Classes | |
struct | dcnnasgn::combined_policy< PP > |
Policy: The complete network. More... | |
class | dcnnasgn::combined_model< PP > |
Model data (weights and biases) of the complete network. More... | |
class | dcnnasgn::combined_data< PP > |
Input data, forward-propagated activations, and loss of the complete network. More... | |
Typedefs | |
using | dcnnasgn::test_labels_t = tagged::tensor_class<gold_labels_policy::label_carrier, input_tag> |
using | dcnnasgn::test_images_t = tagged::tensor_class<idp::image_carrier, input_tag, idp::height_tag, idp::width_tag, idp::channel_tag> |
Functions | |
template<is_policy PP> | |
void | dcnnasgn::combined_load_model (combined_model< PP > &m, const std::filesystem::path &data_folder) |
template<typename mapping, is_policy PP> | |
float | dcnnasgn::combined_forward (const test_images_t &test_images, const test_labels_t &test_labels, mapping &&bmap, const combined_model< PP > &m, combined_data< PP > &d) |
The forward-propagation function of the complete network. | |
|
inline |
The forward-propagation function of the complete network.
Includes creation of a minibatch by selection of the specified input images from the training dataset
mapping | Input selection mapping |
PP | Permutation policy |
train_images | Training image dataset |
train_labels | Ground-truth dataset |
bmap | Input selection mapping |
m | Network model data |
d | Forward-propagation data |