xbchen
xbchen
你测试的时候开fliptest了吗？ 我也只能到87点8左右。
I also found this phenomenon. However, from the annotation, it mostly fits, indicating that the annotation of this dataset is a rough one.
> > 你可以进入kitti_dataset.py和添加`print(calib_file)`的盈 > > ``` > > assert os.path.exists(calib_file) > > ``` > > > > > > 然后检查该文件是否存在。也许您将calib文件夹放在其他位置。 > > 感谢您的帮助，我已修复此错误（我忘记下载一些数据）。 您好，请问您怎么解决的这个问题？能指导一下我吗？
> I got the same error as well, someone please help me to get through it. me too. did you solve it ?
> 感谢@eddienewton的帮助。对于这里值得的是我想出的Python实现来做我需要做的事情： > > ``` > def voxel_filter(pts, scores, grid_size, use_3d=False, min_num_pts=4): > mins = pts.min(axis=0) - grid_size > maxs = pts.max(axis=0) + grid_size > bins = [np.arange(mins[i], maxs[i], grid_size)...
> Sorry about that: > `from scipy import stats` > > Do you have an example of what you would like to use it for? Thank you for your quick...
> Sorry about that: > `from scipy import stats` > > Do you have an example of what you would like to use it for? Thank you very much for...