Samarth Brahmbhatt

Hi @sunnyHelen it is hard to debug this without looking at your dataloader code. It seems like you should be able to load the `poses` file directly into the `ps`...

Hi @cccccv-cm you are right that in the past we have observed that changing the PyTorch version affects reproducibility: https://github.com/NVlabs/geomapnet/issues/36. I don't have the ability to support newer and newer...

> What happens with `IMREAD_ANYCOLOR | IMREAD_ANYDEPTH` instead? @NikolausDemmel I just tried it. `IMREAD_ANYCOLOR | IMREAD_ANYDEPTH` works. So do `IMREAD_GRAYSCALE | IMREAD_ANYDEPTH`, and `IMREAD_UNCHANGED`.

@gs-ren as you can see in the [function documentation](https://github.com/facebookresearch/ContactPose/blob/main/utilities/dataset.py#L300), `cp.mano_meshes(frame_idx)` does not return 3 frames. Instead, it returns a list of 2 dicts. `[left_hand_dict, right_hand_dict]`. Each dict is either `None`...

@canktech I experienced the same while creating a MoveIt! config for KUKA IIWA from the [kuka_lbr_iiwa_support](https://github.com/ros-industrial/kuka_experimental/tree/indigo-devel/kuka_lbr_iiwa_support) package. I was following the [official MoveIt! Setup Assistant tutorial](http://docs.ros.org/kinetic/api/moveit_tutorials/html/doc/setup_assistant/setup_assistant_tutorial.html). Inspired by your comment,...

If you installed GraspIt! to a custom location (denoted by the environment variable `GRASPIT_DIR`), you might face this error. I solved it by using `catkin_make -Dgraspit_DIR=${GRASPIT_DIR}/lib/cmake/graspit`. Directly modifying the `CMAKE_PREFIX_PATH`...

I might be experiencing this too. I am trying to collect a bunch of grasps for an object from various approach vectors. Here is my pseudocode: ``` clearWorld() loadWorld(world_name) #...

It seems like my case was an instance of "Neighbor gen loops" as mentioned in https://github.com/graspit-simulator/graspit/issues/131, not a memory leak.

Hi @nickjyj , thanks for your interest in this work! It seems like `masked_targ` is a `torch.cuda.IntTensor` (`int32`), but should be `torch.cuda.LongTensor` (`int64`). This is coming from L103 of `pointcloud_dataset.py`,...