yolov7实战

def parse_model(d, ch):  # model_dict, input_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 [nn.Conv2d, Conv, RobustConv, RobustConv2, DWConv, GhostConv, RepConv, RepConv_OREPA, DownC, 
                 SPP, SPPF, SPPCSPC, GhostSPPCSPC, MixConv2d, Focus, Stem, GhostStem, CrossConv, 
                 Bottleneck, BottleneckCSPA, BottleneckCSPB, BottleneckCSPC, 
                 RepBottleneck, RepBottleneckCSPA, RepBottleneckCSPB, RepBottleneckCSPC,  
                 Res, ResCSPA, ResCSPB, ResCSPC, 
                 RepRes, RepResCSPA, RepResCSPB, RepResCSPC, 
                 ResX, ResXCSPA, ResXCSPB, ResXCSPC, 
                 RepResX, RepResXCSPA, RepResXCSPB, RepResXCSPC, 
                 Ghost, GhostCSPA, GhostCSPB, GhostCSPC,
                 SwinTransformerBlock, STCSPA, STCSPB, STCSPC,
                 SwinTransformer2Block, ST2CSPA, ST2CSPB, ST2CSPC]:
            c1, c2 = ch[f], args[0]
            if c2 != no:  # if not output
                c2 = make_divisible(c2 * gw, 8)

            args = [c1, c2, *args[1:]]
            if m in [DownC, SPPCSPC, GhostSPPCSPC, 
                     BottleneckCSPA, BottleneckCSPB, BottleneckCSPC, 
                     RepBottleneckCSPA, RepBottleneckCSPB, RepBottleneckCSPC, 
                     ResCSPA, ResCSPB, ResCSPC, 
                     RepResCSPA, RepResCSPB, RepResCSPC, 
                     ResXCSPA, ResXCSPB, ResXCSPC, 
                     RepResXCSPA, RepResXCSPB, RepResXCSPC,
                     GhostCSPA, GhostCSPB, GhostCSPC,
                     STCSPA, STCSPB, STCSPC,
                     ST2CSPA, ST2CSPB, ST2CSPC]:
                args.insert(2, n)  # number of repeats
                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 Chuncat:
            c2 = sum([ch[x] for x in f])
        elif m is Shortcut:
            c2 = ch[f[0]]
        elif m is Foldcut:
            c2 = ch[f] // 2
        elif m in [Detect, IDetect, IAuxDetect, IBin]:
            args.append([ch[x] for x in f])
            if isinstance(args[1], int):  # number of anchors
                args[1] = [list(range(args[1] * 2))] * len(f)
        elif m is ReOrg:
            c2 = ch[f] * 4
        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)  # module
        t = str(m)[8:-2].replace('__main__.', '')  # module type
        np = sum([x.numel() for x in m_.parameters()])  # number params
        m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
        logger.info('%3s%18s%3s%10.0f  %-40s%-30s' % (i, f, n, np, t, args))  # print
        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
        layers.append(m_)
        if i == 0:
            ch = []
        ch.append(c2)
    return nn.Sequential(*layers), sorted(save)

    def forward_once(self, x, profile=False):
        y, dt = [], []  # outputs
        for m in self.model:#按配置文件的每一层网络进行叠加
            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 not hasattr(self, 'traced'):
                self.traced=False

            if self.traced:
                if isinstance(m, Detect) or isinstance(m, IDetect) or isinstance(m, IAuxDetect):
                    break

            if profile:
                c = isinstance(m, (Detect, IDetect, IAuxDetect, IBin))
                o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0  # FLOPS
                for _ in range(10):
                    m(x.copy() if c else x)
                t = time_synchronized()
                for _ in range(10):
                    m(x.copy() if c else 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 find_3_positive(self, p, targets):
        # Build targets for compute_loss(), input targets(image,class,x,y,w,h)
        na, nt = self.na, targets.shape[0]  # number of anchors=3, targets
        indices, anch = [], []
        gain = torch.ones(7, device=targets.device).long()  # 7表示源标签6个+框ID（属于哪个大小的anchor）normalized to gridspace gain
        ai = torch.arange(na, device=targets.device).float().view(na, 1).repeat(1, nt)  #每个点对应的anchors，三种都有可能， same as .repeat_interleave(nt)
        targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2)  # 最后加了一个维度表示anchor的ID append anchor indices

        g = 0.5  # bias 一会玩漂移，上下左右偏移0.5单位得到更多的正样本
        off = torch.tensor([[0, 0],#本身
                            [1, 0], [0, 1], [-1, 0], [0, -1],  # 右方、上、左、下 j,k,l,m
                            # [1, 1], [1, -1], [-1, 1], [-1, -1],  # jk,jm,lk,lm
                            ], device=targets.device).float() * g  # 数值乘以方向表示沿该方向偏移多少，offsets

        for i in range(self.nl):#有3个输出层，分别做
            anchors = self.anchors[i]#当前输出层对应的anchor
            gain[2:6] = torch.tensor(p[i].shape)[[3, 2, 3, 2]]  #赋值，一会用  xyxy gain

