neuronflow
neuronflow
BraTS-preprocess stuck at "status reveived: { 'code': 201, 'message': 'nifti examination queued!'}."
Until this issue https://github.com/neuronflow/BraTS-Toolkit/issues/18 is closed you need `.nii.gz` files. Just renaming is enough, you don't actually need to compress them. You can also try our new preprocessing toolkit which...
any news on this? :)
From my naive understanding rsync will compare source and target files which should result in read operations on your tape?
Thanks for the quick response. In our case, we are trying to register 3D brain MR across modalities. If we understood you correctly we should use: ``` initialize: geometry transform:...
Thank you so much! You are right, Apologies, I failed to provide the whole call. Here is the rest we have in place: ``` dimensionality = "-d 3" initial_moving_transform =...
Thanks. I am working on LiTS data atm: https://competitions.codalab.org/competitions/15595 the total training set is ~41gb atm. I can experiment with lower values of cache_rate, which values should I try and...
41gb on disk no tfs. The training here just uses scaling (setting ct window) and random flips for augmentation. Here a training with the normal `Dataset` class (red) vs. the...
Thanks, I used `replace_rate=0.25`, will do your suggested experiment and report back.
Now with `cache_rate=0.1`, I only trained a few epochs yet, but one can already observe a doubling in epoch duration.
training continued: