Yolov5-v6.0模型详解

先看看yaml文件：可以知道6.0模型主要构成为conv、bottlenet、cs3、sppf、detect层

yaml文件如下：

# YOLOv5 v6.0 backbone

backbone:

# [from, number, module, args]

[[-1, 1, Conv, [64[l1] , 6[l2] , 2[l3] , 2[l4] ]], # 0-P1/2

# 来自上层，含瓶颈层数，本层类型，【输出通道，核大小，滑动，？分组】

#含瓶颈层数只对c3有效，其他层均为1

[-1, 1, Conv, [128, 3, 2]], # 1-P2/4

[-1, 3[l5] , C3, [128]],

[-1, 1, Conv, [256, 3, 2]], # 3-P3/8

[-1, 6, C3, [256]],

[-1, 1, Conv, [512, 3, 2]], # 5-P4/16

[-1, 9, C3, [512]],

[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32

[-1, 3, C3, [1024]],

[-1, 1, SPPF, [1024, 5]], # 9

]

# YOLOv5 v6.0 head

head:

[[-1, 1, Conv, [512, 1, 1]],

[-1, 1, nn.Upsample, [None, 2, 'nearest']],

[[-1, 6], 1, Concat, [1]], # cat backbone P4

[-1, 3, C3, [512, False]], # 13

[-1, 1, Conv, [256, 1, 1]],

[-1, 1, nn.Upsample, [None, 2, 'nearest']],

[[-1, 4], 1, Concat, [1]], # cat backbone P3

[-1, 3, C3, [256, False]], # 17 (P3/8-small)

[-1, 1, Conv, [256, 3, 2]],

[[-1, 14], 1, Concat, [1]], # cat head P4

[-1, 3, C3, [512, False]], # 20 (P4/16-medium)

[-1, 1, Conv, [512, 3, 2]],

[[-1, 10], 1, Concat, [1]], # cat head P5

[-1, 3, C3, [1024, False]], # 23 (P5/32-large)

[[17, 20, 23], 1, Detect[l6] , [nc, anchors]], # Detect(P3, P4, P5)

]

以下根据图示看源码---------------------------------------------------------

class Conv(nn.Module):

# Standard convolution

def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups

super().__init__()

self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)

self.bn = nn.BatchNorm2d(c2)

self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())

def forward(self, x):

return self.act(self.bn(self.conv(x)))

def forward_fuse(self, x):

return self.act(self.conv(x))

class Bottleneck(nn.Module):

# Standard bottleneck

def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansion

super().__init__()

c_ = int(c2 * e) # hidden channels 可以增加通道数，扩充网络宽度

self.cv1 = Conv(c1, c_, 1, 1)

self.cv2 = Conv(c_, c2, 3, 1, g=g) #核是3

self.add = shortcut and c1 == c2

def forward(self, x):

return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))

class C3(nn.Module):

# CSP Bottleneck with 3 convolutions

def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion

super().__init__()

c_ = int(c2 * e) # hidden channels 可以扩充网络宽度

self.cv1 = Conv(c1, c_, 1, 1)

self.cv2 = Conv(c1, c_, 1, 1)

self.cv3 = Conv(2 * c_, c2, 1) # act=FReLU(c2) concat后conv输入通道要是2 * c_，

self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))

#通道数不会变化都是c_

# self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)])

def forward(self, x):

return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))

sppf图示：

class SPPF(nn.Module): # SPPF 输入通道c1,输出通道c2,大小不变

# Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher

def __init__(self, c1, c2, k=5): # equivalent to SPP(k=(5, 9, 13))

super().__init__()

c_ = c1 // 2 # hidden channels

self.cv1 = Conv(c1, c_, 1, 1) #核1，滑动1

self.cv2 = Conv(c_ * 4, c2, 1, 1) #

self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2) #最大池化，滑动1，此处大小不变

def forward(self, x):

x = self.cv1(x)

with warnings.catch_warnings():

warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning

y1 = self.m(x)

y2 = self.m(y1)

return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))

detect层是最后一层：

如果是训练时，

（1）3个head，经过conv，

（2）每层原来数据为4维：[batch,anchor*（class+5）,h,w] 经过处理后变为5维：

[batch,anchor,h,w,class+5]

