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💡💡💡
本文介绍DSConv, DSConv 将传统的卷积核分解为两个组件:可变量化核 (VQK) 和分布偏移。通过在 VQK 中仅存储整数值来实现更低的内存使用和更高的速度,同时通过应用基于内核和通道的分布偏移来保留与原始卷积相同的输出。通过将浮点运算替换为整数运算,将卷积核中的内存使用量减少了 14 倍,并将运算速度提高了 10 倍。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. 代码实现
2.1 添加DSConv到YOLOv11代码中
2.2 更改init.py文件
2.3 新增yaml文件
2.4 在task.py中进行注册
2.5 执行程序
3.修改后的网络结构图
4. 完整代码分享
5. GFLOPs
6. 进阶
7.总结
1. 论文
论文地址:DSConv: Efficient Convolution Operator——点击即可跳转
官方代码:官方代码仓库——点击即可跳转
2. 代码实现
2.1 添加DSConv到YOLOv11代码中
关键步骤一:将下面代码粘贴到在/ultralytics/ultralytics/nn/modules/conv.py中
from torch.nn.modules.conv import _ConvNd
from torch.nn.modules.utils import _pair
class DSConv(_ConvNd):
def __init__(self, in_channels, out_channels, kernel_size, stride=1,
padding=None, dilation=1, groups=1, padding_mode='zeros', bias=False, block_size=32, KDSBias=False,
CDS=False):
padding = _pair(autopad(kernel_size, padding, dilation))
kernel_size = _pair(kernel_size)
stride = _pair(stride)
dilation = _pair(dilation)
blck_numb = math.ceil((in_channels / (block_size * groups)))
super(DSConv, self).__init__(
in_channels, out_channels, kernel_size, stride, padding, dilation,
False, _pair(0), groups, bias, padding_mode)
# KDS weight From Paper
self.intweight = torch.Tensor(out_channels, in_channels, *kernel_size)
self.alpha = torch.Tensor(out_channels, blck_numb, *kernel_size)
# KDS bias From Paper
self.KDSBias = KDSBias
self.CDS = CDS
if KDSBias:
self.KDSb = torch.Tensor(out_channels, blck_numb, *kernel_size)
if CDS:
self.CDSw = torch.Tensor(out_channels)
self.CDSb = torch.Tensor(out_channels)
self.reset_parameters()
def get_weight_res(self):
# Include expansion of alpha and multiplication with weights to include in the convolution layer here
alpha_res = torch.zeros(self.weight.shape).to(self.alpha.device)
# Include KDSBias
if self.KDSBias:
KDSBias_res = torch.zeros(self.weight.shape).to(self.alpha.device)
# Handy definitions:
nmb_blocks = self.alpha.shape[1]
total_depth = self.weight.shape[1]
bs = total_depth // nmb_blocks
llb = total_depth - (nmb_blocks - 1) * bs
# Casting the Alpha values as same tensor shape as weight
for i in range(nmb_blocks):
length_blk = llb if i == nmb_blocks - 1 else bs
shp = self.alpha.shape # Notice this is the same shape for the bias as well
to_repeat = self.alpha[:, i, ...].view(shp[0], 1, shp[2], shp[3]).clone()
repeated = to_repeat.expand(shp[0], length_blk, shp[2], shp[3]).clone()
alpha_res[:, i * bs:(i * bs + length_blk), ...] = repeated.clone()
if self.KDSBias:
to_repeat = self.KDSb[:, i, ...].view(shp[0], 1, shp[2], shp[3]).clone()
repeated = to_repeat.expand(shp[0], length_blk, shp[2], shp[3]).clone()
KDSBias_res[:, i * bs:(i * bs + length_blk), ...] = repeated.clone()
if self.CDS:
to_repeat = self.CDSw.view(-1, 1, 1, 1)
repeated = to_repeat.expand_as(self.weight)
print(repeated.shape)
# Element-wise multiplication of alpha and weight
weight_res = torch.mul(alpha_res, self.weight)
if self.KDSBias:
weight_res = torch.add(weight_res, KDSBias_res)
return weight_res
def forward(self, input):
# Get resulting weight
# weight_res = self.get_weight_res()
# Returning convolution
return F.conv2d(input, self.weight, self.bias,
self.stride, self.padding, self.dilation,
self.groups)
class DSConv2D(Conv):
def __init__(self, inc, ouc, k=1, s=1, p=None, g=1, d=1, act=True):
super().__init__(inc, ouc, k, s, p, g, d, act)
self.conv = DSConv(inc, ouc, k, s, p, g, d)
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 新增yaml文件
关键步骤三:在 \ultralytics\ultralytics\cfg\models\11下新建文件 yolo11_DSConv.yaml并将下面代码复制进去
- 目标检测
