Satrajit Ghosh
Satrajit Ghosh
you can make preprocess an option. presumably you can use the minimal freesurfer for this instead of all of freesurfer. see neurodocker for the min recon-all version. however this can...
why not just log into an ec2 instance and carry out the steps manually?
it's from @fedorov - andrey we should chat sometime.
our current framework is here, based on trained-models: https://neuronets.dev/trained-models/ also moving this to trained-models
@fedorov - i'll be away for a bit, but second half of august may be good to put a brainstorming session in locally. would be happy to have folks over...
this model still needs to be added. and the README/docs needs to improve to describe each model and how to use it. for the docs, we can use the reproschema...
the old model instructions. they should be updated when the new model is added.
i would suggest using brainy. braingen is a GAN, and it would require a very different kind of network architecture and paradigm to be used for segmentation. it would also...
indeed it looks like there is a thread here to talk about curl and web assembly: https://github.com/WebAssembly/WASI/issues/107 the main intent is to leverage the streamability of these HDF5 files on...
i think this is less about the ROS3 driver per se, and more about exposing a remote http or s3 object as an in memory object or a streamable object....