见下面绿色代码

如果是预测，3个head预测结果经过（1）（2）

（3）conv后sigmoid变为0~1，然后转化到格子空间。

（4）3个头的数据转化为（batch, _ ,85）然后cat在一起

#-----------------detct源码-------------------------------------------------------

class Detect(nn.Module):#如果是训练，输出3个张量，如果是预测输出【【batch，_，类+5】

stride = None # strides computed during build

onnx_dynamic = False # ONNX export parameter

def __init__(self, nc=80, anchors=(), ch=(), inplace=True): # detection layer

#ch=()应该是3个头的通道数

super().__init__()

self.nc = nc # number of classes

self.no = nc + 5 # number of outputs per anchor

self.nl = len(anchors) # number of detection layers

self.na = len(anchors[0]) // 2 # number of anchors，一般为3

self.grid = [torch.zeros(1)] * self.nl # init grid

self.anchor_grid = [torch.zeros(1)] * self.nl # init anchor grid

self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2))

# shape(nl,na,2)

self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv

#ch 输入的3个头输出的通道【128，256，512】

self.inplace = inplace # use in-place ops (e.g. slice assignment)

def forward(self, x):

z = [] # inference output

for i in range(self.nl): #3个头分别处理 nl是检测层的数量3

x[i] = self.m[i](x[i]) # conv

bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)

x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()

#4维转为5维 x(bs,3,20,20,85)

if not self.training: # inference，如果不是训练，把数据处理成（batch,_,85）

if self.onnx_dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:

self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)

y = x[i].sigmoid() #0~1化

#下面把预测映射到格子空间尺度。预测使用下面结果 y

if self.inplace:

y[..., 0:2] = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i] # xy

y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh

else: # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953

xy = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i] # xy

wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh

y = torch.cat((xy, wh, y[..., 4:]), -1)

z.append(y.view(bs, -1, self.no))

return x if self.training else (torch.cat(z, 1), x)

#如果是训练直接返回x（3个头），是预测把3个头的数据转化为（batch, _ ,85）然后cat在一起

[l1]输出通道

[l2]核大小

[l3]滑动步长

[l4]可能是分组

[l5]C3中残差模块个数

其他层都为1

[l6]3层预测结果0~1，转为真实的结果输出

Yolov5-v6.0模型详解相关推荐

tensorRT 部署 YOLOV5模型详解
tensorRT 部署 YOLOV5模型详解第一步: 下载tensorRT库 https://developer.nvidia.com/nvidia-tensorrt-8x-download 欢迎使 ...
Transformer 模型详解
Transformer 是 Google 的团队在 2017 年提出的一种 NLP 经典模型,现在比较火热的 Bert 也是基于 Transformer.Transformer 模型使用了 Self- ...
TensorFlow Wide And Deep 模型详解与应用 TensorFlow Wide-And-Deep 阅读344 作者简介：汪剑，现在在出门问问负责推荐与个性化。曾在微软雅虎工作，
TensorFlow Wide And Deep 模型详解与应用 TensorFlow Wide-And-Deep 阅读344 作者简介:汪剑,现在在出门问问负责推荐与个性化.曾在微软雅虎工作,从事 ...
TensorFlow Wide And Deep 模型详解与应用
Wide and deep 模型是 TensorFlow 在 2016 年 6 月左右发布的一类用于分类和回归的模型,并应用到了 Google Play 的应用推荐中 [1].wide and dee ...
数学建模——智能优化之模拟退火模型详解Python代码
数学建模--智能优化之模拟退火模型详解Python代码 #本功能实现最小值的求解#from matplotlib import pyplot as plt import numpy as np imp ...
数学建模——智能优化之粒子群模型详解Python代码
数学建模--智能优化之粒子群模型详解Python代码 import numpy as np import matplotlib.pyplot as plt from mpl_toolkits.mplo ...
数学建模——支持向量机模型详解Python代码
数学建模--支持向量机模型详解Python代码 from numpy import * import random import matplotlib.pyplot as plt import num ...
数学建模——一维、二维插值模型详解Python代码
数学建模--一维.二维插值模型详解Python代码一.一维插值 # -*-coding:utf-8 -*- import numpy as np from scipy import interpol ...
数学建模——线性规划模型详解Python代码
数学建模--线性规划模型详解Python代码标准形式为: min z=2X1+3X2+x s.t x1+4x2+2x3>=8 3x1+2x2>=6 x1,x2,x3>=0 上述线性 ...

Yolov5-v6.0模型详解

sppf图示：

Yolov5-v6.0模型详解相关推荐

最新文章

热门文章