秋招面试专栏推荐 :深度学习算法工程师面试问题总结【百面算法工程师】——点击即可跳转
💡💡💡本专栏所有程序均经过测试,可成功执行💡💡💡
本文给大家带来的教程是将YOLO11的backbone替换为SimRepCSP结构来提取特征。文章在介绍主要的原理后,将手把手教学如何进行模块的代码添加和修改,并将修改后的完整代码放在文章的最后,方便大家一键运行,小白也可轻松上手实践。以帮助您更好地学习深度学习目标检测YOLO系列的挑战。
专栏地址:YOLO11入门 + 改进涨点——点击即可跳转 欢迎订阅
目录
1.论文
2. SimRepCSP代码实现
2.1 将SimRepCSP添加到YOLO11中
2.2 更改init.py文件
2.3 添加yaml文件
2.4 在task.py中进行注册
2.5 执行程序
3. 完整代码分享
4. GFLOPs
6. 进阶
7.总结
1.论文
官方论文:Modified YOLO Model for Small Platform Application using SimRepCSP Module with Case Study——点击即可跳转
2. SimRepCSP代码实现
2.1 将SimRepCSP添加到YOLO11中
关键步骤一:将下面代码粘贴到在/ultralytics/ultralytics/nn/modules/block.py中
class RepConv(nn.Module):# Represented convolution# https://arxiv.org/abs/2101.03697def __init__(self, c1, c2, k=3, s=1, p=None, g=1, act=True, deploy=False):super(RepConv, self).__init__()self.deploy = deployself.groups = gself.in_channels = c1self.out_channels = c2assert k == 3assert autopad(k, p) == 1padding_11 = autopad(k, p) - k // 2self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity()) #if deploy:self.rbr_reparam = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=True)else:self.rbr_identity = (nn.BatchNorm2d(num_features=c1) if c2 == c1 and s == 1 else None)self.rbr_dense = nn.Sequential(nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False),nn.BatchNorm2d(num_features=c2),)self.rbr_1x1 = nn.Sequential(nn.Conv2d( c1, c2, 1, s, padding_11, groups=g, bias=False),nn.BatchNorm2d(num_features=c2),)def forward(self, inputs):if hasattr(self, "rbr_reparam"):return self.act(self.rbr_reparam(inputs))if self.rbr_identity is None:id_out = 0else:id_out = self.rbr_identity(inputs)return self.act(self.rbr_dense(inputs) + self.rbr_1x1(inputs) + id_out)def get_equivalent_kernel_bias(self):kernel3x3, bias3x3 = self._fuse_bn_tensor(self.rbr_dense)kernel1x1, bias1x1 = self._fuse_bn_tensor(self.rbr_1x1)kernelid, biasid = self._fuse_bn_tensor(self.rbr_identity)return (kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid,bias3x3 + bias1x1 + biasid,)def _pad_1x1_to_3x3_tensor(self, kernel1x1):if kernel1x1 is None:return 0else:return nn.functional.pad(kernel1x1, [1, 1, 1, 1])def _fuse_bn_tensor(self, branch):if branch is None:return 0, 0if isinstance(branch, nn.Sequential):kernel = branch[0].weightrunning_mean = branch[1].running_meanrunning_var = branch[1].running_vargamma = branch[1].weightbeta = branch[1].biaseps = branch[1].epselse:assert isinstance(branch, nn.BatchNorm2d)if not hasattr(self, "id_tensor"):input_dim = self.in_channels // self.groupskernel_value = np.zeros((self.in_channels, input_dim, 3, 3), dtype=np.float32)for i in range(self.in_channels):kernel_value[i, i % input_dim, 1, 1] = 1self.id_tensor = torch.from_numpy(kernel_value).to(branch.weight.device)kernel = self.id_tensorrunning_mean = branch.running_meanrunning_var = branch.running_vargamma = branch.weightbeta = branch.biaseps = branch.epsstd = (running_var + eps).sqrt()t = (gamma / std).reshape(-1, 1, 1, 1)return kernel * t, beta - running_mean * gamma / stddef repvgg_convert(self):kernel, bias = self.get_equivalent_kernel_bias()return (kernel.detach().cpu().numpy(),bias.detach().cpu().numpy(),)def fuse_conv_bn(self, conv, bn):std = (bn.running_var + bn.eps).sqrt()bias = bn.bias - bn.running_mean * bn.weight / stdt = (bn.weight / std).reshape(-1, 1, 1, 1)weights = conv.weight * tbn = nn.Identity()conv = nn.Conv2d(in_channels = conv.in_channels,out_channels = conv.out_channels,kernel_size = conv.kernel_size,stride=conv.stride,padding = conv.padding,dilation = conv.dilation,groups = conv.groups,bias = True,padding_mode = conv.padding_mode)conv.weight = torch.nn.Parameter(weights)conv.bias = torch.nn.Parameter(bias)return convdef fuse_repvgg_block(self): if self.deploy:returnprint(f"RepConv.fuse_repvgg_block")self.rbr_dense = self.fuse_conv_bn(self.rbr_dense[0], self.rbr_dense[1])self.rbr_1x1 = self.fuse_conv_bn(self.rbr_1x1[0], self.rbr_1x1[1])rbr_1x1_bias = self.rbr_1x1.biasweight_1x1_expanded = torch.nn.functional.pad(self.rbr_1x1.weight, [1, 1, 1, 1])# Fuse self.rbr_identityif (isinstance(self.rbr_identity, nn.BatchNorm2d) or isinstance(self.rbr_identity, nn.modules.batchnorm.SyncBatchNorm)):# print(f"fuse: rbr_identity == BatchNorm2d or SyncBatchNorm")identity_conv_1x1 = nn.Conv2d(in_channels=self.in_channels,out_channels=self.out_channels,kernel_size=1,stride=1,padding=0,groups=self.groups, bias=False)identity_conv_1x1.weight.data = identity_conv_1x1.weight.data.to(self.rbr_1x1.weight.data.device)identity_conv_1x1.weight.data = identity_conv_1x1.weight.data.squeeze().squeeze()# print(f" identity_conv_1x1.weight = {identity_conv_1x1.weight.shape}")identity_conv_1x1.weight.data.fill_(0.0)identity_conv_1x1.weight.data.fill_diagonal_(1.0)identity_conv_1x1.weight.data = identity_conv_1x1.weight.data.unsqueeze(2).unsqueeze(3)# print(f" identity_conv_1x1.weight = {identity_conv_1x1.weight.shape}")identity_conv_1x1 = self.fuse_conv_bn(identity_conv_1x1, self.rbr_identity)bias_identity_expanded = identity_conv_1x1.biasweight_identity_expanded = torch.nn.functional.pad(identity_conv_1x1.weight, [1, 1, 1, 1]) else:# print(f"fuse: rbr_identity != BatchNorm2d, rbr_identity = {self.rbr_identity}")bias_identity_expanded = torch.nn.Parameter( torch.zeros_like(rbr_1x1_bias) )weight_identity_expanded = torch.nn.Parameter( torch.zeros_like(weight_1x1_expanded) ) #print(f"self.rbr_1x1.weight = {self.rbr_1x1.weight.shape}, ")#print(f"weight_1x1_expanded = {weight_1x1_expanded.shape}, ")#print(f"self.rbr_dense.weight = {self.rbr_dense.weight.shape}, ")self.rbr_dense.weight = torch.nn.Parameter(self.rbr_dense.weight + weight_1x1_expanded + weight_identity_expanded)self.rbr_dense.bias = torch.nn.Parameter(self.rbr_dense.bias + rbr_1x1_bias + bias_identity_expanded)self.rbr_reparam = self.rbr_denseself.deploy = Trueif self.rbr_identity is not None:del self.rbr_identityself.rbr_identity = Noneif self.rbr_1x1 is not None:del self.rbr_1x1self.rbr_1x1 = Noneif self.rbr_dense is not None:del self.rbr_denseself.rbr_dense = None
2.2 更改init.py文件
关键步骤二:修改modules文件夹下的__init__.py文件,先导入函数
然后在下面的__all__中声明函数
2.3 添加yaml文件
关键步骤三:在/ultralytics/ultralytics/cfg/models/11下面新建文件yolo11_SimRepCSP.yaml文件,粘贴下面的内容
- 目标检测
