五小白: loss的选取要看你的关键点是刚性的还是非刚性的，车牌的关键点位置是较为固定的，属于刚性的，所以用wing loss效果更好。

qq_37172257: 楼主你好 我注意到你把oks loss替换成了wing loss，是不是您也用oks loss训练时遇到了一些问题？

weixin_43437396: 博主你好 训练yolov7-pose时报错ValueError:not enough values to unpack (expected 3, got 0)，请问怎么解决

深度学习小白的从无到有: Traceback (most recent call last): File "/root/yolov7-pose_Npoint_Ncla/test_Ncla.py", line 405, in test(opt.data, File "/root/yolov7-pose_Npoint_Ncla/test_Ncla.py", line 101, in test dataloader = create_dataloader(data[task], imgsz, batch_size, gs, opt, pad=0.5, rect=True, File "/root/yolov7-pose_Npoint_Ncla/utils/datasets_Npoint.py", line 64, in create_dataloader dataset = LoadImagesAndLabels(path, imgsz, batch_size, File "/root/yolov7-pose_Npoint_Ncla/utils/datasets_Npoint.py", line 423, in __init__ labels, shapes, self.segments = zip(*cache.values()) ValueError: not enough values to unpack (expected 3, got 0) 大佬请问这是什么问题呀？怎么解决呀？

m0_63640043: 博主大大 请问用目标框标记法标注完后怎么可视化标签