目标检测系列之YOLOv5-yolo.py代码讲解,yolo.py文件主要工作是搭建了YOLOv5网络模型，yolo.py文件也可以单独运行。
YOLOv5中yolo.py代码的讲解，本文使用的YOLOV5-v6版本，小伙伴们可以自行去github上下载。 关于yolov5s.yarm文件的介绍可以参考另一篇博客，地址如下：YOLOV5中yolov5s.yarm文件解析_V爱一世春秋的博客-CSDN博客
一、总体代码讲解
废话不多说直接上代码。
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
YOLO-specific modules
Usage:
$ python path/to/models/yolo.py --cfg yolov5s.yaml
"""
import argparse
import os
import platform
import sys
from copy import deepcopy
from pathlib import Path
FILE = Path(__file__).resolve()
ROOT = FILE.parents[1] # YOLOv5 root directory
if str(ROOT) not in sys.path:
sys.path.append(str(ROOT)) # add ROOT to PATH
if platform.system() != 'Windows':
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
from models.common import *
from models.experimental import *
from utils.autoanchor import check_anchor_order
from utils.general import LOGGER, check_version, check_yaml, make_divisible, print_args
from utils.plots import feature_visualization
from utils.torch_utils import (fuse_conv_and_bn, initialize_weights, model_info, profile, scale_img, select_device,
time_sync)
try:
import thop # for FLOPs computation
except ImportError:
thop = None
class Detect(nn.Module):
stride = None # strides computed during build
onnx_dynamic = False # ONNX export parameter
export = False # export mode
def __init__(self, nc=80, anchors=(), ch=(), inplace=True): # detection layer
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
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
self.inplace = inplace # use in-place ops (e.g. slice assignment)
def forward(self, x):
z = [] # inference output
for i in range(self.nl):
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()
if not self.training: # inference
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()
if self.inplace:
y[..., 0:2] = (y[..., 0:2] * 2 + 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, wh, conf = y.split((2, 2, self.nc + 1), 4) # y.tensor_split((2, 4, 5), 4) # torch 1.8.0
xy = (xy * 2 + self.grid[i]) * self.stride[i] # xy
wh = (wh * 2) ** 2 * self.anchor_grid[i] # wh
y = torch.cat((xy, wh, conf), 4)
z.append(y.view(bs, -1, self.no))
return x if self.training else (torch.cat(z, 1),) if self.export else (torch.cat(z, 1), x)
def _make_grid(self, nx=20, ny=20, i=0):
d = self.anchors[i].device
t = self.anchors[i].dtype
shape = 1, self.na, ny, nx, 2 # grid shape
y, x = torch.arange(ny, device=d, dtype=t), torch.arange(nx, device=d, dtype=t)
if check_version(torch.__version__, '1.10.0'): # torch>=1.10.0 meshgrid workaround for torch>=0.7 compatibility
yv, xv = torch.meshgrid(y, x, indexing='ij')
else:
yv, xv = torch.meshgrid(y, x)
grid = torch.stack((xv, yv), 2).expand(shape) - 0.5 # add grid offset, i.e. y = 2.0 * x - 0.5
anchor_grid = (self.anchors[i] * self.stride[i]).view((1, self.na, 1, 1, 2)).expand(shape)
return grid, anchor_grid
class Model(nn.Module):
# YOLOv5 model
"""
cfg:配置文件
ch:通道数，通常图片传入RGB三个通道，默认为3
nc:模型检测出来的目标类别
anchors:模型所属的类别
在yolov5s.yarm中有nc和ancors参数，这里定义会覆盖掉yolov5s.yarm中定义的值
"""
def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes
super().__init__()
#第一部分：加载配置文件yolov5.yarm
if isinstance(cfg, dict):#判断传入的cfg参数是否为字典False
self.yaml = cfg # model dict
else: # is *.yaml
import yaml # for torch hub
self.yaml_file = Path(cfg).name#获得文件名
with open(cfg, encoding='ascii', errors='ignore') as f: #加载文件
self.yaml = yaml.safe_load(f) # model dict ,加载好后self.yaml中会以字典类型存放yarm文件中参数
# Define model 第二部分，利用配置文件搭建网络模型
ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels, 3 #先去yolov5s.yarm中查询有没有ch参数，yarm文件中没有会用传入的ch值为3
if nc and nc != self.yaml['nc']: #判断nc值跟yarm中传入是否一样，不一样会用新值覆盖
LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
self.yaml['nc'] = nc # override yaml value
if anchors:#如果新传进来的anchors值跟yarm中不一样，会用新传的值覆盖
LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
self.yaml['anchors'] = round(anchors) # override yaml value
#利用yarm文件搭建yolov5的每一层，最后得到模型
self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, 需要单独保存的层savelist:[4, 6, 10, 14, 17, 20, 23]
self.names = [str(i) for i in range(self.yaml['nc'])] # default names 初始化names参数，表示每一类的类别名 80类，每一个赋值一个类名0-80
self.inplace = self.yaml.get('inplace', True) #从yarm文件中加载inplace关键字，如果没有这个关键字会返回一个True
# Build strides, anchors第三部分，对网络步长和ancors进行处理
m = self.model[-1] # 取出网络的最后一层 Detect()
if isinstance(m, Detect):
s = 256 # 2x min stride
m.inplace = self.inplace
"""
通过输入图片的尺寸和预测图片的尺寸得到
torch.zeros(1, ch, s, s)：新建一个空白的图片，图片大小是(1*3*256*256),
把图片传入整个模型中，进行一次前向传播, 传播过程中，会在低层、中层和高层进行三次预测
低层：第四层，通过前向传播输出为32*32大小的图片-->s=256/32=8, 缩放了8倍
同理,256/16得到中间步长为16,256/8得到步长为32
所以:
m.stride = forward：[8,16,32]
"""
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward：[8,16,32]
check_anchor_order(m) # must be in pixel-space (not grid-space)检测ancohrs顺序对不对
m.anchors /= m.stride.view(-1, 1, 1) #定义的anchors是原始图片上的，最终在特征层使用，所以需要anchors除以相同倍数
self.stride = m.stride
self._initialize_biases() # only run once
# Init weights, biases第四部分，网络的初始化以及打印
initialize_weights(self)
self.info()
LOGGER.info('')
def forward(self, x, augment=False, profile=False, visualize=False):
if augment:
return self._forward_augment(x) # augmented inference, None
return self._forward_once(x, profile, visualize) # single-scale inference, train
def _forward_augment(self, x):
img_size = x.shape[-2:] # height, width
s = [1, 0.83, 0.67] # scales
f = [None, 3, None] # flips (2-ud, 3-lr)
y = [] # outputs
for si, fi in zip(s, f):
xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
yi = self._forward_once(xi)[0] # forward
# cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1]) # save
yi = self._descale_pred(yi, fi, si, img_size)
y.append(yi)
y = self._clip_augmented(y) # clip augmented tails
return torch.cat(y, 1), None # augmented inference, train
def _forward_once(self, x, profile=False, visualize=False):
y, dt = [], [] # outputs
for m in self.model:
if m.f != -1: # if not from previous layer
x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers
if profile:
self._profile_one_layer(m, x, dt)
x = m(x) # run
y.append(x if m.i in self.save else None) # save output
if visualize:
feature_visualization(x, m.type, m.i, save_dir=visualize)
return x
def _descale_pred(self, p, flips, scale, img_size):
# de-scale predictions following augmented inference (inverse operation)
if self.inplace:
p[..., :4] /= scale # de-scale
if flips == 2:
p[..., 1] = img_size[0] - p[..., 1] # de-flip ud
elif flips == 3:
p[..., 0] = img_size[1] - p[..., 0] # de-flip lr
else:
x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale # de-scale
if flips == 2:
y = img_size[0] - y # de-flip ud
elif flips == 3:
x = img_size[1] - x # de-flip lr
p = torch.cat((x, y, wh, p[..., 4:]), -1)
return p
def _clip_augmented(self, y):
# Clip YOLOv5 augmented inference tails
nl = self.model[-1].nl # number of detection layers (P3-P5)
g = sum(4 ** x for x in range(nl)) # grid points
e = 1 # exclude layer count
i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e)) # indices
y[0] = y[0][:, :-i] # large
i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e)) # indices
y[-1] = y[-1][:, i:] # small
return y
def _profile_one_layer(self, m, x, dt):
c = isinstance(m, Detect) # is final layer, copy input as inplace fix
o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPs
t = time_sync()
for _ in range(10):
m(x.copy() if c else x)
dt.append((time_sync() - t) * 100)
if m == self.model[0]:
LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s} {'module'}")
LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f} {m.type}')
if c:
LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s} Total")
def _initialize_biases(self, cf=None): # initialize biases into Detect(), cf is class frequency
# https://arxiv.org/abs/1708.02002 section 3.3
# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
m = self.model[-1] # Detect() module
for mi, s in zip(m.m, m.stride): # from
b = mi.bias.view(m.na, -1) # conv.bias(255) to (3,85)
b.data[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)
b.data[:, 5:] += math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum()) # cls
mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
def _print_biases(self):
m = self.model[-1] # Detect() module
for mi in m.m: # from
b = mi.bias.detach().view(m.na, -1).T # conv.bias(255) to (3,85)
LOGGER.info(
('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
# def _print_weights(self):
# for m in self.model.modules():
# if type(m) is Bottleneck:
# LOGGER.info('%10.3g' % (m.w.detach().sigmoid() * 2)) # shortcut weights
def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers
LOGGER.info('Fusing layers... ')
for m in self.model.modules():
if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv
delattr(m, 'bn') # remove batchnorm
m.forward = m.forward_fuse # update forward
self.info()
return self
def info(self, verbose=False, img_size=640): # print model information
model_info(self, verbose, img_size)
def _apply(self, fn):
# Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
self = super()._apply(fn)
m = self.model[-1] # Detect()
if isinstance(m, Detect):
m.stride = fn(m.stride)
m.grid = list(map(fn, m.grid))
if isinstance(m.anchor_grid, list):
m.anchor_grid = list(map(fn, m.anchor_grid))
return self
#依据yolov5s.yarm文件，搭建YOLOV5每一层
def parse_model(d, ch): # model_dict:yolov5s.yaml, input_channels(3):[3] d:字典形式的yarm文件,ch:[3]
LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}")#打印信息
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple'] # gd:0.33, gw:0.5
na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors 看anchors为列表，是anchors有6个值，三对长宽，na=3
no = na * (nc + 5) # number of outputs = anchors * (classes + 5) = 255 输出，nc=80,表示3个anchor下的，每一个anchor都会产生85通道的输出
"""
开始搭建网络每一层
layers:存储创建的网络的每一层
save:统计哪一层的标签是需要单独保存的，例如第四层的输出需要保存，既给第五层使用也供后面第16层使用
c2:输出的通道数
"""
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # 以第0层为例, from:-1, number:1, module:'Conv', args:[64, 6, 2, 2]
m = eval(m) if isinstance(m, str) else m # m是Conv字符串， 通过eval 函数推断 --> Conv 是类在 common.py下面 --> eval strings, m:<class 'models.common.Conv'>
for j, a in enumerate(args):#遍历args:[64, 6, 2, 2]
try:
args[j] = eval(a) if isinstance(a, str) else a # eval strings, [64, 6, 2, 2]
except NameError:
pass
n = n_ = max(round(n * gd), 1) if n > 1 else n # depth gain 如果numbers>1:乘以深度倍数得到真正的number参数
#判断得到的这一层的模块到底是属于什么结构，第0层为Conv
if m in (Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3, C3TR, C3SPP, C3Ghost):
c1, c2 = ch[f], args[0] # c1:3, c2:64, c1表示输入的通道数, c2表示输出的通道数，args:[64, 6, 2, 2]
if c2 != no: # if not output 64 != 255
c2 = make_divisible(c2 * gw, 8) # c2:32, c2要乘以通道倍数64*0.5=32, 在判断32是不是8的倍数，如果不是强制变为8的倍数(8的倍数对CPU/GPU计算更友好)
#初始化Conv类的时候需要传入(c1输入, c2输出, k卷积核大小, s步长, p)共五个参数, 现有的args没有输入c1,c2也需要调整为新计算出的
args = [c1, c2, *args[1:]] # args[3, 32, 6, 2, 2]
if m in [BottleneckCSP, C3, C3TR, C3Ghost]:#C3模块中参数只有[128],而C3类的定义需要传入(c1, c2, n)三个参数, 所以这里新加n参数
args.insert(2, n) # number of repeats
