Closed kmader closed 7 years ago
@mehrtash What do you think?
@kmader @mpslxz definitely makes sense! There is no need to limit ourselves to a specific datatype at slicer level. We should move any preprocessing to the docker side.
@kmader This has been fixed. Now the original image will be sent to the docker for further processing. All conversions will be handled inside the docker.
Currently only uint8 images are supported (https://github.com/DeepInfer/Slicer-DeepInfer/blob/master/DeepInfer/DeepInfer.py#L642) which is very limiting for techniques like CT. It would be good to have support for short and floating point images based on the json files