# 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, DSConv2D, [64, 3, 2]] # 0-P1/2
- [-1, 1, DSConv2D, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, DSConv2D, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, DSConv2D, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, DSConv2D, [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, DSConv2D, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
- [-1, 1, DSConv2D, [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)
- 语义分割
# 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, DSConv2D, [64, 3, 2]] # 0-P1/2
- [-1, 1, DSConv2D, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, DSConv2D, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, DSConv2D, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, DSConv2D, [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, DSConv2D, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
- [-1, 1, DSConv2D, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, Segment, [nc, 32, 256]] # Detect(P3, P4, P5)
- 旋转目标检测
# 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, DSConv2D, [64, 3, 2]] # 0-P1/2
- [-1, 1, DSConv2D, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, DSConv2D, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, DSConv2D, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, DSConv2D, [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, DSConv2D, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
- [-1, 1, DSConv2D, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, OBB, [nc, 1]] # Detect(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task.py的parse_model函数中进行注册
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DSConv
2.5 执行程序
在train.py中,将model的参数路径设置为yolo11_DSConv.yaml的路径
建议大家写绝对路径,确保一定能找到
from ultralytics import YOLO
import warnings
warnings.filterwarnings('ignore')
from pathlib import Path
if __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 model
results = 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 arguments
0 -1 1 464 ultralytics.nn.modules.conv.DSConv2D [3, 16, 3, 2]
1 -1 1 4672 ultralytics.nn.modules.conv.DSConv2D [16, 32, 3, 2]
2 -1 1 6640 ultralytics.nn.modules.block.C3k2 [32, 64, 1, False, 0.25]
3 -1 1 36992 ultralytics.nn.modules.conv.DSConv2D [64, 64, 3, 2]
4 -1 1 26080 ultralytics.nn.modules.block.C3k2 [64, 128, 1, False, 0.25]
5 -1 1 147712 ultralytics.nn.modules.conv.DSConv2D [128, 128, 3, 2]
6 -1 1 87040 ultralytics.nn.modules.block.C3k2 [128, 128, 1, True]
7 -1 1 295424 ultralytics.nn.modules.conv.DSConv2D [128, 256, 3, 2]
8 -1 1 346112 ultralytics.nn.modules.block.C3k2 [256, 256, 1, True]
9 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5]
10 -1 1 249728 ultralytics.nn.modules.block.C2PSA [256, 256, 1]
11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
12 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1]
13 -1 1 111296 ultralytics.nn.modules.block.C3k2 [384, 128, 1, False]
14 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
15 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1]
16 -1 1 32096 ultralytics.nn.modules.block.C3k2 [256, 64, 1, False]
17 -1 1 36992 ultralytics.nn.modules.conv.DSConv2D [64, 64, 3, 2]
18 [-1, 13] 1 0 ultralytics.nn.modules.conv.Concat [1]
19 -1 1 86720 ultralytics.nn.modules.block.C3k2 [192, 128, 1, False]
20 -1 1 147712 ultralytics.nn.modules.conv.DSConv2D [128, 128, 3, 2]
21 [-1, 10] 1 0 ultralytics.nn.modules.conv.Concat [1]
22 -1 1 378880 ultralytics.nn.modules.block.C3k2 [384, 256, 1, True]
23 [16, 19, 22] 1 464912 ultralytics.nn.modules.head.Detect [80, [64, 128, 256]]
YOLO11_DSConv2D summary: 319 layers, 2,624,080 parameters, 2,624,064 gradients, 4.9 GFLOPs
3.修改后的网络结构图
4. 完整代码分享
这个后期补充吧~,先按照步骤来即可
5. 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
通过上面的方法,改进就完成且成功了。在这里给大家推荐我的专栏YOLO11改进有效涨点专栏,本专栏目前是新建的,后期我会持续对各种前沿顶会进行论文复现,如果本文对你有帮助,欢迎订阅本专栏,关注后续更多的更新~如果有问题,可以随时问我