Tong Zhang

Implement of Jumping Knowledge Networks (JKNet). Run "python scripts/train.py --task node_classification --dataset citeseer --model jknet" to train JKNet on citeseer. Run "python scripts/train.py --task node_classification --dataset cora --model jknet" to...

Hi, I am wondering, why in "simmim.py", there is "no_weight_decay" function for "class SwinTransformerForSimMIM", but not for "class VisionTransformerForSimMIM" ?

randomization after reset_to_demo

2

Hi, Thank you for your wonderful implementation. When I evaluate task 'open_fridge', I notice that even after calling the [reset_to_demo](https://github.com/stepjam/RLBench/blob/master/rlbench/task_environment.py#L164) function, the initial object pose configurations sometimes (although not always)...

Wrong visualisation of point cloud after calibration

8

Hello, After I calibrated the RealSense camera extrinsics relative to the Franka Emika Panda using easy_handeye, I visualized the point cloud in the robot frame with rviz /camera/depth/color/points topic (I...

Issue with Using "replay_trajectory" in "pd_ee_pose" Control Mode

6

Hi, Thanks for your explanation in [this issue](https://github.com/haosulab/ManiSkill2/issues/122) Following your advice, I've incorporated both "arm_pd_ee_pose" and "pd_ee_pose" into [ManiSkill2/mani_skill2/agents/configs/panda/defaults.py](https://github.com/haosulab/ManiSkill2/blob/fc08823bf96791946591a508f336d724fa7cad26/mani_skill2/agents/configs/panda/defaults.py). However, I've encountered an issue when using the mani_skill2.trajectory.replay_trajectory function in...

Thank you for your great work. I noticed that in the `apply_se3_aug_con` function for rotation augmentation, there are two options, `ver=1` and `ver=2`. However, I observed that at line 364...