| | |
| | | return "sse"; |
| | | } |
| | | |
| | | cost_layer make_cost_layer(int batch, int inputs, COST_TYPE cost_type) |
| | | cost_layer make_cost_layer(int batch, int inputs, COST_TYPE cost_type, float scale) |
| | | { |
| | | fprintf(stderr, "Cost Layer: %d inputs\n", inputs); |
| | | cost_layer l = {0}; |
| | | l.type = COST; |
| | | |
| | | l.scale = scale; |
| | | l.batch = batch; |
| | | l.inputs = inputs; |
| | | l.outputs = inputs; |
| | |
| | | return l; |
| | | } |
| | | |
| | | void resize_cost_layer(cost_layer *l, int inputs) |
| | | { |
| | | l->inputs = inputs; |
| | | l->outputs = inputs; |
| | | l->delta = realloc(l->delta, inputs*l->batch*sizeof(float)); |
| | | #ifdef GPU |
| | | cuda_free(l->delta_gpu); |
| | | l->delta_gpu = cuda_make_array(l->delta, inputs*l->batch); |
| | | #endif |
| | | } |
| | | |
| | | void forward_cost_layer(cost_layer l, network_state state) |
| | | { |
| | | if (!state.truth) return; |
| | |
| | | |
| | | void backward_cost_layer(const cost_layer l, network_state state) |
| | | { |
| | | axpy_cpu(l.batch*l.inputs, 1, l.delta, 1, state.delta, 1); |
| | | axpy_cpu(l.batch*l.inputs, l.scale, l.delta, 1, state.delta, 1); |
| | | } |
| | | |
| | | #ifdef GPU |
| | |
| | | if (l.cost_type == MASKED) { |
| | | mask_ongpu(l.batch*l.inputs, state.input, SECRET_NUM, 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); |
| | | |
| | |
| | | |
| | | void backward_cost_layer_gpu(const cost_layer l, network_state state) |
| | | { |
| | | axpy_ongpu(l.batch*l.inputs, 1, l.delta_gpu, 1, state.delta, 1); |
| | | axpy_ongpu(l.batch*l.inputs, l.scale, l.delta_gpu, 1, state.delta, 1); |
| | | } |
| | | #endif |
| | | |