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model. More improvement points for YOLOv8, please see https://github.com/iscyy/ultralyticsPro# 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 GFLOPss: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPsm: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPsl: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPsx: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs# YOLOv8.0n 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, 1, Conv, [64, 1, 1]]- [-1, 1, RepConv, [64, 3, 1]]- [[-1,-2], 1, Concat, [1]] #4- [-1, 1, Conv, [128, 1, 1]]- [-1, 1, Conv, [256, 3, 2]]- [-1, 1, Conv, [128, 1, 1]] #7- [-1, 1, RepConv, [128, 3, 1]] #8- [[-1,-2], 1, Concat, [1]] #9- [-1, 1, Conv, [256, 1, 1]] #10 -P4/16 - [-1, 1, Conv, [512, 3, 2]] #11- [-1, 1, Conv, [256, 1, 1]] #12- [-1, 1, RepConv, [256, 3, 1]] #13- [[-1,-2], 1, Concat, [1]] #14- [-1, 1, Conv, [512, 1, 1]] #15- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 16- [-1, 1, Conv, [512, 1, 1]] #17- [-1, 1, RepConv, [512, 3, 1]] #18- [[-1,-2], 1, Concat, [1]] #19- [-1, 1, Conv, [1024, 1, 1]] #20- [-1, 1, SPPF, [1024, 5]] # 21# YOLOv8.0n head
head:- [-1, 1, Conv, [512, 1, 1]] #22- [-1, 1, nn.Upsample, [None, 2, 'nearest']]- [[-1, 11], 1, Concat, [1]] # cat backbone P4- [-1, 3, C3k2, [512, False]] # 25- [-1, 1, Conv, [256, 1, 1]] #26- [-1, 1, nn.Upsample, [None, 2, 'nearest']]- [[-1, 6], 1, Concat, [1]] #28 cat backbone P3- [-1, 3, C3k2, [256, False]] # 29 (P3/8-small)- [-1, 1, Conv, [256, 3, 2]]- [[-1,26], 1, Concat, [1]] # 31 cat head P4- [-1, 3, C3k2, [512, False]] # 32 (P4/16-medium)- [-1, 1, Conv, [512, 3, 2]]- [[-1, 22], 1, Concat, [1]] #34 cat head P5- [-1, 3, C3k2, [1024, False]] #35 (P5/32-large)- [[29, 32, 35], 1, Detect, [nc]] # Detect(P3, P4, P5)
- 语义分割
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model. More improvement points for YOLOv8, please see https://github.com/iscyy/ultralyticsPro# 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 GFLOPss: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPsm: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPsl: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPsx: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs# YOLOv8.0n 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, 1, Conv, [64, 1, 1]]- [-1, 1, RepConv, [64, 3, 1]]- [[-1,-2], 1, Concat, [1]] #4- [-1, 1, Conv, [128, 1, 1]]- [-1, 1, Conv, [256, 3, 2]]- [-1, 1, Conv, [128, 1, 1]] #7- [-1, 1, RepConv, [128, 3, 1]] #8- [[-1,-2], 1, Concat, [1]] #9- [-1, 1, Conv, [256, 1, 1]] #10 -P4/16 - [-1, 1, Conv, [512, 3, 2]] #11- [-1, 1, Conv, [256, 1, 1]] #12- [-1, 1, RepConv, [256, 3, 1]] #13- [[-1,-2], 1, Concat, [1]] #14- [-1, 1, Conv, [512, 1, 1]] #15- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 16- [-1, 1, Conv, [512, 1, 1]] #17- [-1, 1, RepConv, [512, 3, 1]] #18- [[-1,-2], 1, Concat, [1]] #19- [-1, 1, Conv, [1024, 1, 1]] #20- [-1, 1, SPPF, [1024, 5]] # 21# YOLOv8.0n head
head:- [-1, 1, Conv, [512, 1, 1]] #22- [-1, 1, nn.Upsample, [None, 2, 'nearest']]- [[-1, 11], 1, Concat, [1]] # cat backbone P4- [-1, 3, C3k2, [512, False]] # 25- [-1, 1, Conv, [256, 1, 1]] #26- [-1, 1, nn.Upsample, [None, 2, 'nearest']]- [[-1, 6], 1, Concat, [1]] #28 cat backbone P3- [-1, 3, C3k2, [256, False]] # 29 (P3/8-small)- [-1, 1, Conv, [256, 3, 2]]- [[-1,26], 1, Concat, [1]] # 31 cat head P4- [-1, 3, C3k2, [512, False]] # 32 (P4/16-medium)- [-1, 1, Conv, [512, 3, 2]]- [[-1, 22], 1, Concat, [1]] #34 cat head P5- [-1, 3, C3k2, [1024, False]] #35 (P5/32-large)- [[29, 32, 35], 1, Segment, [nc, 32, 256]] # Segment(P3, P4, P5)
