图片赋值操作

tracks=np.array([[[1, 1, 1, 1, 1],
    [2, 2, 2 ,2, 2],
    [3, 3, 3, 3 ,3]],
[[1, 1, 1, 1, 1],
    [2, 2, 2 ,2, 2],
    [3, 3, 3, 3 ,3]]]
)

track_feature = np.zeros((2, 4, 5))
track_feature[:, :3, :] = np.array(tracks)  # 覆盖前几行
注：track_feature第二维的3要和tracks第2维的3要保持一致。