0 前言

🔥 優(yōu)質(zhì)競賽項目系列，今天要分享的是

🚩 基于深度學(xué)習(xí)的中國交通標志識別算法研究與實現(xiàn)

該項目較為新穎，適合作為競賽課題方向，學(xué)長非常推薦！

🥇學(xué)長這里給一個題目綜合評分(每項滿分5分)

• 難度系數(shù)：4分
• 工作量：4分
• 創(chuàng)新點：3分

🧿 更多資料, 項目分享：

https://gitee.com/dancheng-senior/postgraduate

1 yolov5實現(xiàn)中國交通標志檢測

整個互聯(lián)網(wǎng)基本沒有國內(nèi)交通標志識別的開源項目(都是國外的)，今天學(xué)長分享一個中國版本的實時交通標志識別項目，非常適合作為競賽項目~

2.算法原理

2.1 算法簡介

YOLOv5是一種單階段目標檢測算法，該算法在YOLOv4的基礎(chǔ)上添加了一些新的改進思路，使其速度與精度都得到了極大的性能提升。主要的改進思路如下所示：

輸入端：在模型訓(xùn)練階段，提出了一些改進思路，主要包括Mosaic數(shù)據(jù)增強、自適應(yīng)錨框計算、自適應(yīng)圖片縮放；
基準網(wǎng)絡(luò)：融合其它檢測算法中的一些新思路，主要包括：Focus結(jié)構(gòu)與CSP結(jié)構(gòu)；
Neck網(wǎng)絡(luò)：目標檢測網(wǎng)絡(luò)在BackBone與最后的Head輸出層之間往往會插入一些層，Yolov5中添加了FPN+PAN結(jié)構(gòu)；
Head輸出層：輸出層的錨框機制與YOLOv4相同，主要改進的是訓(xùn)練時的損失函數(shù)GIOU_Loss，以及預(yù)測框篩選的DIOU_nms。

2.2網(wǎng)絡(luò)架構(gòu)

上圖展示了YOLOv5目標檢測算法的整體框圖。對于一個目標檢測算法而言，我們通常可以將其劃分為4個通用的模塊，具體包括：輸入端、基準網(wǎng)絡(luò)、Neck網(wǎng)絡(luò)與Head輸出端，對應(yīng)于上圖中的4個紅色模塊。YOLOv5算法具有4個版本，具體包括：YOLOv5s、YOLOv5m、YOLOv5l、YOLOv5x四種，本文重點講解YOLOv5s，其它的版本都在該版本的基礎(chǔ)上對網(wǎng)絡(luò)進行加深與加寬。

• 輸入端-輸入端表示輸入的圖片。該網(wǎng)絡(luò)的輸入圖像大小為608*608，該階段通常包含一個圖像預(yù)處理階段，即將輸入圖像縮放到網(wǎng)絡(luò)的輸入大小，并進行歸一化等操作。在網(wǎng)絡(luò)訓(xùn)練階段，YOLOv5使用Mosaic數(shù)據(jù)增強操作提升模型的訓(xùn)練速度和網(wǎng)絡(luò)的精度；并提出了一種自適應(yīng)錨框計算與自適應(yīng)圖片縮放方法。
• 基準網(wǎng)絡(luò)-基準網(wǎng)絡(luò)通常是一些性能優(yōu)異的分類器種的網(wǎng)絡(luò)，該模塊用來提取一些通用的特征表示。YOLOv5中不僅使用了CSPDarknet53結(jié)構(gòu)，而且使用了Focus結(jié)構(gòu)作為基準網(wǎng)絡(luò)。
• Neck網(wǎng)絡(luò)-Neck網(wǎng)絡(luò)通常位于基準網(wǎng)絡(luò)和頭網(wǎng)絡(luò)的中間位置，利用它可以進一步提升特征的多樣性及魯棒性。雖然YOLOv5同樣用到了SPP模塊、FPN+PAN模塊，但是實現(xiàn)的細節(jié)有些不同。
• Head輸出端-Head用來完成目標檢測結(jié)果的輸出。針對不同的檢測算法，輸出端的分支個數(shù)不盡相同，通常包含一個分類分支和一個回歸分支。YOLOv4利用GIOU_Loss來代替Smooth L1 Loss函數(shù)，從而進一步提升算法的檢測精度。