            # Match targets to anchors这块在遍历看看这些GT到底放在哪个输出层合适
            t = targets * gain#归一化的标签映射到特征图上
            if nt:
                # Matches
                r = t[:, :, 4:6] / anchors[:, None]  # 每一个GT与anchor大宽高比大小，wh ratio
                j = torch.max(r, 1. / r).max(2)[0] < self.hyp['anchor_t']  # 0.25<比例<4 才会被保留
                # compare
                # j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t']  # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2))
                t = t[j]  # filter

                # Offsets
                gxy = t[:, 2:4]  # 到左上角的距离 grid xy
                gxi = gain[[2, 3]] - gxy  #到右下角的距离  inverse
                j, k = ((gxy % 1. < g) & (gxy > 1.)).T#当前格子，离左上角近的选出来，而且不能是边界
                l, m = ((gxi % 1. < g) & (gxi > 1.)).T#离右下角近的选出来，而且不能是边界
                j = torch.stack((torch.ones_like(j), j, k, l, m))#5个，因为自己所在的实际位置一定为true
                t = t.repeat((5, 1, 1))[j]#相当于原来就1个，现在还有考虑两个邻居，target必然增多
                offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j]#对应区域玩对应漂移大小，都是0.5个单位
            else:
                t = targets[0]
                offsets = 0

            # Define
            b, c = t[:, :2].long().T  # image, class
            gxy = t[:, 2:4]  # grid xy
            gwh = t[:, 4:6]  # grid wh
            gij = (gxy - offsets).long()#漂移后整数部分就是格子的索引
            gi, gj = gij.T  # grid xy indices

            # Append
            a = t[:, 6].long()  # 每一个target对应的anchor indices
            indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1)))  # image, anchor, grid indices
            anch.append(anchors[a])  # anchors大小

        return indices, anch

        #复筛：IOU、类别（根据这两找损失最小的）
        matching_bs = [[] for pp in p]
        matching_as = [[] for pp in p]
        matching_gjs = [[] for pp in p]
        matching_gis = [[] for pp in p]
        matching_targets = [[] for pp in p]
        matching_anchs = [[] for pp in p]
        
        nl = len(p)    
    
        for batch_idx in range(p[0].shape[0]):
        
            b_idx = targets[:, 0]==batch_idx
            this_target = targets[b_idx]#当前图像里的标注框GT
            if this_target.shape[0] == 0:
                continue
                
            txywh = this_target[:, 2:6] * imgs[batch_idx].shape[1]#得到实际大小
            txyxy = xywh2xyxy(txywh)

            pxyxys = []
            p_cls = []
            p_obj = []
            from_which_layer = []
            all_b = []
            all_a = []
            all_gj = []
            all_gi = []
            all_anch = []
            
            for i, pi in enumerate(p):#遍历每一个输出层（3层）
                
                b, a, gj, gi = indices[i]
                idx = (b == batch_idx)
                b, a, gj, gi = b[idx], a[idx], gj[idx], gi[idx]   #生成候选框的位置，索引值
                all_b.append(b)
                all_a.append(a)
                all_gj.append(gj)
                all_gi.append(gi)
                all_anch.append(anch[i][idx])
                from_which_layer.append(torch.ones(size=(len(b),)) * i)#来自哪个输出层
                
                fg_pred = pi[b, a, gj, gi]   #取对应target位置的预测结果
                p_obj.append(fg_pred[:, 4:5])
                p_cls.append(fg_pred[:, 5:])
                
                grid = torch.stack([gi, gj], dim=1)
                pxy = (fg_pred[:, :2].sigmoid() * 2. - 0.5 + grid) * self.stride[i] #中心点在当前格子偏移量，-0.5-1.5之间，再还原  / 8.
                #pxy = (fg_pred[:, :2].sigmoid() * 3. - 1. + grid) * self.stride[i]
                pwh = (fg_pred[:, 2:4].sigmoid() * 2) ** 2 * anch[i][idx] * self.stride[i] #之前是考虑四倍，这也得同步   / 8.
                pxywh = torch.cat([pxy, pwh], dim=-1)
                pxyxy = xywh2xyxy(pxywh)
                pxyxys.append(pxyxy)
            
            pxyxys = torch.cat(pxyxys, dim=0)
            if pxyxys.shape[0] == 0:
                continue
            p_obj = torch.cat(p_obj, dim=0)
            p_cls = torch.cat(p_cls, dim=0)
            from_which_layer = torch.cat(from_which_layer, dim=0)
            all_b = torch.cat(all_b, dim=0)
            all_a = torch.cat(all_a, dim=0)
            all_gj = torch.cat(all_gj, dim=0)
            all_gi = torch.cat(all_gi, dim=0)
            all_anch = torch.cat(all_anch, dim=0)
        
            pair_wise_iou = box_iou(txyxy, pxyxys)#计算GT与所有候选正样本的IOU

            pair_wise_iou_loss = -torch.log(pair_wise_iou + 1e-8)#IOU损失

            top_k, _ = torch.topk(pair_wise_iou, min(10, pair_wise_iou.shape[1]), dim=1)#多的话选10个，少的话有几个算几个
            dynamic_ks = torch.clamp(top_k.sum(1).int(), min=1)#累加，取整，取这么多个框，相当于有些可能太小的我不需要，最少1个
            #类别损失
            gt_cls_per_image = (#真实值
                F.one_hot(this_target[:, 1].to(torch.int64), self.nc)
                .float()
                .unsqueeze(1)
                .repeat(1, pxyxys.shape[0], 1)#onehot后重复候选框数量次
            )

            num_gt = this_target.shape[0]
            cls_preds_ = (#预测类别情况
                p_cls.float().unsqueeze(0).repeat(num_gt, 1, 1).sigmoid_()
                * p_obj.unsqueeze(0).repeat(num_gt, 1, 1).sigmoid_()#是物体的置信度
            )

            y = cls_preds_.sqrt_()
            pair_wise_cls_loss = F.binary_cross_entropy_with_logits(
               torch.log(y/(1-y)) , gt_cls_per_image, reduction="none"
            ).sum(-1)#交叉熵，类别差异
            del cls_preds_
        
            cost = (#候选框里开始选了，要看他们的IOU情况和分类情况，综合考虑
                pair_wise_cls_loss
                + 3.0 * pair_wise_iou_loss#IOU损失占3份
            )

            matching_matrix = torch.zeros_like(cost)#匹配矩阵，匹配上的为1

            for gt_idx in range(num_gt):#遍历损失选最小的几个，根据所有在匹配矩阵中置0
                _, pos_idx = torch.topk(
                    cost[gt_idx], k=dynamic_ks[gt_idx].item(), largest=False
                )
                matching_matrix[gt_idx][pos_idx] = 1.0

            del top_k, dynamic_ks
            anchor_matching_gt = matching_matrix.sum(0)#竖着加
            if (anchor_matching_gt > 1).sum() > 0:#一个正样本匹配到了多个GT的情况
                _, cost_argmin = torch.min(cost[:, anchor_matching_gt > 1], dim=0)#那就匹配跟哪一个损失最小，删除其他
                matching_matrix[:, anchor_matching_gt > 1] *= 0.0#其他删除
                matching_matrix[cost_argmin, anchor_matching_gt > 1] = 1.0#最小的那个保留
            fg_mask_inboxes = matching_matrix.sum(0) > 0.0#哪些是正样本
            matched_gt_inds = matching_matrix[:, fg_mask_inboxes].argmax(0)#每个正样本对应的真实框索引
        
            from_which_layer = from_which_layer[fg_mask_inboxes]
            all_b = all_b[fg_mask_inboxes]#对应的batch索引
            all_a = all_a[fg_mask_inboxes]#对应的anchor索引
            all_gj = all_gj[fg_mask_inboxes]
            all_gi = all_gi[fg_mask_inboxes]
            all_anch = all_anch[fg_mask_inboxes]
        
