void forward_cost_layer_gpu(cost_layer l, network_state state)
{
if (!state.truth) return;
if (l.cost_type == MASKED) {
mask_ongpu(l.batch*l.inputs, state.input, state.truth);
}
copy_ongpu(l.batch*l.inputs, state.truth, 1, l.delta_gpu, 1);
axpy_ongpu(l.batch*l.inputs, -1, state.input, 1, l.delta_gpu, 1);
cuda_pull_array(l.delta_gpu, l.delta, l.batch*l.inputs);
*(l.output) = dot_cpu(l.batch*l.inputs, l.delta, 1, l.delta, 1);
}
void forward_cost_layer_gpu(cost_layer l, network_state state)
{
if (!state.truth) return;
if (l.cost_type == MASKED) {
mask_ongpu(l.batch*l.inputs, state.input, SECRET_NUM, state.truth);
}
if(l.cost_type == SMOOTH){
smooth_l1_gpu(l.batch*l.inputs, state.input, state.truth, l.delta_gpu);
} else {
copy_ongpu(l.batch*l.inputs, state.truth, 1, l.delta_gpu, 1);
axpy_ongpu(l.batch*l.inputs, -1, state.input, 1, l.delta_gpu, 1);
}
cuda_pull_array(l.delta_gpu, l.delta, l.batch*l.inputs);
*(l.output) = dot_cpu(l.batch*l.inputs, l.delta, 1, l.delta, 1);
}
void forward_cost_layer_gpu(cost_layer l, network_state state)
{
if (!state.truth) return;
if(l.smooth){
scal_ongpu(l.batch*l.inputs, (1-l.smooth), state.truth, 1);
add_ongpu(l.batch*l.inputs, l.smooth * 1./l.inputs, state.truth, 1);
}
if (l.cost_type == MASKED) {
mask_ongpu(l.batch*l.inputs, state.input, SECRET_NUM, state.truth);
}
if(l.cost_type == SMOOTH){
smooth_l1_gpu(l.batch*l.inputs, state.input, state.truth, l.delta_gpu, l.output_gpu);
} else if (l.cost_type == L1){
l1_gpu(l.batch*l.inputs, state.input, state.truth, l.delta_gpu, l.output_gpu);
} else {
l2_gpu(l.batch*l.inputs, state.input, state.truth, l.delta_gpu, l.output_gpu);
}
if(l.ratio){
cuda_pull_array(l.delta_gpu, l.delta, l.batch*l.inputs);
qsort(l.delta, l.batch*l.inputs, sizeof(float), float_abs_compare);
int n = (1-l.ratio) * l.batch*l.inputs;
float thresh = l.delta[n];
thresh = 0;
printf("%f\n", thresh);
supp_ongpu(l.batch*l.inputs, thresh, l.delta_gpu, 1);
}
if(l.thresh){
supp_ongpu(l.batch*l.inputs, l.thresh*1./l.inputs, l.delta_gpu, 1);
}
cuda_pull_array(l.output_gpu, l.output, l.batch*l.inputs);
l.cost[0] = sum_array(l.output, l.batch*l.inputs);
}
