-
When I started training using my data，such an error occurred
data:
centered: false
dataset: AAPM
image_size: 256
is_complex: false
is_multi: false
num_channels: 1
random_flip: tr…
-
Thank you very much for your contribution and sharing, but when I read the code I didn't find the "MBIR" module mentioned in the paper, can you tell me about it?
-
When testing MACE with qGGMRF denoiser, we observed that while the converged result seems correct (in the sense that it is close to MBIR recon result), the convergence is slow.
See the slides below f…
-
Hi!
Currently svmbir prints to console all it's messages. This makes ist somewhat hacky to use inside other projects, which have a propper logging interface or a CLI.
There basically two options…
-
## Expected Behavior
I am using pytorch and TIGRE together to do inverse projection, but I found that when I put pytorch and TIGRE on the same GPU, it will report an error. If I put pytorch and TIGRE…
-
The current C code reduces the number of parallel threads to stabilize convergence when the positivity constraint is turned off. If we implement the relaxation factor for voxel update, then there will…
-
I was excited to try your generative Large Language Model for generalized, linear or nonlinear, multivariate latent-variable mixed/multilevel modeling. It installs OK but none of the examples seem to…
-
when I run:
> limited_angle = np.linspace(0, np.pi/2, 180)
> limited_projection = tigre.Ax(img, geo, limited_angle)
> print(limited_projection.shape)
> img_tv = ossart_tv(limited_projection,geo,…
-
Recently "bugzilla" is observed again on a problem with small number of slices, where divergence of the MBIR recon is observed with default number of threads on a problem with recon array size of 5x40…
-
The code generates nans in the recon.
This seems to happen when the weights are small/zero or iterations are run to very precise convergence.
The problem can be reproduce by setting `weight_type="…