Explanations

The concepts behind bartorch, one page each, from the call into BART to learned reconstruction and performance. Exact interfaces are in API reference, and complete workflows in the examples.

Page	Contents
Execution model	Tools, apps and operators over one embedded BART; errors, devices and threads
Data layout	Tensor axes as BART dimensions, Fourier conventions, trajectory units and file formats
Encoding operators	MRI forward operator, operator algebra, the plan it is lowered into
Non-Cartesian transform	NUFFT, density compensation, Toeplitz normal
Regularizers	Penalties and their proximal operators
Solvers	Choice of iteration, step size and regularization weight
Model-based reconstruction	Nonlinear forward models, IRGNM, joint coil estimation and parameter maps
Learned reconstruction	Gradients through operators and solvers; networks inside a reconstruction
Performance	Devices, precision, threads and the libraries behind BLAS, LAPACK and the FFT