- Yolov5s的网络结构
1.1 yaml文件解读
Yolov5中,网络模型的配置放在yaml文件中,而yolov5s放置在models/yolov5s.yaml文件中
参考视频:
bilibili
yolov5s.yaml文件内容如下:
nc: 80
depth_multiple: 0.33
width_multiple: 0.50
anchors:
- [10,13, 16,30, 33,23]
- [30,61, 62,45, 59,119]
- [116,90, 156,198, 373,326]
backbone:
[[-1, 1, Conv, [64, 6, 2, 2]],
[-1, 1, Conv, [128, 3, 2]],
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]],
[-1, 6, C3, [256]],
[-1, 1, Conv, [512, 3, 2]],
[-1, 9, C3, [512]],
[-1, 1, Conv, [1024, 3, 2]],
[-1, 3, C3, [1024]],
[-1, 1, SPPF, [1024, 5]],
]
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]],
[-1, 3, C3, [512, False]],
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]],
[-1, 3, C3, [256, False]],
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]],
[-1, 3, C3, [512, False]],
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]],
[-1, 3, C3, [1024, False]],
[[17, 20, 23], 1, Detect, [nc, anchors]],
]
其中一层网络的参数是用列表实现的,比如：
[-1, 1, Conv, [64, 6, 2, 2]]
四个参数的含义分别是：
-1: 输入来自上一层,如果是正数i则代表第i层
1：使用一个网络模块
Conv: 该层的网络层名字是Conv
[64, 6, 2, 2]： Conv层的四个参数
yaml文件可以被yaml库解析为字典对象
1.2 yolov5s网络结构解读
对应的结构图如下:
图片来源: 文首视频链接
网络中使用了特征融合, 第4、6、9层的特征均被连接到Concat层进行检测，特征融合的意义在于第4、6、9层的抽象度不同，第四层更容易检测小目标，第9层更容易检测大目标。
; 2. yolo.py 解读
文件地址：
这一部分具体解读是如何构建网络模块的
2.1 class Model 92~250行
2.1.1 init 94~130行
def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None):
super().__init__()
if isinstance(cfg, dict):
self.yaml = cfg
else:
import yaml
self.yaml_file = Path(cfg).name
with open(cfg, encoding='ascii', errors='ignore') as f:
self.yaml = yaml.safe_load(f)
ch = self.yaml['ch'] = self.yaml.get('ch', ch)
if nc and nc != self.yaml['nc']:
LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
self.yaml['nc'] = nc
if anchors:
LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
self.yaml['anchors'] = round(anchors)
self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])
self.names = [str(i) for i in range(self.yaml['nc'])]
self.inplace = self.yaml.get('inplace', True)
m = self.model[-1]
if isinstance(m, Detect):
s = 256
m.inplace = self.inplace
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])
check_anchor_order(m)
m.anchors /= m.stride.view(-1, 1, 1)
self.stride = m.stride
self._initialize_biases()
initialize_weights(self)
self.info()
LOGGER.info('')
2.2 parse_model方法 243~295行
def parse_model(d, ch):
LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}{'module':}{'arguments':}")
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors
no = na * (nc + 5)
layers, save, c2 = [], [], ch[-1]
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):
m = eval(m) if isinstance(m, str) else m
for j, a in enumerate(args):
try:
args[j] = eval(a) if isinstance(a, str) else a
except NameError:
pass
n = n_ = max(round(n * gd), 1) if n > 1 else n
if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3, C3TR, C3SPP, C3Ghost]:
c1, c2 = ch[f], args[0]
if c2 != no:
c2 = make_divisible(c2 * gw, 8)
args = [c1, c2, *args[1:]]
if m in [BottleneckCSP, C3, C3TR, C3Ghost]:
args.insert(2, n)
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):
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)
t = str(m)[8:-2].replace('__main__.', '')
np = sum(x.numel() for x in m_.parameters())
m_.i, m_.f, m_.type, m_.np = i, f, t, np
LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f}{t:}{str(args):}')
save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)
layers.append(m_)
if i == 0:
ch = []
ch.append(c2)
return nn.Sequential(*layers), sorted(save)
Original: https://blog.csdn.net/weixin_46183779/article/details/125832454
Author: supermax2020
Title: YOLOv5 最详细的源码逐行解读(二: 网络结构)
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/718315/
转载文章受原作者版权保护。转载请注明原作者出处！