【发布时间】:2020-09-18 16:57:39
【问题描述】:
我有一个从奶牛行为检测模型获得的输出列表。即使在奶牛产蛋的视频中,它通常也会识别为站立,反之亦然。在每个视频帧中,模型给出一个分类结果,我们将其附加到一个列表中。假设在 20 帧之后,我们有一系列输出如下 -
behavious_cow_1 = ["stand","stand","stand","stand","lying", "stand","stand", "eating", "stand","stand","stand","stand","lying""stand","stand","stand","stand","stand","stand","lying"]
在 20 个分类结果中,我们有 4 个错误分类; 3个谎言,1个吃东西。然而,这头牛一直坐在一个地方。如果列表只包含像 - 1,2,3...这样的数值,我会选择移动平均线来改变错误分类。是否有任何可以平滑分类输出的 Scipy、Pandas、Numpy 函数?我正在考虑使用前 3 个和后 3 个值来确定当前类别。
【问题讨论】:
标签: python pandas numpy math scipy