| | |
| | | truth.y = state.truth[j+1]/7; |
| | | truth.w = pow(state.truth[j+2], 2); |
| | | truth.h = pow(state.truth[j+3], 2); |
| | | |
| | | box out; |
| | | out.x = l.output[j+0]/7; |
| | | out.y = l.output[j+1]/7; |
| | |
| | | float iou = box_iou(out, truth); |
| | | avg_iou += iou; |
| | | ++count; |
| | | dbox delta = diou(out, truth); |
| | | |
| | | l.delta[j+0] = 10 * delta.dx/7; |
| | | l.delta[j+1] = 10 * delta.dy/7; |
| | | l.delta[j+2] = 10 * delta.dw * 2 * sqrt(out.w); |
| | | l.delta[j+3] = 10 * delta.dh * 2 * sqrt(out.h); |
| | | |
| | | |
| | | *(l.cost) += pow((1-iou), 2); |
| | | l.delta[j+0] = 4 * (state.truth[j+0] - l.output[j+0]); |
| | |
| | | float scale = 1; |
| | | float latent_delta = 0; |
| | | if(l.joint) scale = state.input[in_i++]; |
| | | else if (l.objectness) state.delta[in_i++] = -l.delta[out_i++]; |
| | | else if (l.background) state.delta[in_i++] = scale*l.delta[out_i++]; |
| | | else if (l.objectness) state.delta[in_i++] += -l.delta[out_i++]; |
| | | else if (l.background) state.delta[in_i++] += scale*l.delta[out_i++]; |
| | | for(j = 0; j < l.classes; ++j){ |
| | | latent_delta += state.input[in_i]*l.delta[out_i]; |
| | | state.delta[in_i++] = scale*l.delta[out_i++]; |
| | | state.delta[in_i++] += scale*l.delta[out_i++]; |
| | | } |
| | | |
| | | if (l.objectness) { |
| | | |
| | | }else if (l.background) gradient_array(l.output + out_i, l.coords, LOGISTIC, l.delta + out_i); |
| | | for(j = 0; j < l.coords; ++j){ |
| | | state.delta[in_i++] = l.delta[out_i++]; |
| | | state.delta[in_i++] += l.delta[out_i++]; |
| | | } |
| | | if(l.joint) state.delta[in_i-l.coords-l.classes-l.joint] = latent_delta; |
| | | if(l.joint) state.delta[in_i-l.coords-l.classes-l.joint] += latent_delta; |
| | | } |
| | | } |
| | | |
| | |
| | | cpu_state.truth = truth_cpu; |
| | | cpu_state.delta = delta_cpu; |
| | | |
| | | cuda_pull_array(state.input, in_cpu, l.batch*l.inputs); |
| | | cuda_pull_array(state.input, in_cpu, l.batch*l.inputs); |
| | | cuda_pull_array(state.delta, delta_cpu, l.batch*l.inputs); |
| | | cuda_pull_array(l.delta_gpu, l.delta, l.batch*outputs); |
| | | backward_detection_layer(l, cpu_state); |
| | | cuda_push_array(state.delta, delta_cpu, l.batch*l.inputs); |
| | | |
| | | if (truth_cpu) free(truth_cpu); |
| | | free(in_cpu); |
| | | free(delta_cpu); |
| | | } |