n = 1
elif m is nn.BatchNorm2d:
args = [ch[f]]
elif m is Concat:
c2 = sum(ch[x] for x in f)
elif m is Detect:
args.append([ch[x] for x in f])
if isinstance(args[1], int): # number of anchors
args[1] = [list(range(args[1] * 2))] * len(f)
elif m is Contract:
c2 = ch[f] * args[0] ** 2
elif m is Expand:
c2 = ch[f] // args[0] ** 2
else:
c2 = ch[f]
m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module 判断n是否>1, 如果n>1, 会根据n的数量去初始化这一层有多少n的模块，例如有n=3的C3模块，n>1,此时这一层就要有3个C3模块
t = str(m)[8:-2].replace('__main__.', '') # module type #判断模块名有没有__main__名字，如果有就用空替换掉
np = sum(x.numel() for x in m_.parameters()) # number params 统计参数量
m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f} {t:<40}{str(args):<30}') # print 打印输出信息
save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist 统计需要保存的层
layers.append(m_)
if i == 0:# 第0层会把ch重置为0
ch = []
#把通道数添加到ch里面，后面层会取出上一层的输出通道，作为输入通道
ch.append(c2) # [32],[32,64],[32,64,64]
#所有层都执行完毕，会返回整个网络结构以及需要保存特征的层
return nn.Sequential(*layers), sorted(save) # 需要保存的层号[6, 4, 14, 10, 17, 20, 23] -> [4, 6, 10, 14, 17, 20, 23]
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
parser.add_argument('--batch-size', type=int, default=1, help='total batch size for all GPUs')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--profile', action='store_true', help='profile model speed')
parser.add_argument('--line-profile', action='store_true', help='profile model speed layer by layer')
parser.add_argument('--test', action='store_true', help='test all yolo*.yaml')
opt = parser.parse_args() # Namespace(batch_size=1, cfg='yolov5s.yaml', device='', line_profile=False, profile=False, test=False)
opt.cfg = check_yaml(opt.cfg) # check YAML
print_args(vars(opt))
device = select_device(opt.device)
# Create model 创建YOLOv5模型
im = torch.rand(opt.batch_size, 3, 640, 640).to(device)
model = Model(opt.cfg).to(device)
# Options
if opt.line_profile: # profile layer by layer
_ = model(im, profile=True)
elif opt.profile: # profile forward-backward
results = profile(input=im, ops=[model], n=3)
elif opt.test: # test all models
for cfg in Path(ROOT / 'models').rglob('yolo*.yaml'):
try:
_ = Model(cfg)
except Exception as e:
print(f'Error in {cfg}: {e}')
else: # report fused model summary
model.fuse()二、代码逐步讲解
1、代码开始入口
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
parser.add_argument('--batch-size', type=int, default=1, help='total batch size for all GPUs')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--profile', action='store_true', help='profile model speed')
parser.add_argument('--line-profile', action='store_true', help='profile model speed layer by layer')
parser.add_argument('--test', action='store_true', help='test all yolo*.yaml')
opt = parser.parse_args() # Namespace(batch_size=1, cfg='yolov5s.yaml', device='', line_profile=False, profile=False, test=False)
opt.cfg = check_yaml(opt.cfg) # check YAML
print_args(vars(opt))
device = select_device(opt.device)
# Create model 创建YOLOv5模型
im = torch.rand(opt.batch_size, 3, 640, 640).to(device)
model = Model(opt.cfg).to(device)
# Options
if opt.line_profile: # profile layer by layer
_ = model(im, profile=True)
elif opt.profile: # profile forward-backward
results = profile(input=im, ops=[model], n=3)
elif opt.test: # test all models
for cfg in Path(ROOT / 'models').rglob('yolo*.yaml'):
try:
_ = Model(cfg)
except Exception as e:
print(f'Error in {cfg}: {e}')
else: # report fused model summary
model.fuse()2、继续执行
这里会进行一些参数的设置。
parser = argparse.ArgumentParser()
parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