2.3 關(guān)鍵代碼

?

class Detect(nn.Module):stride = None  # strides computed during buildonnx_dynamic = False  # ONNX export parameterdef __init__(self, nc=80, anchors=(), ch=(), inplace=True):  # detection layersuper().__init__()self.nc = nc  # number of classesself.no = nc + 5  # number of outputs per anchorself.nl = len(anchors)  # number of detection layersself.na = len(anchors[0]) // 2  # number of anchorsself.grid = [torch.zeros(1)] * self.nl  # init gridself.anchor_grid = [torch.zeros(1)] * self.nl  # init anchor gridself.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 convself.inplace = inplace  # use in-place ops (e.g. slice assignment)def forward(self, x):z = []  # inference outputfor i in range(self.nl):x[i] = self.m[i](x[i])  # convbs, _, 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:  # inferenceif 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 - 0.5 + self.grid[i]) * self.stride[i]  # xyy[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # whelse:  # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953xy = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i]  # xywh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # why = torch.cat((xy, wh, y[..., 4:]), -1)z.append(y.view(bs, -1, self.no))return x if self.training else (torch.cat(z, 1), x)def _make_grid(self, nx=20, ny=20, i=0):d = self.anchors[i].deviceif check_version(torch.__version__, '1.10.0'):  # torch>=1.10.0 meshgrid workaround for torch>=0.7 compatibilityyv, xv = torch.meshgrid([torch.arange(ny).to(d), torch.arange(nx).to(d)], indexing='ij')else:yv, xv = torch.meshgrid([torch.arange(ny).to(d), torch.arange(nx).to(d)])grid = torch.stack((xv, yv), 2).expand((1, self.na, ny, nx, 2)).float()anchor_grid = (self.anchors[i].clone() * self.stride[i]) \.view((1, self.na, 1, 1, 2)).expand((1, self.na, ny, nx, 2)).float()return grid, anchor_gridclass Model(nn.Module):def __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 yaml  # for torch hubself.yaml_file = Path(cfg).namewith open(cfg, encoding='ascii', errors='ignore') as f:self.yaml = yaml.safe_load(f)  # model dict# 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 valueself.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])  # model, savelistself.names = [str(i) for i in range(self.yaml['nc'])]  # default namesself.inplace = self.yaml.get('inplace', True)# Build strides, anchorsm = 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))])  # forwardm.anchors /= m.stride.view(-1, 1, 1)check_anchor_order(m)self.stride = m.strideself._initialize_biases()  # only run once# Init weights, biasesinitialize_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, Nonereturn self._forward_once(x, profile, visualize)  # single-scale inference, traindef _forward_augment(self, x):img_size = x.shape[-2:]  # height, widths = [1, 0.83, 0.67]  # scalesf = [None, 3, None]  # flips (2-ud, 3-lr)y = []  # outputsfor 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])  # saveyi = self._descale_pred(yi, fi, si, img_size)y.append(yi)y = self._clip_augmented(y)  # clip augmented tailsreturn torch.cat(y, 1), None  # augmented inference, traindef _forward_once(self, x, profile=False, visualize=False):y, dt = [], []  # outputsfor m in self.model:if m.f != -1:  # if not from previous layerx = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layersif profile:self._profile_one_layer(m, x, dt)x = m(x)  # runy.append(x if m.i in self.save else None)  # save outputif visualize:feature_visualization(x, m.type, m.i, save_dir=visualize)return xdef _descale_pred(self, p, flips, scale, img_size):# de-scale predictions following augmented inference (inverse operation)if self.inplace:p[..., :4] /= scale  # de-scaleif flips == 2:p[..., 1] = img_size[0] - p[..., 1]  # de-flip udelif flips == 3:p[..., 0] = img_size[1] - p[..., 0]  # de-flip lrelse:x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale  # de-scaleif flips == 2:y = img_size[0] - y  # de-flip udelif flips == 3:x = img_size[1] - x  # de-flip lrp = torch.cat((x, y, wh, p[..., 4:]), -1)return pdef _clip_augmented(self, y):# Clip YOLOv5 augmented inference tailsnl = self.model[-1].nl  # number of detection layers (P3-P5)g = sum(4 ** x for x in range(nl))  # grid pointse = 1  # exclude layer counti = (y[0].shape[1] // g) * sum(4 ** x for x in range(e))  # indicesy[0] = y[0][:, :-i]  # largei = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e))  # indicesy[-1] = y[-1][:, i:]  # smallreturn ydef _profile_one_layer(self, m, x, dt):c = isinstance(m, Detect)  # is final layer, copy input as inplace fixo = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0  # FLOPst = 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() modulefor mi, s in zip(m.m, m.stride):  # fromb = 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())  # clsmi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)def _print_biases(self):m = self.model[-1]  # Detect() modulefor mi in m.m:  # fromb = 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 weightsdef fuse(self):  # fuse model Conv2d() + BatchNorm2d() layersLOGGER.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 convdelattr(m, 'bn')  # remove batchnormm.forward = m.forward_fuse  # update forwardself.info()return selfdef autoshape(self):  # add AutoShape moduleLOGGER.info('Adding AutoShape... ')m = AutoShape(self)  # wrap modelcopy_attr(m, self, include=('yaml', 'nc', 'hyp', 'names', 'stride'), exclude=())  # copy attributesreturn mdef info(self, verbose=False, img_size=640):  # print model informationmodel_info(self, verbose, img_size)def _apply(self, fn):# Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffersself = 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 selfdef 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, save, c2 = [], [], ch[-1]  # layers, savelist, ch outfor i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, argsm = eval(m) if isinstance(m, str) else m  # eval stringsfor j, a in enumerate(args):try:args[j] = eval(a) if isinstance(a, str) else a  # eval stringsexcept NameError:passn = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gainif 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:  # if not outputc2 = make_divisible(c2 * gw, 8)args = [c1, c2, *args[1:]]if m in [BottleneckCSP, C3, C3TR, C3Ghost]: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)

3 數(shù)據(jù)集處理

中國交通標志檢測數(shù)據(jù)集CCTSDB，由長沙理工大學(xué)提供，包括上萬張有標注的圖片

推薦只使用前4000張照片，因為后面有很多張圖片沒有標注，需要一張一張的刪除，太過于麻煩，所以盡量用前4000張圖

3.1 VOC格式介紹

VOC格式主要包含三個文件夾Annotations，ImageSets，JPEGImages，主要適用于faster-
rcnn等模型的訓(xùn)練，ImageSets下面有一個Main的文件夾，如下圖，一定按照這個名字和格式建好文件夾：

• Annotations：這里是存放你對所有數(shù)據(jù)圖片做的標注，每張照片的標注信息必須是xml格式。

• JPEGImages：用來保存你的數(shù)據(jù)圖片，一定要對圖片進行編號，一般按照voc數(shù)據(jù)集格式，采用六位數(shù)字編碼，如000001.jpg、000002.jpg等。

• ImageSets：該文件下有一個main文件，main文件下有四個txt文件，分別是train.txt、test.txt、trainval.txt、val.txt，里面都是存放的圖片號碼。

3.2 將中國交通標志檢測數(shù)據(jù)集CCTSDB數(shù)據(jù)轉(zhuǎn)換成VOC數(shù)據(jù)格式

將標注的數(shù)據(jù)提取出來并且排序，并將里面每一行分割成一個文件

3.3 手動標注數(shù)據(jù)集

如果為了更深入的學(xué)習(xí)也可自己標注，但過程相對比較繁瑣，麻煩。

以下簡單介紹數(shù)據(jù)標注的相關(guān)方法，數(shù)據(jù)標注這里推薦的軟件是labelimg，通過pip指令即可安裝，相關(guān)教程可網(wǎng)上搜索

?
pip install labelimg

4 模型訓(xùn)練

修改train.py中的weights、cfg、data、epochs、batch_size、imgsz、device、workers等參數(shù)

訓(xùn)練代碼成功執(zhí)行之后會在命令行中輸出下列信息，接下來就是安心等待模型訓(xùn)練結(jié)束即可。

5 實現(xiàn)效果

5.1 視頻效果

6 最后

🧿 更多資料, 項目分享：

https://gitee.com/dancheng-senior/postgraduate