elevenjiang
elevenjiang
Yeah, I have same problem,the dataset use is DexNet2.0 dataset and output is same all Pred nonzero=0 Do you find the reason?
After testing a little more, It seems that when you train a more(around 3 epoch),Then it will not all 0; And after removing all nosing param from .yaml file,This will...
Sorry for reply so so so late @aprath1 Actually, I find that when train a lot, this problem will be solve, remove parameters seems don't make much sense. By the...
yeah,I also hope can get a detailed tools for annotating~ I know a tool named [LabelFusion](https://github.com/RobotLocomotion/LabelFusion) but the code is too old and difficult to use
I also have same problem! I think the main problem is the version are too mess in autolab github !
> It seems that in Python3,or in high version in autolab_core,```from perception import CameraIntrinsics``` need to change to ```from autolab_core import CameraIntrinsics``` I have setup dexnet on Ubuntu 16.04 python2,...
> > > > > > > > > It seems that in Python3,or in high version in autolab_core,`from perception import CameraIntrinsics` need to change to `from autolab_core import CameraIntrinsics`...
I also have this problem by self make database. Even the object are from their shapes. Hoping to provide the origin parameters of generate database and generate gqcnn @jeffmahler Best
Any annotation tools have ever found?
I also want this function. Now I use another method to achieve this. By change it into pointcloud,then use VoxelGrid.create_from_point_cloud() to get the voxel. All code are below,hoping can help...