This is the class and function reference of cycompsense. Please refer to the tutorial for further details, as the class and function raw specifications may not be enough to give full guidelines on their uses.
The classes defined in this module, implement different operators that operate on input signals. These operators are used for defining problems. opBase should be subclassed for creating new operators.
| compsense.operators.opBase(name, shape[, ...]) | Base class for operators |
| compsense.operators.opMatrix(A) | Operator that wraps a simple matrix. |
| compsense.operators.opBlur(shape) | Two-dimensional blurring operator. |
| compsense.operators.opRandMask(shape, fill_ratio) | Random binary mask. |
| compsense.operators.opWavelet(shape[, name, ...]) | Wavelet operator. |
| compsense.operators.opDirac(shape) | Identity operator |
| compsense.operators.opFoG(operators_list) | Concatenate a sequence of operators into a single operator. |
| compsense.operators.opFFT2d(shape) | Two-dimensional fast Fourier transform (FFT) operator. |
| compsense.operators.opDCT(shape[, axis]) | Arbitrary dimensional discrete cosine transform (DCT). |
| compsense.operators.op3DStack(operator, dim3) | Extend an operator to process a stack of signals. |
A set of problems for testing and benchmarking algorithms for sparse signal reconstruction. problemBase should be subclassed for creating new problems.
| compsense.problems.problemBase(name[, noseed]) | Base class for all CS problems. The problems follow |
| compsense.problems.problemBase.reconstruct(x) | Reconstruct signal from sparse coefficients |
| compsense.problems.probCustom(A, b[, x0, name]) | This class allows the user to define his own problem object based on the problem matrices. |
| compsense.problems.prob701([sigma, ...]) | GPSR example: Daubechies basis, blurred Photographer. |
| compsense.problems.probMissingPixels([...]) | RandomMask example: Wavelet basis, masked Photographer. |
A set of reconstruction algorithms.
| compsense.algorithms.algorithmBase(name, P) | Base class for algorithms |
| compsense.algorithms.algorithmBase.solve([...]) | Solve the problem |
| compsense.algorithms.TwIST(P, tau[, ...]) | Two-step Iterative Shrinkage/Thresholding Algorithm for Linear Inverse Problems. |
| compsense.algorithms.TwIST_raw(y, A, tau[, ...]) | Two-step Iterative Shrinkage/Thresholding Algorithm for Linear Inverse Problems. |