| | |
| | | #include <string.h> |
| | | #include <stdlib.h> |
| | | |
| | | layer make_yolo_layer(int batch, int w, int h, int n, int total, int *mask, int classes) |
| | | layer make_yolo_layer(int batch, int w, int h, int n, int total, int *mask, int classes, int max_boxes) |
| | | { |
| | | int i; |
| | | layer l = {0}; |
| | |
| | | l.bias_updates = calloc(n*2, sizeof(float)); |
| | | l.outputs = h*w*n*(classes + 4 + 1); |
| | | l.inputs = l.outputs; |
| | | l.truths = 90*(4 + 1); |
| | | l.max_boxes = max_boxes; |
| | | l.truths = l.max_boxes*(4 + 1); // 90*(4 + 1); |
| | | l.delta = calloc(batch*l.outputs, sizeof(float)); |
| | | l.output = calloc(batch*l.outputs, sizeof(float)); |
| | | for(i = 0; i < total*2; ++i){ |
| | |
| | | return batch*l.outputs + n*l.w*l.h*(4+l.classes+1) + entry*l.w*l.h + loc; |
| | | } |
| | | |
| | | static box float_to_box_stride(float *f, int stride) |
| | | { |
| | | box b = { 0 }; |
| | | b.x = f[0]; |
| | | b.y = f[1 * stride]; |
| | | b.w = f[2 * stride]; |
| | | b.h = f[3 * stride]; |
| | | return b; |
| | | } |
| | | |
| | | void forward_yolo_layer(const layer l, network_state state) |
| | | { |
| | | int i,j,b,t,n; |
| | |
| | | float best_iou = 0; |
| | | int best_t = 0; |
| | | for(t = 0; t < l.max_boxes; ++t){ |
| | | box truth = float_to_box(state.truth + t*(4 + 1) + b*l.truths, 1); |
| | | box truth = float_to_box_stride(state.truth + t*(4 + 1) + b*l.truths, 1); |
| | | if(!truth.x) break; |
| | | float iou = box_iou(pred, truth); |
| | | if (iou > best_iou) { |
| | |
| | | if (l.map) class = l.map[class]; |
| | | int class_index = entry_index(l, b, n*l.w*l.h + j*l.w + i, 4 + 1); |
| | | delta_yolo_class(l.output, l.delta, class_index, class, l.classes, l.w*l.h, 0); |
| | | box truth = float_to_box(state.truth + best_t*(4 + 1) + b*l.truths, 1); |
| | | box truth = float_to_box_stride(state.truth + best_t*(4 + 1) + b*l.truths, 1); |
| | | delta_yolo_box(truth, l.output, l.biases, l.mask[n], box_index, i, j, l.w, l.h, state.net.w, state.net.h, l.delta, (2-truth.w*truth.h), l.w*l.h); |
| | | } |
| | | } |
| | | } |
| | | } |
| | | for(t = 0; t < l.max_boxes; ++t){ |
| | | box truth = float_to_box(state.truth + t*(4 + 1) + b*l.truths, 1); |
| | | box truth = float_to_box_stride(state.truth + t*(4 + 1) + b*l.truths, 1); |
| | | |
| | | if(!truth.x) break; |
| | | float best_iou = 0; |
| | |
| | | return; |
| | | } |
| | | |
| | | cuda_pull_array(l.output_gpu, state.input, l.batch*l.inputs); |
| | | forward_yolo_layer(l, state); |
| | | //cuda_pull_array(l.output_gpu, state.input, l.batch*l.inputs); |
| | | float *in_cpu = calloc(l.batch*l.inputs, sizeof(float)); |
| | | cuda_pull_array(l.output_gpu, in_cpu, l.batch*l.inputs); |
| | | float *truth_cpu = 0; |
| | | if (state.truth) { |
| | | int num_truth = l.batch*l.truths; |
| | | truth_cpu = calloc(num_truth, sizeof(float)); |
| | | cuda_pull_array(state.truth, truth_cpu, num_truth); |
| | | } |
| | | network_state cpu_state = state; |
| | | cpu_state.net = state.net; |
| | | cpu_state.index = state.index; |
| | | cpu_state.train = state.train; |
| | | cpu_state.truth = truth_cpu; |
| | | cpu_state.input = in_cpu; |
| | | forward_yolo_layer(l, cpu_state); |
| | | //forward_yolo_layer(l, state); |
| | | cuda_push_array(l.delta_gpu, l.delta, l.batch*l.outputs); |
| | | free(in_cpu); |
| | | if (cpu_state.truth) free(cpu_state.truth); |
| | | } |
| | | |
| | | void backward_yolo_layer_gpu(const layer l, network_state state) |