Skip to content
Snippets Groups Projects
Commit 0606194d authored by Martin Beseda's avatar Martin Beseda
Browse files

[WIP] Trying to fix mini-batch variants of GD.

parent c8183082
No related branches found
No related tags found
No related merge requests found
......@@ -77,6 +77,7 @@ namespace lib4neuro {
arma::Mat<double>* outputs_matrix;
unsigned int last_batch_vector_ind = 0;
public:
......@@ -315,9 +316,23 @@ namespace lib4neuro {
* @param max
* @return
*/
[[deprecated("get_next_random_data_batch() should be used instead")]]
LIB4NEURO_API std::vector<std::pair<std::vector<double>, std::vector<double>>>
get_random_data_batch(size_t max);
/**
* Function, that returns being&end iterators of the next random disjunct batch of DataSet.
* Randomness is given by copying the current DataSet, shuffling it once by Fisher-Yates algorithm and then
* selecting first 'max' elements, which weren't selected before.
*
* If the shuffled vector is depleted, the process repeats with copying the DataSet again and another random
* shuffle...
*
* @param max
* @return
*/
LIB4NEURO_API std::vector<std::pair<std::vector<double>, std::vector<double>>> get_next_data_batch(size_t max);
/**
* Adds a new output column filled with zeros
* @param n_columns Number of columns to be inserted
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment