| | |
| | | int batch_num = get_current_batch(net); |
| | | int i; |
| | | float rate; |
| | | if (batch_num < net.burn_in) return net.learning_rate * pow((float)batch_num / net.burn_in, net.power); |
| | | switch (net.policy) { |
| | | case CONSTANT: |
| | | return net.learning_rate; |
| | |
| | | case EXP: |
| | | return net.learning_rate * pow(net.gamma, batch_num); |
| | | case POLY: |
| | | if (batch_num < net.burn_in) return net.learning_rate * pow((float)batch_num / net.burn_in, net.power); |
| | | return net.learning_rate * pow(1 - (float)batch_num / net.max_batches, net.power); |
| | | return net.learning_rate * pow(1 - (float)batch_num / net.max_batches, net.power); |
| | | //if (batch_num < net.burn_in) return net.learning_rate * pow((float)batch_num / net.burn_in, net.power); |
| | | //return net.learning_rate * pow(1 - (float)batch_num / net.max_batches, net.power); |
| | | case RANDOM: |
| | | return net.learning_rate * pow(rand_uniform(0,1), net.power); |
| | | case SIG: |
| | |
| | | state.delta = prev.delta; |
| | | } |
| | | layer l = net.layers[i]; |
| | | if (l.stopbackward) break; |
| | | l.backward(l, state); |
| | | } |
| | | } |
| | |
| | | }else if(l.type == COST){ |
| | | resize_cost_layer(&l, inputs); |
| | | }else{ |
| | | fprintf(stderr, "Resizing type %d \n", (int)l.type); |
| | | error("Cannot resize this type of layer"); |
| | | } |
| | | if(l.workspace_size > workspace_size) workspace_size = l.workspace_size; |