2
5
=
32
2^{5} =32
25=32;最后对该数值除以2,即将填充的区域分散到两边。这样将416*416大小的图片缩小到416*320大小,因而极大的提升了算法的推理速度。**
需要注意的是:(1)该操作仅在模型推理阶段执行,模型训练阶段仍然和传统的方法相同,将原始图片裁剪到416*416大小;(2)YOLOv3与YOLOv4中默认填充的数值是(0,0,0),而YOLOv5中默认填充的数值是(114,114,114);(3)该操作仅仅针对原始图片的短边而言,仍然将长边裁剪到416。
3.2.3 基准网络细节详解
- Focus结构-该结构的主要思想是通过slice操作来对输入图片进行裁剪。如下图所示,原始输入图片大小为608*608*3,经过Slice与Concat操作之后输出一个304*304*12的特征映射;接着经过一个通道个数为32的Conv层(该通道个数仅仅针对的是YOLOv5s结构,其它结构会有相应的变化),输出一个304*304*32大小的特征映射。
- CSP结构-YOLOv4网络结构中,借鉴了CSPNet的设计思路,仅仅在主干网络中设计了CSP结构。而YOLOv5中设计了两种CSP结构,以YOLOv5s网络为例,CSP1_X结构应用于Backbone主干网络中,另一种CSP2_X结构则应用于Neck网络中。CSP1_X与CSP2_X模块的实现细节如3.1所示。
3.2.4 Neck网络细节详解
- FPN+PAN-YOLOv5的Neck网络仍然使用了FPN+PAN结构,但是在它的基础上做了一些改进操作,YOLOv4的Neck结构中,采用的都是普通的卷积操作。而YOLOv5的Neck网络中,采用借鉴CSPnet设计的CSP2结构,从而加强网络特征融合能力。下图展示了YOLOv4与YOLOv5的Neck网络的具体细节,通过比较我们可以发现:(1)灰色区域表示第1个不同点,YOLOv5不仅利用CSP2_\1结构代替部分CBL模块,而且去掉了下方的CBL模块;(2)绿色区域表示第2个不同点,YOLOv5不仅将Concat操作之后的CBL模块更换为CSP2_1模块,而且更换了另外一个CBL模块的位置;(3)蓝色区域表示第3个不同点,YOLOv5中将原始的CBL模块更换为CSP2_1模块。
3.2.5 Head输出端细节详解
- GIoU_Loss-YOLOv5中采用GIoU_Loss做Bounding box的损失函数,更多的细节请参考这篇博客。
4、YOLOv5网络代码实现
# 检测类
class Detect(nn.Module):
stride = None # strides computed during build
export = False # onnx export
def \_\_init\_\_(self, nc=80, anchors=(), ch=()): # detection layer
super(Detect, self).__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
a = torch.tensor(anchors).float().view(self.nl, -1, 2)
self.register_buffer('anchors', a) # shape(nl,na,2)
self.register_buffer('anchor\_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2)) # shape(nl,1,na,1,1,2)
self.m = nn.ModuleList(nn.Conv2d(x, self.no \* self.na, 1) for x in ch) # output conv
def forward(self, x):
# x = x.copy() # for profiling
z = [] # inference output
self.training |= self.export
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.grid[i].shape[2:4] != x[i].shape[2:4]:
self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
y = x[i].sigmoid()
y[..., 0:2] = (y[..., 0:2] \* 2. - 0.5 + self.grid[i].to(x[i].device)) \* self.stride[i] # xy
y[..., 2:4] = (y[..., 2:4] \* 2) \*\* 2 \* self.anchor_grid[i] # wh
z.append(y.view(bs, -1, self.no))
return x if self.training else (torch.cat(z, 1), x)
@staticmethod
def \_make\_grid(nx=20, ny=20):
yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
# 根据配置的.yaml文件搭建模型
class Model(nn.Module):
def \_\_init\_\_(self, cfg='yolov5s.yaml', ch=3, nc=None): # model, input channels, number of classes
super(Model, self).__init__()
if isinstance(cfg, dict):
self.yaml = cfg # model dict
else: # is \*.yaml
import yaml # for torch hub
self.yaml_file = Path(cfg).name
with open(cfg) as f:
self.yaml = yaml.load(f, Loader=yaml.SafeLoader) # model dict
# Define model
ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
if nc and nc != self.yaml['nc']:
logger.info('Overriding model.yaml nc=%g with nc=%g' % (self.yaml['nc'], nc))
self.yaml['nc'] = nc # override yaml value
self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
self.names = [str(i) for i in range(self.yaml['nc'])] # default names
# print([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
# Build strides, anchors
m = self.model[-1] # Detect()
if isinstance(m, Detect):
s = 256 # 2x min stride
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
m.anchors /= m.stride.view(-1, 1, 1)
check_anchor_order(m)
self.stride = m.stride
self._initialize_biases() # only run once
# print('Strides: %s' % m.stride.tolist())
# Init weights, biases
initialize_weights(self)
self.info()
logger.info('')
def forward(self, x, augment=False, profile=False):
if augment:
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[..., :4] /= si # de-scale
if fi == 2:
yi[..., 1] = img_size[0] - yi[..., 1] # de-flip ud
