Mahesh Bhosale

Same, could you please le us know ?

Any luck anyone? I am not sure which checkpoint to use? Can we use inpaint_big, but why does it have an absurdly large number of conditional channels?

> I change model config to this: > > ``` > model: > target: cldm.scldm.ExtendedControlLDM > params: > linear_start: 0.00085 > linear_end: 0.0120 > num_timesteps_cond: 1 > log_every_t: 200 >...

I was able to register with mri_register, and I could verify it by visualizing it in ITKsnap. I then trained on affinely aligned volumes with the preprocessing [from this paper](https://github.com/cheng-01037/Self-supervised-Fewshot-Medical-Image-Segmentation/tree/master/data/CHAOST2...

For the CHAOS dataset I was able to first globally register the pairs, and found the improvement.

Yes above solution worked for me too.

Thank you.

Yes, I am getting similar errors

Yes looking forward to the release of the training code since the paper has already been accepted.

yes this is the paper.