- 旋转目标检测
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model. More improvement points for YOLOv8, please see https://github.com/iscyy/ultralyticsPro# 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 GFLOPss: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPsm: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPsl: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPsx: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs# YOLOv8.0n 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, 1, Conv, [64, 1, 1]]- [-1, 1, RepConv, [64, 3, 1]]- [[-1,-2], 1, Concat, [1]] #4- [-1, 1, Conv, [128, 1, 1]]- [-1, 1, Conv, [256, 3, 2]]- [-1, 1, Conv, [128, 1, 1]] #7- [-1, 1, RepConv, [128, 3, 1]] #8- [[-1,-2], 1, Concat, [1]] #9- [-1, 1, Conv, [256, 1, 1]] #10 -P4/16 - [-1, 1, Conv, [512, 3, 2]] #11- [-1, 1, Conv, [256, 1, 1]] #12- [-1, 1, RepConv, [256, 3, 1]] #13- [[-1,-2], 1, Concat, [1]] #14- [-1, 1, Conv, [512, 1, 1]] #15- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 16- [-1, 1, Conv, [512, 1, 1]] #17- [-1, 1, RepConv, [512, 3, 1]] #18- [[-1,-2], 1, Concat, [1]] #19- [-1, 1, Conv, [1024, 1, 1]] #20- [-1, 1, SPPF, [1024, 5]] # 21# YOLOv8.0n head
head:- [-1, 1, Conv, [512, 1, 1]] #22- [-1, 1, nn.Upsample, [None, 2, 'nearest']]- [[-1, 11], 1, Concat, [1]] # cat backbone P4- [-1, 3, C3k2, [512, False]] # 25- [-1, 1, Conv, [256, 1, 1]] #26- [-1, 1, nn.Upsample, [None, 2, 'nearest']]- [[-1, 6], 1, Concat, [1]] #28 cat backbone P3- [-1, 3, C3k2, [256, False]] # 29 (P3/8-small)- [-1, 1, Conv, [256, 3, 2]]- [[-1,26], 1, Concat, [1]] # 31 cat head P4- [-1, 3, C3k2, [512, False]] # 32 (P4/16-medium)- [-1, 1, Conv, [512, 3, 2]]- [[-1, 22], 1, Concat, [1]] #34 cat head P5- [-1, 3, C3k2, [1024, False]] #35 (P5/32-large)- [[29, 32, 35], 1, OBB, [nc, 1]] # OBB(P3, P4, P5)
温馨提示:本文只是对yolo11基础上添加模块,如果要对yolo11n/l/m/x进行添加则只需要指定对应的depth_multiple 和 width_multiple
# YOLO11n
depth_multiple: 0.50 # model depth multiple
width_multiple: 0.25 # layer channel multiple
max_channel:1024# YOLO11s
depth_multiple: 0.50 # model depth multiple
width_multiple: 0.50 # layer channel multiple
max_channel:1024# YOLO11m
depth_multiple: 0.50 # model depth multiple
width_multiple: 1.00 # layer channel multiple
max_channel:512# YOLO11l
depth_multiple: 1.00 # model depth multiple
width_multiple: 1.00 # layer channel multiple
max_channel:512 # YOLO11x
depth_multiple: 1.00 # model depth multiple
width_multiple: 1.50 # layer channel multiple
max_channel:512
2.4 在task.py中进行注册
关键步骤四:在parse_model函数中进行注册,添加GCNet
先在task.py导入函数
然后在task.py文件下找到parse_model这个函数,如下图,添加GCNet
2.5 执行程序
关键步骤五: 在ultralytics文件中新建train.py,将model的参数路径设置为yolo11_SimRepCSP.yaml的路径即可
from ultralytics import YOLO
import warnings
warnings.filterwarnings('ignore')
from pathlib import Pathif __name__ == '__main__':# 加载模型model = YOLO("ultralytics/cfg/11/yolo11.yaml") # 你要选择的模型yaml文件地址# Use the modelresults = model.train(data=r"你的数据集的yaml文件地址",epochs=100, batch=16, imgsz=640, workers=4, name=Path(model.cfg).stem) # 训练模型
