There are two ways for building a simple set:
, retrieves the ith-sample from the input, target and weight source (if any) calling the gnn_input_get function on each of them. Typedefs | |
| typedef _gnn_simple_set | gnn_simple_set |
| The datatype for simple sets. | |
Functions | |
| int | gnn_simple_set_reset (gnn_dataset *set) |
| The "reset" function for a simple set. | |
| int | gnn_simple_set_get (gnn_dataset *set, size_t k, gsl_vector **x, gsl_vector **t, double *p) |
| The "get" function for a simple set. | |
| void | gnn_simple_set_destroy (gnn_dataset *set) |
| Destroy function. | |
| gnn_dataset * | gnn_simple_set_new (gnn_input *inputs, gnn_input *outputs, gnn_input *weights) |
| Builds a new simple set. | |
| gnn_dataset * | gnn_simple_set_from_files_new (const char *inputsFile, const char *outputsFile, const char *weightsFile) |
| Builds a new simple set from text files. | |
| gnn_input * | gnn_simple_set_get_inputs (gnn_dataset *set) |
| Returns a pointer to the inputs. | |
| gnn_input * | gnn_simple_set_get_outputs (gnn_dataset *set) |
| Returns a pointer to the target vector input device. | |
| gnn_input * | gnn_simple_set_get_weights (gnn_dataset *set) |
| Returns a pointer to the inputs. | |
|
|
This is the datatype for simple sets. It extends the basic gnn_dataset : Datasets for Training. structure to include three additional pointers to the input pattern, output pattern and pattern weights samplers. Definition at line 50 of file gnn_simple_set.h. |
|
|
This is the gnn_simple_set : A simple implementation of datasets. destroy function.
Definition at line 174 of file gnn_simple_set.c. |
|
||||||||||||||||
|
This functions creates a new simple set from two or three text files containing the patterns. The text files should be ASCII-formatted, and should contain matrices where the number of columns corresponds to the size of the vectors, and the row number to the number of patterns. Obviously, it is illegal to provide matrices of different row sizes. Also, the weights file should have only one column.
If the weights file is omitted (i.e. it is a pointer to It is basically a shorthand for building the dataset from gnn_input : Reading and handling of sets of vectors. structures which themselves should be built from text files.
Definition at line 304 of file gnn_simple_set.c. |
|
||||||||||||||||||||||||
|
This function is returns the k-th pattern in the simple set, where the k-th input pattern, output pattern and pattern weight are sampled from the internally installed device samplers.
Definition at line 128 of file gnn_simple_set.c. |
|
|
This function returns a pointer to the inputs, which are of the gnn_input : Reading and handling of sets of vectors. type.
Definition at line 341 of file gnn_simple_set.c. |
|
|
This function returns a pointer to the outputs, which are of the gnn_input : Reading and handling of sets of vectors. type.
Definition at line 361 of file gnn_simple_set.c. |
|
|
This function returns a pointer to the weights input device, which are of the gnn_input : Reading and handling of sets of vectors. type or NULL if not available.
Definition at line 382 of file gnn_simple_set.c. |
|
||||||||||||||||
|
This functions creates a new simple set from two or three input samplers. The first two correspond to the input pattern and output pattern samplers, wich should contain the same amount of patterns. The third is the pattern weight sampler, which, if given, should also be of the same size. If omitted (that means it is a
Definition at line 215 of file gnn_simple_set.c. |
|
|
This function resets the gnn_simple_set : A simple implementation of datasets..
Definition at line 95 of file gnn_simple_set.c. |
1.2.18