parser.add_argument('--batch-size', type=int, default=1, help='total batch size for all GPUs')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--profile', action='store_true', help='profile model speed')
parser.add_argument('--line-profile', action='store_true', help='profile model speed layer by layer')
parser.add_argument('--test', action='store_true', help='test all yolo*.yaml')
opt = parser.parse_args() # Namespace(batch_size=1, cfg='yolov5s.yaml', device='', line_profile=False, profile=False, test=False)
opt.cfg = check_yaml(opt.cfg) # check YAML
print_args(vars(opt))创建YoloV5模型
model = Model(opt.cfg).to(device)3、Model网络的搭建
关于yolo.py全代码上面已经给出，这里只介绍__init__初始化模型时的代码。
def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes
super().__init__()
#第一部分：加载配置文件yolov5.yarm
if isinstance(cfg, dict):#判断传入的cfg参数是否为字典False
self.yaml = cfg # model dict
else: # is *.yaml
import yaml # for torch hub
self.yaml_file = Path(cfg).name#获得文件名
with open(cfg, encoding='ascii', errors='ignore') as f: #加载文件
self.yaml = yaml.safe_load(f) # model dict ,加载好后self.yaml中会以字典类型存放yarm文件中参数
# Define model 第二部分，利用配置文件搭建网络模型
ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels, 3 #先去yolov5s.yarm中查询有没有ch参数，yarm文件中没有会用传入的ch值为3
if nc and nc != self.yaml['nc']: #判断nc值跟yarm中传入是否一样，不一样会用新值覆盖
LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
self.yaml['nc'] = nc # override yaml value
if anchors:#如果新传进来的anchors值跟yarm中不一样，会用新传的值覆盖
LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
self.yaml['anchors'] = round(anchors) # override yaml value
#利用yarm文件搭建yolov5的每一层，最后得到模型
self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, 需要单独保存的层savelist:[4, 6, 10, 14, 17, 20, 23]
self.names = [str(i) for i in range(self.yaml['nc'])] # default names 初始化names参数，表示每一类的类别名 80类，每一个赋值一个类名0-80
self.inplace = self.yaml.get('inplace', True) #从yarm文件中加载inplace关键字，如果没有这个关键字会返回一个True
# Build strides, anchors第三部分，对网络步长和ancors进行处理
m = self.model[-1] # 取出网络的最后一层 Detect()
if isinstance(m, Detect):
s = 256 # 2x min stride
m.inplace = self.inplace
"""
通过输入图片的尺寸和预测图片的尺寸得到
torch.zeros(1, ch, s, s)：新建一个空白的图片，图片大小是(1*3*256*256),
把图片传入整个模型中，进行一次前向传播, 传播过程中，会在低层、中层和高层进行三次预测
低层：第四层，通过前向传播输出为32*32大小的图片-->s=256/32=8, 缩放了8倍
同理,256/16得到中间步长为16,256/8得到步长为32
所以:
m.stride = forward：[8,16,32]
"""
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward：[8,16,32]
check_anchor_order(m) # must be in pixel-space (not grid-space)检测ancohrs顺序对不对
m.anchors /= m.stride.view(-1, 1, 1) #定义的anchors是原始图片上的，最终在特征层使用，所以需要anchors除以相同倍数
self.stride = m.stride
self._initialize_biases() # only run once
# Init weights, biases第四部分，网络的初始化以及打印
initialize_weights(self)
self.info()
LOGGER.info('')1、第一部分:加载配置文件yolov5s.yarm文件。
#第一部分：加载配置文件yolov5.yarm
if isinstance(cfg, dict):#判断传入的cfg参数是否为字典False
self.yaml = cfg # model dict
else: # is *.yaml
import yaml # for torch hub
self.yaml_file = Path(cfg).name#获得文件名
with open(cfg, encoding='ascii', errors='ignore') as f: #加载文件
self.yaml = yaml.safe_load(f) # model dict ,加载好后self.yaml中会以字典类型存放yarm文件中参数2、利用配置文件搭建网络模型
ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels, 3 #先去yolov5s.yarm中查询有没有ch参数，yarm文件中没有会用传入的ch值为3
if nc and nc != self.yaml['nc']: #判断nc值跟yarm中传入是否一样，不一样会用新值覆盖
LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
self.yaml['nc'] = nc # override yaml value
if anchors:#如果新传进来的anchors值跟yarm中不一样，会用新传的值覆盖
LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
self.yaml['anchors'] = round(anchors) # override yaml value
#利用yarm文件搭建yolov5的每一层，最后得到模型
self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, 需要单独保存的层savelist:[4, 6, 10, 14, 17, 20, 23]
self.names = [str(i) for i in range(self.yaml['nc'])] # default names 初始化names参数，表示每一类的类别名 80类，每一个赋值一个类名0-80