🚀运行程序,如果出现下面的内容则说明添加成功🚀
from n params module arguments0 -1 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2]1 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2]2 -1 1 544 ultralytics.nn.modules.conv.Conv [32, 16, 1, 1]3 -1 1 2624 ultralytics.nn.modules.conv.RepConv [16, 16, 3, 1]4 [-1, -2] 1 0 ultralytics.nn.modules.conv.Concat [1]5 -1 1 1088 ultralytics.nn.modules.conv.Conv [32, 32, 1, 1]6 -1 1 18560 ultralytics.nn.modules.conv.Conv [32, 64, 3, 2]7 -1 1 2112 ultralytics.nn.modules.conv.Conv [64, 32, 1, 1]8 -1 1 10368 ultralytics.nn.modules.conv.RepConv [32, 32, 3, 1]9 [-1, -2] 1 0 ultralytics.nn.modules.conv.Concat [1]10 -1 1 4224 ultralytics.nn.modules.conv.Conv [64, 64, 1, 1]11 -1 1 73984 ultralytics.nn.modules.conv.Conv [64, 128, 3, 2]12 -1 1 8320 ultralytics.nn.modules.conv.Conv [128, 64, 1, 1]13 -1 1 41216 ultralytics.nn.modules.conv.RepConv [64, 64, 3, 1]14 [-1, -2] 1 0 ultralytics.nn.modules.conv.Concat [1]15 -1 1 16640 ultralytics.nn.modules.conv.Conv [128, 128, 1, 1]16 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2]17 -1 1 33024 ultralytics.nn.modules.conv.Conv [256, 128, 1, 1]18 -1 1 164352 ultralytics.nn.modules.conv.RepConv [128, 128, 3, 1]19 [-1, -2] 1 0 ultralytics.nn.modules.conv.Concat [1]20 -1 1 66048 ultralytics.nn.modules.conv.Conv [256, 256, 1, 1]21 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5]22 -1 1 33024 ultralytics.nn.modules.conv.Conv [256, 128, 1, 1]23 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']24 [-1, 11] 1 0 ultralytics.nn.modules.conv.Concat [1]25 -1 1 94912 ultralytics.nn.modules.block.C3k2 [256, 128, 1, False]26 -1 1 8320 ultralytics.nn.modules.conv.Conv [128, 64, 1, 1]27 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']28 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1]29 -1 1 23904 ultralytics.nn.modules.block.C3k2 [128, 64, 1, False]30 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2]31 [-1, 26] 1 0 ultralytics.nn.modules.conv.Concat [1]32 -1 1 78528 ultralytics.nn.modules.block.C3k2 [128, 128, 1, False]33 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2]34 [-1, 22] 1 0 ultralytics.nn.modules.conv.Concat [1]35 -1 1 312704 ultralytics.nn.modules.block.C3k2 [256, 256, 1, False]36 [29, 32, 35] 1 464912 ultralytics.nn.modules.head.Detect [80, [64, 128, 256]]
YOLO11_SimRepCSP summary: 246 layers, 2,109,280 parameters, 2,109,264 gradients, 5.4 GFLOPs
3. 完整代码分享
这个后期补充吧~,先按照步骤来即可
4. GFLOPs
关于GFLOPs的计算方式可以查看:百面算法工程师 | 卷积基础知识——Convolution
未改进的YOLO11n GFLOPs
改进后的GFLOPs
6. 进阶
可以与其他的注意力机制或者损失函数等结合,进一步提升检测效果
7.总结
通过以上的改进方法,我们成功提升了模型的表现。这只是一个开始,未来还有更多优化和技术深挖的空间。在这里,我想隆重向大家推荐我的专栏——<专栏地址:YOLO11入门 + 改进涨点——点击即可跳转 欢迎订阅>。这个专栏专注于前沿的深度学习技术,特别是目标检测领域的最新进展,不仅包含对YOLO11的深入解析和改进策略,还会定期更新来自各大顶会(如CVPR、NeurIPS等)的论文复现和实战分享。
为什么订阅我的专栏? ——专栏地址:YOLO11入门 + 改进涨点——点击即可跳转 欢迎订阅
-
前沿技术解读:专栏不仅限于YOLO系列的改进,还会涵盖各类主流与新兴网络的最新研究成果,帮助你紧跟技术潮流。
-
详尽的实践分享:所有内容实践性也极强。每次更新都会附带代码和具体的改进步骤,保证每位读者都能迅速上手。
-
问题互动与答疑:订阅我的专栏后,你将可以随时向我提问,获取及时的答疑。
-
实时更新,紧跟行业动态:不定期发布来自全球顶会的最新研究方向和复现实验报告,让你时刻走在技术前沿。
专栏适合人群:
-
对目标检测、YOLO系列网络有深厚兴趣的同学
-
希望在用YOLO算法写论文的同学
-
对YOLO算法感兴趣的同学等