、如何进行二次创新三、iEMA的核心代码四、添加教程4.1 修改一4.2 修改二4.3 修改三4.4 修改四4.5 修改五4.6 修改六五、正式训练5.1 yaml文件5.1.1 yaml文件15.1.2 yaml文件25.2 训练代码5.3 训练过程截图五、本文总结二、如何进行二次创新这里给大家介绍以下如何进行二次创新。我的视频中说过二次创新主要分为两种本文介绍的是另外一种。组合为一种全新的结构 其他模块(可以是卷积也可以是注意力机制也可以是重参数化模块)iRMB主要提出了一种倒置残差的结构然后其中涉及到一种Transformer注意力机制因为创新注意力机制是十分困难的事情大家都是炼丹师所以这肯定不现实但是借鉴其中的结构还是一个比较容易的事情所以我们借鉴了iRMB其中倒置残差结构结合一种即插即用的EMA注意力机制(也可以替换其它的注意力机制)形成一个新的模块iEMA也是一种创新对于写论文来说总比你单用iRMB或者EMA要好对吧最起码工作量的方面我们是堆叠上去了。三、iEMA的核心代码使用方式看章节四import math import torch import torch.nn as nn from functools import partial from einops import rearrange from timm.models._efficientnet_blocks import SqueezeExcite from timm.models.layers import DropPath __all__ [iEMA, C2PSAiEMA] class EMA(nn.Module): def __init__(self, channels, factor32): super(EMA, self).__init__() self.groups factor assert channels // self.groups 0 self.softmax nn.Softmax(-1) self.agp nn.AdaptiveAvgPool2d((1, 1)) self.pool_h nn.AdaptiveAvgPool2d((None, 1)) self.pool_w nn.AdaptiveAvgPool2d((1, None)) self.gn nn.GroupNorm(channels // self.groups, channels // self.groups) self.conv1x1 nn.Conv2d(channels // self.groups, channels // self.groups, kernel_size1, stride1, padding0) self.conv3x3 nn.Conv2d(channels // self.groups, channels // self.groups, kernel_size3, stride1, padding1) def forward(self, x): b, c, h, w x.size() group_x x.reshape(b * self.groups, -1, h, w) # b*g,c//g,h,w x_h self.pool_h(group_x) x_w self.pool_w(group_x).permute(0, 1, 3, 2) hw self.conv1x1(torch.cat([x_h, x_w], dim2)) x_h, x_w torch.split(hw, [h, w], dim2) x1 self.gn(group_x * x_h.sigmoid() * x_w.permute(0, 1, 3, 2).sigmoid()) x2 self.conv3x3(group_x) x11 self.softmax(self.agp(x1).reshape(b * self.groups, -1, 1).permute(0, 2, 1)) x12 x2.reshape(b * self.groups, c // self.groups, -1) # b*g, c//g, hw x21 self.softmax(self.agp(x2).reshape(b * self.groups, -1, 1).permute(0, 2, 1)) x22 x1.reshape(b * self.groups, c // self.groups, -1) # b*g, c//g, hw weights (torch.matmul(x11, x12) torch.matmul(x21, x22)).reshape(b * self.groups, 1, h, w) return (group_x * weights.sigmoid()).reshape(b, c, h, w) inplace True class LayerNorm2d(nn.Module): def __init__(self, normalized_shape, eps1e-6, elementwise_affineTrue): super().__init__() self.norm nn.LayerNorm(normalized_shape, eps, elementwise_affine) def forward(self, x): x rearrange(x, b c h w - b h w c).contiguous() x self.norm(x) x rearrange(x, b h w c - b c h w).contiguous() return x def get_norm(norm_layerin_1d): eps 1e-6 norm_dict { none: nn.Identity, in_1d: partial(nn.InstanceNorm1d, epseps), in_2d: partial(nn.InstanceNorm2d, epseps), in_3d: partial(nn.InstanceNorm3d, epseps), bn_1d: partial(nn.BatchNorm1d, epseps), bn_2d: partial(nn.BatchNorm2d, epseps), # bn_2d: partial(nn.SyncBatchNorm, epseps), bn_3d: partial(nn.BatchNorm3d, epseps), gn: partial(nn.GroupNorm, epseps), ln_1d: partial(nn.LayerNorm, epseps), ln_2d: partial(LayerNorm2d, epseps), } return norm_dict[norm_layer] def get_act(act_layerrelu): act_dict { none: nn.Identity, relu: nn.ReLU, relu6: nn.ReLU6, silu: nn.SiLU } return act_dict[act_layer] class ConvNormAct(nn.Module): def __init__(self, dim_in, dim_out, kernel_size, stride1, dilation1, groups1, biasFalse, skipFalse, norm_layerbn_2d, act_layerrelu, inplaceTrue, drop_path_rate0.): super(ConvNormAct, self).__init__() self.has_skip skip and dim_in dim_out padding math.ceil((kernel_size - stride) / 2) self.conv nn.Conv2d(dim_in, dim_out, kernel_size, stride, padding, dilation, groups, bias) self.norm get_norm(norm_layer)(dim_out) self.act get_act(act_layer)(inplaceinplace) self.drop_path DropPath(drop_path_rate) if drop_path_rate else nn.Identity() def forward(self, x): shortcut x x self.conv(x) x self.norm(x) x self.act(x) if self.has_skip: x self.drop_path(x) shortcut return x class iEMA(nn.Module): def __init__(self, dim_in, norm_inTrue, has_skipTrue, exp_ratio1.0, norm_layerbn_2d, act_layerrelu, v_projTrue, dw_ks3, stride1, dilation1, se_ratio0.0, attn_sTrue, qkv_biasFalse, drop0., drop_path0.): super().