Thomas Lips

@HamzaNaseerFHWS , no I didn't unfortunately

need to pin timm to >=0.9.X to avoid these issues.

Hi @mareksubocz This is indeed not supported in the dataloader at the moment, and stacking these tensors will give the error you have encountered above. What you will need to...

> I think I might try to do this on my own and submit a pr, we'll see . Looking forward to it! > I guess the keypoint values should...

@jarnebogaert, pytorch 2.0 and PL 2.0 have some breaking changes, most prominently the CLI for PL as you have encountered. I'll lock the version of PL to 1.9 untill I...

@lucasvandijck, we've had this issue in the past with the drive kit, but I never bothered to change all occurances of the 'same' padding. I'm not entirely sure if creating...

> Hi all, I think the prompt template for VQA is as below: > > question = "Question: how many dogs are in the picture? Answer:" > > See the...

@Cadene, good suggestion! I've started a train run for diffusion on the pushT task, will post the the results here later today or tomorrow

@Cadene @marinabar I trained on the PushT env with diffusion policy using all default settings. The (surprising) results are as follows:  - validation loss is increasing during training, instead...

@alexander-soare Same plot + train loss (switched to log scale) pusht + diffusion:  aloha-insertion + act:  the aloha + ACT val loss curve is more what I expected....