Bausager/Flux-openbuild
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Sync public subset from Flux

Browse Source
This commit is contained in:
Gitea CI
2025-10-20 12:24:21 +00:00
parent 9a69d64d79
commit a334b74935
8 changed files with 230 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

79
include/modules/neural_networks/loss/Loss_CategoricalCrossentrophy.h
View File

@@ -16,38 +16,67 @@ namespace neural_networks{
template <typename Td, typename Ti>
struct Loss_CategoricalCrossentrophy : Loss<Td, Ti> {
utils::Vector<Td> forward(const utils::Matrix<Td>& y_pred, const utils::Matrix<Ti>& y_true) override{
utils::Vector<Td> correct_confidences(y_true.rows(), Td{0});
utils::Matrix<Td> cast_y_true = utils::matcast<Td, Ti>(y_true);
// Number of samles in a batch
const uint64_t samples = y_true.rows();
utils::Matrix<Td> dinputs;
// Clip data to prevent dividning by 0
// Clip both sides to not drag mean towards any value
utils::Matrix<Td> y_pred_clipped = numerics::matclip(y_pred, Td{1e-7}, Td{1.0} - Td{1e-7});
utils::Vector<Td> forward(const utils::Matrix<Td>& y_pred, const utils::Matrix<Ti>& y_true) override{
utils::Vector<Td> correct_confidences(y_true.rows(), Td{0});
utils::Matrix<Td> cast_y_true = utils::matcast<Td, Ti>(y_true);
// Probabilities for taget values
// only if categorical labes
if (y_true.cols() == 1){
for (uint64_t i = 0; i < y_true.rows(); ++i){
const uint64_t idx = static_cast<uint64_t>(y_true(i, 0));
correct_confidences[i] = y_pred_clipped(i, idx);
}
}else{ // Mask values - only for one-hot encoded labels
correct_confidences = numerics::matdot_row(y_pred_clipped, cast_y_true);
// Number of samles in a batch
const uint64_t samples = y_true.rows();
// Clip data to prevent dividning by 0
// Clip both sides to not drag mean towards any value
utils::Matrix<Td> y_pred_clipped = numerics::matclip(y_pred, Td{1e-7}, Td{1.0} - Td{1e-7});
// Probabilities for taget values
// only if categorical labes
if (y_true.cols() == 1){
for (uint64_t i = 0; i < y_true.rows(); ++i){
const uint64_t idx = static_cast<uint64_t>(y_true(i, 0));
correct_confidences[i] = y_pred_clipped(i, idx);
}
// Losses
utils::Vector<Td> negative_log_likelihoods(samples, Td{0});
for (uint64_t i = 0; i < samples; ++i){
negative_log_likelihoods[i] = -std::log(static_cast<Td>(correct_confidences[i]));
}
}else{ // Mask values - only for one-hot encoded labels
correct_confidences = numerics::matdot_row(y_pred_clipped, cast_y_true);
return negative_log_likelihoods;
}
// Losses
utils::Vector<Td> negative_log_likelihoods(samples, Td{0});
for (uint64_t i = 0; i < samples; ++i){
negative_log_likelihoods[i] = -std::log(static_cast<Td>(correct_confidences[i]));
}
return negative_log_likelihoods;
}
void backward(const utils::Matrix<Td>& dvalues, const utils::Matrix<Ti>& y_true) override{
// Number of samples
const Td samples = static_cast<Td> (y_true.rows());
// Number of labels in every sample
// We'll use the first samle to count them
const Ti labels = dvalues.cols();
utils::Matrix<Ti> y_temp;
if (y_true.cols() == 1){
y_temp = utils::eye(labels, y_true.get_col(0));
}else{
y_temp = y_true;
}
// Calculate the gradient
numerics::inplace_matscalar(y_temp,Ti{-1});
dinputs = numerics::matdiv(utils::matcast<Td, Ti>(y_temp), dvalues);
numerics::inplace_matdiv(dinputs, samples);
}
};