self.inplace = self.yaml.get('inplace', True) #从yarm文件中加载inplace关键字，如果没有这个关键字会返回一个True搭建YOLOv5网络模型每一层
def parse_model(d, ch): # model_dict:yolov5s.yaml, input_channels(3):[3] d:字典形式的yarm文件,ch:[3]
LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}")#打印信息
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple'] # gd:0.33, gw:0.5
na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors 看anchors为列表，是anchors有6个值，三对长宽，na=3
no = na * (nc + 5) # number of outputs = anchors * (classes + 5) = 255 输出，nc=80,表示3个anchor下的，每一个anchor都会产生85通道的输出
"""
开始搭建网络每一层
layers:存储创建的网络的每一层
save:统计哪一层的标签是需要单独保存的，例如第四层的输出需要保存，既给第五层使用也供后面第16层使用
c2:输出的通道数
"""
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # 以第0层为例, from:-1, number:1, module:'Conv', args:[64, 6, 2, 2]
m = eval(m) if isinstance(m, str) else m # m是Conv字符串， 通过eval 函数推断 --> Conv 是类在 common.py下面 --> eval strings, m:<class 'models.common.Conv'>
for j, a in enumerate(args):#遍历args:[64, 6, 2, 2]
try:
args[j] = eval(a) if isinstance(a, str) else a # eval strings, [64, 6, 2, 2]
except NameError:
pass
n = n_ = max(round(n * gd), 1) if n > 1 else n # depth gain 如果numbers>1:乘以深度倍数得到真正的number参数
#判断得到的这一层的模块到底是属于什么结构，第0层为Conv
if m in (Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3, C3TR, C3SPP, C3Ghost):
c1, c2 = ch[f], args[0] # c1:3, c2:64, c1表示输入的通道数, c2表示输出的通道数，args:[64, 6, 2, 2]
if c2 != no: # if not output 64 != 255
c2 = make_divisible(c2 * gw, 8) # c2:32, c2要乘以通道倍数64*0.5=32, 在判断32是不是8的倍数，如果不是强制变为8的倍数(8的倍数对CPU/GPU计算更友好)
#初始化Conv类的时候需要传入(c1输入, c2输出, k卷积核大小, s步长, p)共五个参数, 现有的args没有输入c1,c2也需要调整为新计算出的
args = [c1, c2, *args[1:]] # args[3, 32, 6, 2, 2]
if m in [BottleneckCSP, C3, C3TR, C3Ghost]:#C3模块中参数只有[128],而C3类的定义需要传入(c1, c2, n)三个参数, 所以这里新加n参数
args.insert(2, n) # number of repeats
n = 1
elif m is nn.BatchNorm2d:
args = [ch[f]]
elif m is Concat:
c2 = sum(ch[x] for x in f)
elif m is Detect:
args.append([ch[x] for x in f])
if isinstance(args[1], int): # number of anchors
args[1] = [list(range(args[1] * 2))] * len(f)
elif m is Contract:
c2 = ch[f] * args[0] ** 2
elif m is Expand:
c2 = ch[f] // args[0] ** 2
else:
c2 = ch[f]
m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module 判断n是否>1, 如果n>1, 会根据n的数量去初始化这一层有多少n的模块，例如有n=3的C3模块，n>1,此时这一层就要有3个C3模块
t = str(m)[8:-2].replace('__main__.', '') # module type #判断模块名有没有__main__名字，如果有就用空替换掉
np = sum(x.numel() for x in m_.parameters()) # number params 统计参数量
m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f} {t:<40}{str(args):<30}') # print 打印输出信息
save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist 统计需要保存的层
layers.append(m_)
if i == 0:# 第0层会把ch重置为0
ch = []
#把通道数添加到ch里面，后面层会取出上一层的输出通道，作为输入通道
ch.append(c2) # [32],[32,64],[32,64,64]
#所有层都执行完毕，会返回整个网络结构以及需要保存特征的层
return nn.Sequential(*layers), sorted(save) # 需要保存的层号[6, 4, 14, 10, 17, 20, 23] -> [4, 6, 10, 14, 17, 20, 23]3、第三部分，对网络步长和anchors进行处理
m = self.model[-1] # 取出网络的最后一层 Detect()
if isinstance(m, Detect):
s = 256 # 2x min stride
m.inplace = self.inplace
"""
通过输入图片的尺寸和预测图片的尺寸得到
torch.zeros(1, ch, s, s)：新建一个空白的图片，图片大小是(1*3*256*256),
把图片传入整个模型中，进行一次前向传播, 传播过程中，会在低层、中层和高层进行三次预测
低层：第四层，通过前向传播输出为32*32大小的图片-->s=256/32=8, 缩放了8倍
同理,256/16得到中间步长为16,256/8得到步长为32
所以:
m.stride = forward：[8,16,32]
"""
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward：[8,16,32]
check_anchor_order(m) # must be in pixel-space (not grid-space)检测ancohrs顺序对不对
m.anchors /= m.stride.view(-1, 1, 1) #定义的anchors是原始图片上的，最终在特征层使用，所以需要anchors除以相同倍数
self.stride = m.stride
self._initialize_biases() # only run once4、第四部分，网络的初始化及效果打印
initialize_weights(self)
self.info()
LOGGER.info('')
1053
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
