stnava

also - I would recommend using ANTsPy I/O as follows: ``` import ants img=ants.image_read("MRI_4.nii").iMath("Normalize") img2=ants.image_read("MRI_4.nii").iMath("Normalize") reg=ants.registration(img,img2,'SyN') # check mag of def warp=ants.image_read( reg['fwdtransforms'][0] ).split_channels() for k in range(3): print(warp[k].abs().max()) #...

if they have negative values, then yes

shrinidhi and i put something together for this a while ago but i am unable to locate it is there an easy / maintainable at least osx/linux approach for this?...

this is clearer http://www.debian-administration.org/article/An_introduction_to_bash_completion_part_2 brian On Sun, Aug 18, 2013 at 12:35 PM, brian avants [email protected] wrote: > shrinidhi and i put something together for this a while ago but...

the intended approach is: ``` import ants reg=ants.registration( ants.image_read( ants.get_data("r16" ) ), ants.image_read( ants.get_data("r16" ) ), 'SyN') warp=ants.image_read( reg['fwdtransforms'][0] ) # image not transform warptx = ants.transform_from_displacement_field( warp ) ```...

the objects saved in the `reg['fwdtransforms'][0]` is not explicitly coded as a transformation .... so we'd have to guess that it represents an actual deformation field ......

we would welcome any contributions that improve clarity and usability.

that's not really how we expect the code to be called. try: ``` import ants fi = ants.image_read( ants.get_data( "r16" ) ) - 128 mi = ants.image_read( ants.get_data( "r64" )...

probably need to share the data brian On Wed, May 13, 2020 at 8:50 AM Maximilian Hoffmann < [email protected]> wrote: > fi = ants.from_numpy(tmpl.astype('float32')) > mi = ants.from_numpy(vol1_shift_c.astype('float32')) > reg...

can you provide a reproducible example based on this h5 data?