代碼基于yolov5 v6.0

目錄：

• yolo源碼注釋1——文件結構
• yolo源碼注釋2——數(shù)據(jù)集配置文件
• yolo源碼注釋3——模型配置文件
• yolo源碼注釋4——yolo-py

yolo.py 用于搭建 yolov5 的網(wǎng)絡模型，主要包含 3 部分：

• Detect：Detect 層
• Model：搭建網(wǎng)絡
• parse_model：根據(jù)配置實例化模塊

Model（僅注釋了 init 函數(shù)）：

class Model(nn.Module):# YOLOv5 modeldef __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None):  # 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, encoding='ascii', errors='ignore') 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(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")self.yaml['nc'] = nc  # override yaml valueif anchors:LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')self.yaml['anchors'] = round(anchors)  # override yaml value# 根據(jù)配置搭建網(wǎng)絡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)# 計算生成 anchors 時的步長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： 保存每一層的結構# save： 記錄 from 不是 -1 的層，即需要多個輸入的層如 Concat 和 Detect 層# c2: 當前層輸出的特征圖數(shù)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'># 數(shù)字、列表直接放入args[i]，字符串通過 eval 函數(shù)變成模塊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# 對數(shù)量大于1的模塊和 depth_multiple 相乘然后四舍五入n = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gain# 實例化 ymal 文件中的每個模塊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]  # 輸入特征圖數(shù)量（f指向的層的輸出特征圖數(shù)量），輸出特征圖數(shù)量# 如果輸出層的特征圖數(shù)量不等于 no (Detect輸出層)# 則將輸出圖的特征圖數(shù)量乘 width_multiple ，并調整為 8 的倍數(shù)if c2 != no:  # if not outputc2 = make_divisible(c2 * gw, 8)args = [c1, c2, *args[1:]]  # 默認參數(shù)格式：[輸入， 輸出， 其他參數(shù)……]# 參數(shù)有特殊格式要求的模塊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)