            this_target = this_target[matched_gt_inds]#匹配到正样本的GT
        
            for i in range(nl):#得到每一层的正样本
                layer_idx = from_which_layer == i
                matching_bs[i].append(all_b[layer_idx])
                matching_as[i].append(all_a[layer_idx])
                matching_gjs[i].append(all_gj[layer_idx])
                matching_gis[i].append(all_gi[layer_idx])
                matching_targets[i].append(this_target[layer_idx])
                matching_anchs[i].append(all_anch[layer_idx])

    def __call__(self, p, targets, imgs):  # predictions预测值, targets标签, model 实际的原始输入
        device = targets.device
        lcls, lbox, lobj = torch.zeros(1, device=device), torch.zeros(1, device=device), torch.zeros(1, device=device)#初始化需要计算的三个损失
        bs, as_, gjs, gis, targets, anchors = self.build_targets(p, targets, imgs)
        pre_gen_gains = [torch.tensor(pp.shape, device=device)[[3, 2, 3, 2]] for pp in p] 
    

        # Losses
        for i, pi in enumerate(p):  # layer index, layer predictions
            b, a, gj, gi = bs[i], as_[i], gjs[i], gis[i]  # image, anchor, gridy, gridx
            tobj = torch.zeros_like(pi[..., 0], device=device)  # target obj

            n = b.shape[0]  # number of targets
            if n:
                ps = pi[b, a, gj, gi]  # prediction subset corresponding to targets

                # Regression，XYWH损失，预测的准不准
                grid = torch.stack([gi, gj], dim=1)#特征图中索引位置
                pxy = ps[:, :2].sigmoid() * 2. - 0.5
                #pxy = ps[:, :2].sigmoid() * 3. - 1.
                pwh = (ps[:, 2:4].sigmoid() * 2) ** 2 * anchors[i]
                pbox = torch.cat((pxy, pwh), 1)  # predicted box
                selected_tbox = targets[i][:, 2:6] * pre_gen_gains[i]
                selected_tbox[:, :2] -= grid#拿到偏移量
                iou = bbox_iou(pbox.T, selected_tbox, x1y1x2y2=False, CIoU=True)  # CIOU重叠面积、中心点距离、宽高比，同时加入了计算iou(prediction, target)
                lbox += (1.0 - iou).mean()  # iou loss

                # Objectness置信度损失
                tobj[b, a, gj, gi] = (1.0 - self.gr) + self.gr * iou.detach().clamp(0).type(tobj.dtype)  # iou ratio当做置信度

                # Classification
                selected_tcls = targets[i][:, 1].long()
                if self.nc > 1:  # cls loss (only if multiple classes)
                    t = torch.full_like(ps[:, 5:], self.cn, device=device)  # targets
                    t[range(n), selected_tcls] = self.cp#onehot一下
                    lcls += self.BCEcls(ps[:, 5:], t)  # BCE

                # Append targets to text file
                # with open('targets.txt', 'a') as file:
                #     [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)]

            obji = self.BCEobj(pi[..., 4], tobj)#大部分都是背景
            lobj += obji * self.balance[i]  # 置信度损失obj loss
            if self.autobalance:
                self.balance[i] = self.balance[i] * 0.9999 + 0.0001 / obji.detach().item()

        if self.autobalance:
            self.balance = [x / self.balance[self.ssi] for x in self.balance]
        lbox *= self.hyp['box']#回归损失
        lobj *= self.hyp['obj']#置信度损失
        lcls *= self.hyp['cls']#分类损失
        bs = tobj.shape[0]  # batch size

        loss = lbox + lobj + lcls
        return loss * bs, torch.cat((lbox, lobj, lcls, loss)).detach()

def detect(save_img=False):
    source, weights, view_img, save_txt, imgsz, trace = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size, not opt.no_trace
    save_img = not opt.nosave and not source.endswith('.txt')  # save inference images
    webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
        ('rtsp://', 'rtmp://', 'http://', 'https://'))

    # Directories
    save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))  # increment run
    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir

    # Initialize
    set_logging()
    device = select_device(opt.device)
    half = device.type != 'cpu'  # half precision only supported on CUDA

    # Load model
    model = attempt_load(weights, map_location=device)  # load FP32 model
    stride = int(model.stride.max())  # model stride
    imgsz = check_img_size(imgsz, s=stride)  # check img_size

    if trace:
        model = TracedModel(model, device, opt.img_size)

    if half:
        model.half()  # to FP16

    # Second-stage classifier
    classify = False
    if classify:
        modelc = load_classifier(name='resnet101', n=2)  # initialize
        modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']).to(device).eval()

