Johannes Pitz
Johannes Pitz
I also searched through the repository, and couldn't find another occurrence of "np.float" (without the 64 following it).
Hey, for sure. So I have sweeps: And in the sweep overview, I would like to keep track of configurations that are shared by all the individual runs. Ideally with...
Thanks, worked also with Python3.7.
> Doesn't work for pytorch. As far as I remember I had to import a second package, but for me the easy workaround was to set `num_workers=0` in the `Dataloader`...
I mean this is all did so far: ``` class ForwardKinematics(): def __init__(self): self.num_in_joints = 3 self.num_fk_joints = 4 self.chain = pk.build_serial_chain_from_urdf( open("finger.urdf").read(), "virtual_distal_link" ) def _joints_from_x(self, x): return torch.stack(...
Thank's for the reply @mmacklin! And I would be very interested to hear if/where we really need to call `wp.synchronize()` @nvlukasz. Regarding the accumulation of gradients. When we use `wp.from_torch()`...
Thank you for the detailed answer regarding the synchronization! @nvlukasz Though, can either of you comment on the accumulation of the gradients again. @mmacklin Am I missing something, or is...