Closed ahundt closed 5 years ago
Additional bug: There are also NaN bboxes, which aren't handled correctly.
@ahundt Yeah,I also find the problem.As the issue #20 ,I have deleted the Nan valude in pcd0132cpos.txt and pcd0165cpos.txt file and run build_cgd_dataset.py.However,when I run grasp_det.py for train,the loss is nan.
There are newer repositories with better results and more complete implementations available on github. It was a great starting point at the time of release, but I don't recommend using this repo/code anymore.
@ahundt Thank you for your reply.
@ahundt By the way,would you mind sharing the link of newer repositories with better results and more complete implementations available on github? Thanks a lot.
This is mine and has a keras/tf loader, but it only supports single grasp: https://github.com/jhu-lcsr/costar_plan
I'm finding this pytorch implementation is pretty decent and runs on a real robot: https://github.com/andyzeng/visual-pushing-grasping
@ahundt Thanks a lot.Yeah,I have read your paper "The CoSTAR Block Stacking Dataset: Learning with Workspace Constraints",a very interseting work about block stacking. Andyzeng uses Reinforcement Learning to learn how to pick and place.However,the environment is limited.Thank you for your kindness.
Thanks!
It seems only the positive bounding boxes might be loaded, is this the case?![bounding box](https://user-images.githubusercontent.com/34765938/35213959-75afc960-ff9a-11e7-9916-ac11117415c5.png)
Also, how are the varying numbers of bboxes handled / structured?
The code for that part is split in several locations so it isn't easy to tell the design.