__init__() dim_out dim_in self.norm get_norm(norm_layer)(dim_in) if norm_in else nn.Identity() dim_mid int(dim_in * exp_ratio) self.has_skip (dim_in dim_out and stride 1) and has_skip self.attn_s attn_s if self.attn_s: self.ema EMA(dim_in) else: if v_proj: self.v ConvNormAct(dim_in, dim_mid, kernel_size1, biasqkv_bias, norm_layernone, act_layeract_layer, inplaceinplace) else: self.v nn.Identity() self.conv_local ConvNormAct(dim_mid, dim_mid, kernel_sizedw_ks, stridestride, dilationdilation, groupsdim_mid, norm_layerbn_2d, act_layersilu, inplaceinplace) self.se SqueezeExcite(dim_mid, rd_ratiose_ratio, act_layerget_act(act_layer)) if se_ratio 0.0 else nn.Identity() self.proj_drop nn.Dropout(drop) self.proj ConvNormAct(dim_mid, dim_out, kernel_size1, norm_layernone, act_layernone, inplaceinplace) self.drop_path DropPath(drop_path) if drop_path else nn.Identity() def forward(self, x): shortcut x x self.norm(x) if self.attn_s: x self.ema(x) else: x self.v(x) x x self.se(self.conv_local(x)) if self.has_skip else self.se(self.conv_local(x)) x self.proj_drop(x) x self.proj(x) x (shortcut self.drop_path(x)) if self.has_skip else x return x def autopad(k, pNone, d1): # 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, k1, s1, pNone, g1, d1, actTrue): Initialize Conv layer with given arguments including activation. super().__init__() self.conv nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groupsg, dilationd, biasFalse) 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 def __init__(self, c, attn_ratio0.5, num_heads4, shortcutTrue) - None: Initializes the PSABlock with attention and feed-forward layers for enhanced feature extraction. super().__init__() self.attn iEMA(c) self.ffn nn.Sequential(Conv(c, c * 2, 1), Conv(c * 2, c, 1, actFalse)) 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 C2PSAiEMA(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: def __init__(self, c1, c2, n1, e0.5): 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_ratio0.5, num_headsself.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), dim1) b self.m(b) return self.cv2(torch.cat((a, b), 1)) if __name__ __main__: # Generating Sample image image_size (1, 64, 640, 640) image torch.rand(*image_size) # Model model C2PSAiEMA(64, 64) out model(image) print(out.size())四、添加教程下面的步骤如果你不会或者不想麻烦操作可以联系作者获得本专栏添加所有项目文件的源代码可直接训练.4.1 修改一第一还是建立文件我们找到如下ultralytics/nn文件夹下建立一个目录名字呢就是Addmodules文件夹4.2 修改二然后在Addmodules文件夹内建立一个新的py文件将本文章节三中的“核心代码复制粘贴进去。4.3 修改三第二步我们在该目录下创建一个新的py文件名字为__init__.py然后在其内部导入我们的文件如下图所示。4.4 修改四第三步我门中到如下文件ultralytics/nn/tasks.py进行导入和注册我们的模块(此处只需要添加一次即可如果你用我其它的改进机制这里的步骤只需要添加一次)4.5 修改五在ultralytics/nn/tasks.py文件内的parse_model方法函数内位置大概在1500行左右按照图示位置添加即可此处需要自己有一定的判别能力如果不会可联系作者获得视频教程。4.6 修改六在ultralytics/nn/tasks.py文件内的parse_model方法函数内位置大概在1550行左右按照图示位置添加即可此处一定要对应好位置和缩进否则很容易报错。elif m in {此处填写本章代码的名字.}: c2 ch[f] args [c2, *args]五、正式训练5.1 yaml文件5.1.1 yaml文件1训练信息YOLO26-C2PSA-iEMA summary: 271 layers, 2,473,036 parameters, 2,473,036 gradients, 5.8 GFLOPs# 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. modelyolo26n.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, C2PSAiEMA, [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)5.1.2 yaml文件2训练信息YOLO26-Att-iEMA summary: 279 layers, 2,511,116 parameters, 2,511,116 gradients, 5.9 GFLOPs# 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. modelyolo26n.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, iEMA, []] # 23 # - [19, 1, iEMA, []] # 24 # - [22, 1, iEMA, []] # 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)5.2 训练代码大家可以创建一个py文件将我给的代码复制粘贴进去配置好自己的文件路径即可运行。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( datar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 cacheFalse, imgsz640, epochs20, single_clsFalse, # 是否是单类别检测 batch16, close_mosaic0, workers0, device0, optimizerMuSGD, # using SGD/MuSGD # resume, # 这里是填写last.pt地址 ampTrue, # 如果出现训练损失为Nan可以关闭amp projectruns/train, nameexp, )5.3 训练过程截图五、本文总结到此本文的正式分享内容就结束了在这里给大家推荐我的YOLOv26改进有效涨点专栏本专栏目前为新开的平均质量分98分后期我会根据各种最新的前沿顶会进行论文复现也会对一些老的改进机制进行补充如果大家觉得本文帮助到你了订阅本专栏关注后续更多的更新~专栏链接YOLOv26有效涨点专栏包含Conv、注意力机制、主干/Backbone、损失函数、优化器、后处理等改进机制
