xibeisiber

usually it is because the necessary config file is not found. Check all the paths of files that need to be loaded. And it's better that you give the error...

Actually GPD will give the message if some file is not found, but not as an error message, but a "normal" output. so you can also check the whole output...

Thanks for your reply! Yes, the pointcloud is taken with one camera. It would be difficult for my robot to install a 2nd camera for now. I will consider it...

I create a virtual frame where the z axis directs from the robot base to the bottle, transform the pointcloud into this frame and send it to GPD, filter the...

I just realized yesterday I forgot to turn PCL_GPU off when compiling GPD after switching my pc. After I turned it off, the quality is much better. I plan to...

> That part of the code is deprecated and should **not** be used. > > How large is your point cloud? Thanks for your reply. You mean the option "-DUSE_PCL_GPU"...

Yesterday I tried to use PCL_GPU in GPD and CloudSamples as the input, the whole process is very fast, but sometimes it can't generate any valid grasp pose, sometimes it...

> Hello, have you considered using a Checkpoint callback or a custom callback ? ("alternatives" part in the issue template). checkpointCallback saves models every fixed steps and may save a...

> This sounds like you should evaluate the agent for more episodes, `--eval-episodes` in the zoo (you can also use multiple envs for evaluation to make it faster) The default...

I may find the possible reason that the saved best model has a quite different reward when evaluated using enjoy.py compared to the reward in tensorboard curve. My env is...