You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
你好,我查看COCO与AIC数据结合训练的demo。但是我有个疑惑COCO数据集是17个关键点,AIC与COCO的关键点数是不一样的,尽管在AIC中提取了与COCO相同的关键点,而AIC并没有脸部的关键点,因此在AIC中把脸部关键点的可见性变为0。在模型训练中读取AIC的图像时对象脸部的关键点实际是可见的,但又告诉模型这是不可见,这不是对比读COCO数据集时有明显的差别,这样训练出来的结果会好么?但是rtmpose论文中告诉我是能提点的,我有点疑惑,这样的训练对脸部关键点的检测不会有影响么?为什么指标会有提升?那如果我添加一个只有上半身的关键点的数据集(下半身的关键点没有标注但可见),也可以这样添加么?是会对上半身的关键点检测有提升么?
尽管说在https://github.com/open-mmlab/mmpose/issues/2704中收到答复,但是在模型读取图片的时候,脸部是可见的,但把脸部关键点的可见性设置为0,这不是会有冲突么?对于loss的解释我能理解,但是我个人感觉还是有点疑惑。希望能有个解释。
Beta Was this translation helpful? Give feedback.
All reactions