Chaithya G R
Chaithya G R
We soon will support autodiff wrt to trajectory. However, we should perhaps handle: - [ ] autodiff wrt to smaps - [x] https://github.com/mind-inria/mri-nufft/pull/116#discussion_r1626161177 We need the users to be able...
Recently with #90 we now have Smaps estimation module. However, this was not tested. It will be helpful to have tests for this
Currently we seem to have 2 different memory elements for `samples` (perhaps 3 assuming interfaces has a copy of its own internally, but that cant be fixed). What we need...
Currently, we dont pull out this data. However, it is crucial information for us to finally save the reconstructed images. This could involve moving from pymapvbvd to twixtools if needed.
Currently, we support all the ingridients needed for doing CG iteration, just a small function in extras module with: Here is a simple example of gradient descent step. All thats...
For now imports seem really slow, make it faster for faster debug cycles
We currently dont check if the image shape matches what was specified in the init. Additionally, it will help a lot to ensure that we are C ordered in the...
Currently, in https://github.com/mind-inria/mri-nufft/blob/f5a6ba006184b96a1f73ff54be27d854797c79fe/src/mrinufft/operators/off_resonnance.py#L19-L58 we just generate the fourier_op which takes the B and C values into account. - [ ] It might help to also include a function in `mrinufft.operators.off_resonance`...
Hi there, Thank you again for the amazing work. We re-ran our [MRI benchmark](https://github.com/mind-inria/mri-nufft-benchmark) for different nufft suits, and we are pleased to announce that **cufinufft is the fastest NUFFT...