    # Set Dataloader
    vid_path, vid_writer = None, None
    if webcam:
        view_img = check_imshow()
        cudnn.benchmark = True  # set True to speed up constant image size inference
        dataset = LoadStreams(source, img_size=imgsz, stride=stride)
    else:
        dataset = LoadImages(source, img_size=imgsz, stride=stride)

    # Get names and colors
    names = model.module.names if hasattr(model, 'module') else model.names
    colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]

    # Run inference
    if device.type != 'cpu':
        model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters())))  # run once
    t0 = time.time()
    for path, img, im0s, vid_cap in dataset:
        img = torch.from_numpy(img).to(device)
        img = img.half() if half else img.float()  # uint8 to fp16/32
        img /= 255.0  # 0 - 255 to 0.0 - 1.0
        if img.ndimension() == 3:
            img = img.unsqueeze(0)

        # Inference
        t1 = time_synchronized()
        pred = model(img, augment=opt.augment)[0]

        # Apply NMS
        pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
        t2 = time_synchronized()

        # Apply Classifier
        if classify:
            pred = apply_classifier(pred, modelc, img, im0s)

        # Process detections
        for i, det in enumerate(pred):  # detections per image
            if webcam:  # batch_size >= 1
                p, s, im0, frame = path[i], '%g: ' % i, im0s[i].copy(), dataset.count
            else:
                p, s, im0, frame = path, '', im0s, getattr(dataset, 'frame', 0)

            p = Path(p)  # to Path
            save_path = str(save_dir / p.name)  # img.jpg
            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # img.txt
            s += '%gx%g ' % img.shape[2:]  # print string
            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
            if len(det):
                # Rescale boxes from img_size to im0 size
                det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()

                # Print results
                for c in det[:, -1].unique():
                    n = (det[:, -1] == c).sum()  # detections per class
                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string

                # Write results
                for *xyxy, conf, cls in reversed(det):
                    if save_txt:  # Write to file
                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
                        line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh)  # label format
                        with open(txt_path + '.txt', 'a') as f:
                            f.write(('%g ' * len(line)).rstrip() % line + '\n')

                    if save_img or view_img:  # Add bbox to image
                        label = f'{names[int(cls)]} {conf:.2f}'
                        plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=3)

            # Print time (inference + NMS)
            #print(f'{s}Done. ({t2 - t1:.3f}s)')

            # Stream results
            if view_img:
                cv2.imshow(str(p), im0)
                cv2.waitKey(1)  # 1 millisecond

            # Save results (image with detections)
            if save_img:
                if dataset.mode == 'image':
                    cv2.imwrite(save_path, im0)
                    print(f" The image with the result is saved in: {save_path}")
                else:  # 'video' or 'stream'
                    if vid_path != save_path:  # new video
                        vid_path = save_path
                        if isinstance(vid_writer, cv2.VideoWriter):
                            vid_writer.release()  # release previous video writer
                        if vid_cap:  # video
                            fps = vid_cap.get(cv2.CAP_PROP_FPS)
                            w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
                            h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
                        else:  # stream
                            fps, w, h = 30, im0.shape[1], im0.shape[0]
                            save_path += '.mp4'
                        vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
                    vid_writer.write(im0)

    if save_txt or save_img:
        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
        #print(f"Results saved to {save_dir}{s}")

    print(f'Done. ({time.time() - t0:.3f}s)')


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', nargs='+', type=str, default='yolov7.pt', help='model.pt path(s)')
    parser.add_argument('--source', type=str, default='inference/images', help='source')  # file/folder, 0 for webcam
    parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
    parser.add_argument('--conf-thres', type=float, default=0.25, help='object confidence threshold')
    parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--view-img', action='store_true', help='display results')
    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
    parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
    parser.add_argument('--augment', action='store_true', help='augmented inference')
    parser.add_argument('--update', action='store_true', help='update all models')
    parser.add_argument('--project', default='runs/detect', help='save results to project/name')
    parser.add_argument('--name', default='exp', help='save results to project/name')
    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
    parser.add_argument('--no-trace', action='store_true', help='don`t trace model')
    opt = parser.parse_args()
    print(opt)
    #check_requirements(exclude=('pycocotools', 'thop'))

    with torch.no_grad():
        if opt.update:  # update all models (to fix SourceChangeWarning)
            for opt.weights in ['yolov7.pt']:
                detect()
                strip_optimizer(opt.weights)
        else:
            detect()