企业网站建设内容报价,将自己做的网站发布到,网站seo报价,济宁哪里有网站建设代码基于yolov5 v6.0 目录#xff1a;
yolo源码注释1——文件结构yolo源码注释2——数据集配置文件yolo源码注释3——模型配置文件yolo源码注释4——yolo-py
yolo.py 用于搭建 yolov5 的网络模型#xff0c;主要包含 3 部分#xff1a;
Detect#xff1a;Detect 层Model… 代码基于yolov5 v6.0 目录
yolo源码注释1——文件结构yolo源码注释2——数据集配置文件yolo源码注释3——模型配置文件yolo源码注释4——yolo-py
yolo.py 用于搭建 yolov5 的网络模型主要包含 3 部分
DetectDetect 层Model搭建网络parse_model根据配置实例化模块
Model仅注释了 init 函数
class Model(nn.Module):# YOLOv5 modeldef __init__(self, cfgyolov5s.yaml, ch3, ncNone, anchorsNone): # model, input channels, number of classessuper().__init__()if isinstance(cfg, dict):self.yaml cfg # model dictelse: # is *.yamlimport yamlself.yaml_file Path(cfg).namewith open(cfg, encodingascii, errorsignore) as f:self.yaml yaml.safe_load(f)# Define modelch self.yaml[ch] self.yaml.get(ch, ch) # input channelsif nc and nc ! self.yaml[nc]:LOGGER.info(fOverriding model.yaml nc{self.yaml[nc]} with nc{nc})self.yaml[nc] nc # override yaml valueif anchors:LOGGER.info(fOverriding model.yaml anchors with anchors{anchors})self.yaml[anchors] round(anchors) # override yaml value# 根据配置搭建网络self.model, self.save parse_model(deepcopy(self.yaml), ch[ch])self.names [str(i) for i in range(self.yaml[nc])] # default namesself.inplace self.yaml.get(inplace, True)# 计算生成 anchors 时的步长m self.model[-1] # Detect()if isinstance(m, Detect):s 256 # 2x min stridem.inplace self.inplacem.stride torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forwardcheck_anchor_order(m) # must be in pixel-space (not grid-space)m.anchors / m.stride.view(-1, 1, 1)self.stride m.strideself._initialize_biases() # only run once# Init weights, biasesinitialize_weights(self)self.info()LOGGER.info()parse_model
def parse_model(d, ch): # model_dict, input_channels(3)LOGGER.info(f\n{:3}{from:18}{n:3}{params:10} {module:40}{arguments:30})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 anchorsno na * (nc 5) # number of outputs anchors * (classes 5)# layers 保存每一层的结构# save 记录 from 不是 -1 的层即需要多个输入的层如 Concat 和 Detect 层# c2: 当前层输出的特征图数量layers, save, c2 [], [], ch[-1] # layers, savelist, ch outfor i, (f, n, m, args) in enumerate(d[backbone] d[head]): # from:-1, number:1, module:Conv, args:[64, 6, 2, 2]m eval(m) if isinstance(m, str) else m # eval strings, m:class models.common.Conv# 数字、列表直接放入args[i]字符串通过 eval 函数变成模块for j, a in enumerate(args):try:args[j] eval(a) if isinstance(a, str) else a # eval strings, [64, 6, 2, 2]except NameError:pass# 对数量大于1的模块和 depth_multiple 相乘然后四舍五入n n_ max(round(n * gd), 1) if n 1 else n # depth gain# 实例化 ymal 文件中的每个模块if m in (Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,BottleneckCSP, C3, C3TR, C3SPP, C3Ghost,SE, FSM):c1, c2 ch[f], args[0] # 输入特征图数量f指向的层的输出特征图数量输出特征图数量# 如果输出层的特征图数量不等于 no (Detect输出层)# 则将输出图的特征图数量乘 width_multiple 并调整为 8 的倍数if c2 ! no: # if not outputc2 make_divisible(c2 * gw, 8)args [c1, c2, *args[1:]] # 默认参数格式[输入 输出 其他参数……]# 参数有特殊格式要求的模块if m in [BottleneckCSP, C3, C3TR, C3Ghost, CSPStage]:args.insert(2, n) # number of repeatsn 1elif 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 anchorsargs[1] [list(range(args[1] * 2))] * len(f)elif m is Contract:c2 ch[f] * args[0] ** 2elif m is Expand:c2 ch[f] // args[0] ** 2else:c2 ch[f]m_ nn.Sequential(*(m(*args) for _ in range(n))) if n 1 else m(*args) # modulet str(m)[8:-2].replace(__main__., ) # module typenp sum(x.numel() for x in m_.parameters()) # number paramsm_.i, m_.f, m_.type, m_.np i, f, t, np # attach index, from index, type, number paramsLOGGER.info(f{i:3}{str(f):18}{n_:3}{np:10.0f} {t:40}{str(args):30}) # printsave.extend(x % i for x in ([f] if isinstance(f, int) else f) if x ! -1) # append to savelistlayers.append(m_)if i 0:ch []ch.append(c2)return nn.Sequential(*layers), sorted(save)
