|
nnlib
GPU-accelerated, C/C++ neural network library.
|
Structure to contain information about the current epoch. More...
Public Member Functions | |
| EpochProgress (size_t numTotal) | |
| The constructor of the EpochProgress class. More... | |
| void | update (sTensor &targets, sTensor &predictions, Loss *loss, std::vector< Metric * > &metrics) |
| Update the current state of the epoch. More... | |
Public Attributes | |
| size_t | numProcessed |
| Total number of samples already processed. | |
| size_t | numTotal |
| The total number of samples (processed + non-processed). | |
| float | lossValue |
| The value of the loss. | |
| std::map< std::string, float > | metricsValues |
| Mapping of names of metrics to their computed values. | |
| std::chrono::time_point< std::chrono::steady_clock > | timeStart |
| The time the epoch started. | |
Structure to contain information about the current epoch.
|
inlineexplicit |
The constructor of the EpochProgress class.
| numTotal | The total number of samples to be processed. |
|
inline |
Update the current state of the epoch.
| targets | The desired predictions of the network in the current batch. |
| predictions | The actual predictions of the network in the current batch. |
| loss | The loss object to update. |
| metrics | The metrics to update given the new batch. |