一、shufflenetv2简介
ShuffleNetV2是一种高效的卷积神经网络架构,用于图像分类和目标检测任务。其主要特点是在保持较高准确性的同时,显著减少了模型的计算和参数量。
ShuffleNetV2的核心思想是通过引入轻量级的通道重排(channel shuffle)操作,促使信息在网络中充分混合和传递,从而提高模型的表示能力。通道重排操作将输入特征图按通道数分组,并将这些组进行随机排列,然后再按顺序重新组合,从而打破了通道之间的信息孤岛,增加了特征图之间的交互。
此外,ShuffleNetV2还采用了逐通道的组卷积(depthwise conv)策略,将卷积操作分成多个较小的组,减少了计算成本。
ShuffleNetV2的设计灵感来自于传统的打牌方式中的洗牌操作,通过将特征图的通道进行重排和混合,从而实现了在较小的计算和参数开销下,保持较高的模型性能。这使得ShuffleNetV2成为一种理想的深度学习网络架构,适用于嵌入式设备和计算资源有限的场景。
如下为Channel Shuffle原理:
网络结构:
(a)(b)为ShuffleNet V1原理图,(c)(d)为ShuffleNet V2原理图(d为降采样层)
二、源代码
import torch
import torch.nn as nn
def channel_shuffle(x, groups):
batchsize, num_channels, height, width = x.data.size()
channels_per_group = num_channels // groups
x = x.view(batchsize, groups, channels_per_group, height, width)
x = torch.transpose(x, 1, 2).contiguous()
x = x.view(batchsize, -1, height, width)
return x
class CBRM(nn.Module): # Conv BN ReLU Maxpool2d
def __init__(self, c1, c2):
super(CBRM, self).__init__()
self.conv = nn.Sequential(
nn.Conv2d(c1, c2, kernel_size=3, stride=2, padding=1, bias=False),
nn.BatchNorm2d(c2),
nn.ReLU(inplace=True),
)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
def forward(self, x):
return self.maxpool(self.conv(x))
class Shuffle_Block(nn.Module):
def __init__(self, ch_in, ch_out, stride):
super(Shuffle_Block, self).__init__()
if not (1 <= stride <= 2):
raise ValueError('illegal stride value')
self.stride = stride
branch_features = ch_out // 2
assert (self.stride != 1) or (ch_in == branch_features << 1)
if self.stride > 1:
self.branch1 = nn.Sequential(
self.depthwise_conv(ch_in, ch_in, kernel_size=3, stride=self.stride, padding=1),
nn.BatchNorm2d(ch_in),
nn.Conv2d(ch_in, branch_features, kernel_size=1, stride=1, padding=0, bias=False),
nn.BatchNorm2d(branch_features),
nn.ReLU(inplace=True),
)
self.branch2 = nn.Sequential(
nn.Conv2d(ch_in if (self.stride > 1) else branch_features,
branch_features, kernel_size=1, stride=1, padding=0, bias=False),
nn.BatchNorm2d(branch_features),
nn.ReLU(inplace=True),
self.depthwise_conv(branch_features, branch_features, kernel_size=3, stride=self.stride, padding=1),
nn.BatchNorm2d(branch_features),
nn.Conv2d(branch_features, branch_features, kernel_size=1, stride=1, padding=0, bias=False),
nn.BatchNorm2d(branch_features),
nn.ReLU(inplace=True),
)
@staticmethod
def depthwise_conv(i, o, kernel_size, stride=1, padding=0, bias=False):
return nn.Conv2d(i, o, kernel_size, stride, padding, bias=bias, groups=i)
def forward(self, x):
if self.stride == 1:
x1, x2 = x.chunk(2, dim=1)
out = torch.cat((x1, self.branch2(x2)), dim=1)
else:
out = torch.cat((self.branch1(x), self.branch2(x)), dim=1)
out = channel_shuffle(out, 2)
return out
三、应用YOLOv8
3.1 block.py文件
在ultralytics/nn/modules/block.py中添加第二步的代码,然后在该文件最上方添加如下代码:
3.2 init.py 文件
在 ultralytics/nn/modules/init.py 文件中的两处位置分别添加如下代码,
3.3 task.py导入
在 ultralytics/nn/tasks.py 上方导入类名:
在parse_model类中,添加如下代码:
elif m in [CBRM, Shuffle_Block]:
c1, c2 = ch[f], args[0]
if c2 != nc:
c2 = make_divisible(min(c2, max_channels) * width, 8)
args = [c1, c2, *args[1:]]
3.4 yolov8-ShuffleNetv2.yaml文件配置
# 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
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [ -1, 1, CBRM, [ 32 ] ] # 0-P2/4
- [ -1, 1, Shuffle_Block, [ 128, 2 ] ] # 1-P3/8
- [ -1, 3, Shuffle_Block, [ 128, 1 ] ] # 2
- [ -1, 1, Shuffle_Block, [ 256, 2 ] ] # 3-P4/16
- [ -1, 7, Shuffle_Block, [ 256, 1 ] ] # 4
- [ -1, 1, Shuffle_Block, [ 512, 2 ] ] # 5-P5/32
- [ -1, 3, Shuffle_Block, [ 512, 1 ] ] # 6
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 3], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 9
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 2], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 12 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 15 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 6], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 18 (P5/32-large)
- [[12, 15, 18], 1, Detect, [nc]] # Detect(P3, P4, P5)