improve batch-wise grasp generation in sampling scripts

robotgradient / grasp_diffusion

Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home

MIT License

234 stars 24 forks source link

improve batch-wise grasp generation in sampling scripts #5

Closed kuldeepbrd1 closed 1 year ago

kuldeepbrd1 commented 1 year ago

To resolve issue #4

added consistent use of batch_size and device variables
added sampling loop to support desired n_grasps
added device and batch_size as cli args
Auto-sorted imports and format changes from black

kuldeepbrd1 commented 1 year ago

@TheCamusean

In the diff for the changed files, you will also see that there are lots of formatting changes (indentation, terminal spaces, linebreaks etc). These were automatically included in the commit as I use auto-format on save using black. I only noticed later.

Let me know if you want me to remove these auto-formatting changes. Happy to also do that :)