| | |
| | | |
| | | #define DOABS 1 |
| | | |
| | | region_layer make_region_layer(int batch, int w, int h, int n, int classes, int coords) |
| | | region_layer make_region_layer(int batch, int w, int h, int n, int classes, int coords, int max_boxes) |
| | | { |
| | | region_layer l = {0}; |
| | | l.type = REGION; |
| | |
| | | l.bias_updates = calloc(n*2, sizeof(float)); |
| | | l.outputs = h*w*n*(classes + coords + 1); |
| | | l.inputs = l.outputs; |
| | | l.truths = 30*(5); |
| | | l.max_boxes = max_boxes; |
| | | l.truths = max_boxes*(5); |
| | | l.delta = calloc(batch*l.outputs, sizeof(float)); |
| | | l.output = calloc(batch*l.outputs, sizeof(float)); |
| | | int i; |
| | |
| | | l.delta_gpu = cuda_make_array(l.delta, batch*l.outputs); |
| | | #endif |
| | | |
| | | fprintf(stderr, "Region Layer\n"); |
| | | fprintf(stderr, "detection\n"); |
| | | srand(0); |
| | | |
| | | return l; |
| | |
| | | |
| | | void resize_region_layer(layer *l, int w, int h) |
| | | { |
| | | int old_w = l->w; |
| | | int old_h = l->h; |
| | | l->w = w; |
| | | l->h = h; |
| | | |
| | |
| | | l->delta = realloc(l->delta, l->batch*l->outputs*sizeof(float)); |
| | | |
| | | #ifdef GPU |
| | | cuda_free(l->delta_gpu); |
| | | cuda_free(l->output_gpu); |
| | | if (old_w < w || old_h < h) { |
| | | cuda_free(l->delta_gpu); |
| | | cuda_free(l->output_gpu); |
| | | |
| | | l->delta_gpu = cuda_make_array(l->delta, l->batch*l->outputs); |
| | | l->output_gpu = cuda_make_array(l->output, l->batch*l->outputs); |
| | | l->delta_gpu = cuda_make_array(l->delta, l->batch*l->outputs); |
| | | l->output_gpu = cuda_make_array(l->output, l->batch*l->outputs); |
| | | } |
| | | #endif |
| | | } |
| | | |
| | |
| | | for (b = 0; b < l.batch; ++b){ |
| | | for(i = 0; i < l.h*l.w*l.n; ++i){ |
| | | int index = size*i + b*l.outputs; |
| | | softmax(l.output + index + 5, l.classes, 1, l.output + index + 5); |
| | | softmax(l.output + index + 5, l.classes, 1, l.output + index + 5, 1); |
| | | } |
| | | } |
| | | } |
| | |
| | | for (b = 0; b < l.batch; ++b) { |
| | | if(l.softmax_tree){ |
| | | int onlyclass = 0; |
| | | for(t = 0; t < 30; ++t){ |
| | | for(t = 0; t < l.max_boxes; ++t){ |
| | | box truth = float_to_box(state.truth + t*5 + b*l.truths); |
| | | if(!truth.x) break; |
| | | int class = state.truth[t*5 + b*l.truths + 4]; |
| | |
| | | if(truth.x > 100000 && truth.y > 100000){ |
| | | for(n = 0; n < l.n*l.w*l.h; ++n){ |
| | | int index = size*n + b*l.outputs + 5; |
| | | float p = get_hierarchy_probability(l.output + index, l.softmax_tree, class); |
| | | float scale = l.output[index-1]; |
| | | float p = scale*get_hierarchy_probability(l.output + index, l.softmax_tree, class); |
| | | if(p > maxp){ |
| | | maxp = p; |
| | | maxi = n; |
| | |
| | | box pred = get_region_box(l.output, l.biases, n, index, i, j, l.w, l.h); |
| | | float best_iou = 0; |
| | | int best_class = -1; |
| | | for(t = 0; t < 30; ++t){ |
| | | for(t = 0; t < l.max_boxes; ++t){ |
| | | box truth = float_to_box(state.truth + t*5 + b*l.truths); |
| | | if(!truth.x) break; |
| | | float iou = box_iou(pred, truth); |
| | |
| | | } |
| | | } |
| | | } |
| | | for(t = 0; t < 30; ++t){ |
| | | for(t = 0; t < l.max_boxes; ++t){ |
| | | box truth = float_to_box(state.truth + t*5 + b*l.truths); |
| | | |
| | | if(!truth.x) break; |
| | |
| | | axpy_cpu(l.batch*l.inputs, 1, l.delta, 1, state.delta, 1); |
| | | } |
| | | |
| | | void get_region_boxes(layer l, int w, int h, float thresh, float **probs, box *boxes, int only_objectness) |
| | | void get_region_boxes(layer l, int w, int h, float thresh, float **probs, box *boxes, int only_objectness, int *map) |
| | | { |
| | | int i,j,n; |
| | | float *predictions = l.output; |
| | |
| | | |
| | | hierarchy_predictions(predictions + class_index, l.classes, l.softmax_tree, 0); |
| | | int found = 0; |
| | | for(j = l.classes - 1; j >= 0; --j){ |
| | | if(1){ |
| | | if(map){ |
| | | for(j = 0; j < 200; ++j){ |
| | | float prob = scale*predictions[class_index+map[j]]; |
| | | probs[index][j] = (prob > thresh) ? prob : 0; |
| | | } |
| | | } else { |
| | | for(j = l.classes - 1; j >= 0; --j){ |
| | | if(!found && predictions[class_index + j] > .5){ |
| | | found = 1; |
| | | } else { |
| | |
| | | } |
| | | float prob = predictions[class_index+j]; |
| | | probs[index][j] = (scale > thresh) ? prob : 0; |
| | | }else{ |
| | | float prob = scale*predictions[class_index+j]; |
| | | probs[index][j] = (prob > thresh) ? prob : 0; |
| | | } |
| | | } |
| | | }else{ |
| | | } else { |
| | | for(j = 0; j < l.classes; ++j){ |
| | | float prob = scale*predictions[class_index+j]; |
| | | probs[index][j] = (prob > thresh) ? prob : 0; |
| | |
| | | cuda_pull_array(state.truth, truth_cpu, num_truth); |
| | | } |
| | | cuda_pull_array(l.output_gpu, in_cpu, l.batch*l.inputs); |
| | | cudaStreamSynchronize(get_cuda_stream()); |
| | | network_state cpu_state = state; |
| | | cpu_state.train = state.train; |
| | | cpu_state.truth = truth_cpu; |
| | |
| | | free(cpu_state.input); |
| | | if(!state.train) return; |
| | | cuda_push_array(l.delta_gpu, l.delta, l.batch*l.outputs); |
| | | cudaStreamSynchronize(get_cuda_stream()); |
| | | if(cpu_state.truth) free(cpu_state.truth); |
| | | } |
| | | |