elif fi == 3:
yi[..., 0] = img_size[1] - yi[..., 0] # de-flip lr
y.append(yi)
return torch.cat(y, 1), None # augmented inference, train
else:
return self.forward_once(x, profile) # single-scale inference, train
def forward\_once(self, x, profile=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:
o = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 \* 2 if thop else 0 # FLOPS
t = time_synchronized()
for _ in range(10):
_ = m(x)
dt.append((time_synchronized() - t) \* 100)
print('%10.1f%10.0f%10.1fms %-40s' % (o, m.np, dt[-1], m.type))
x = m(x) # run
y.append(x if m.i in self.save else None) # save output
if profile:
print('%.1fms total' % sum(dt))
return x
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 - 0.99)) 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)
print(('%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:
# print('%10.3g' % (m.w.detach().sigmoid() \* 2)) # shortcut weights
def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers
print('Fusing layers... ')
for m in self.model.modules():
if type(m) is Conv and hasattr(m, 'bn'):
m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv
delattr(m, 'bn') # remove batchnorm
m.forward = m.fuseforward # update forward
self.info()
return self
def nms(self, mode=True): # add or remove NMS module
present = type(self.model[-1]) is NMS # last layer is NMS
if mode and not present:
print('Adding NMS... ')
m = NMS() # module
m.f = -1 # from
m.i = self.model[-1].i + 1 # index
self.model.add_module(name='%s' % m.i, module=m) # add
self.eval()
elif not mode and present:
print('Removing NMS... ')
self.model = self.model[:-1] # remove
return self
def autoshape(self): # add autoShape module
print('Adding autoShape... ')
m = autoShape(self) # wrap model
copy_attr(m, self, include=('yaml', 'nc', 'hyp', 'names', 'stride'), exclude=()) # copy attributes
return m
def info(self, verbose=False, img_size=640): # print model information
model_info(self, verbose, img_size)
# 解析模型
def parse\_model(d, ch): # model\_dict, input\_
**作者徽是vip1024c**
channels(3)
logger.info('\n%3s%18s%3s%10s %-40s%-30s' % ('', 'from', 'n', 'params', '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 # number of anchors
no = na \* (nc + 5) # number of outputs = anchors \* (classes + 5)
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args
m = eval(m) if isinstance(m, str) else m # eval strings
for j, a in enumerate(args):
try:
args[j] = eval(a) if isinstance(a, str) else a # eval strings
except:
pass
n = max(round(n \* gd), 1) if n > 1 else n # depth gain
if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP,
C3]:
c1, c2 = ch[f], args[0]
# Normal
# if i > 0 and args[0] != no: # channel expansion factor
# ex = 1.75 # exponential (default 2.0)
# e = math.log(c2 / ch[1]) / math.log(2)
# c2 = int(ch[1] \* ex \*\* e)
# if m != Focus:
c2 = make_divisible(c2 \* gw, 8) if c2 != no else c2
# Experimental
# if i > 0 and args[0] != no: # channel expansion factor
# ex = 1 + gw # exponential (default 2.0)
# ch1 = 32 # ch[1]
# e = math.log(c2 / ch1) / math.log(2) # level 1-n
# c2 = int(ch1 \* ex \*\* e)
# if m != Focus:
# c2 = make\_divisible(c2, 8) if c2 != no else c2
args = [c1, c2, \*args[1:]]
if m in [BottleneckCSP, C3]:
args.insert(2, n)
n = 1
elif m is nn.BatchNorm2d:
args = [ch[f]]
elif m is Concat:
c2 = sum([ch[x if x < 0 else x + 1] for x in f])
elif m is Detect:
## 写在最后
**在结束之际,我想重申的是,学习并非如攀登险峻高峰,而是如滴水穿石般的持久累积。尤其当我们步入工作岗位之后,持之以恒的学习变得愈发不易,如同在茫茫大海中独自划舟,稍有松懈便可能被巨浪吞噬。然而,对于我们程序员而言,学习是生存之本,是我们在激烈市场竞争中立于不败之地的关键。一旦停止学习,我们便如同逆水行舟,不进则退,终将被时代的洪流所淘汰。因此,不断汲取新知识,不仅是对自己的提升,更是对自己的一份珍贵投资。让我们不断磨砺自己,与时代共同进步,书写属于我们的辉煌篇章。**
需要完整版PDF学习资源私我