Amir Shamaei
Amir Shamaei
@effigies thanks. it helped. this issue has been solved. *surprisingly when I am using complex128 the results are accurate as complex64.
sorry for closing the topic :) It would be really nice to detect complex. I think spec2nii API uses nibabel as a backend for accessing nifti files; and spectroscopy imaging...
I made it a bit better as follows: ```python criterions: List = [torch.nn.MSELoss], ``` and config file: ``` criterions: - _target_: torch.nn.MSELoss - _target_: torch.nn.MSELoss ``` and the training step:...
I think the problem was related to example.yaml file since it didn't set default values for loggers. by adding - override /logger: wandb it logged successfully. I proposed this change.
@mmuckley Hi, I worked on this. However, it wasn't possible to make it using the same structure. I added a yaml file as a config file. I have tested only...
I need pytorch pretrained files as well.
Are you up to train it and release the pre-trained file?
@lchauvin thank you. Have you seen this: https://github.com/Hsankesara/VoxelMorph-PyTorch/blob/master/README.md I am trying to get a master student to do this. I think having it as a library would be helpful when...
@adalca Thank you. Looking forward to using that!
@dvm-shlee Sorry for my delayed response, too :) absolutely, my colleague put a dataset in Zenodo (https://zenodo.org/record/3894651). The 30th set is CSI data (20200612_094625_lego_phantom_3_1_2/30/fid). * in case you can not...