Parameter (max) in the cfg-file has an effect on the Yolo-training
| | |
| | | int coords = option_find_int(options, "coords", 4); |
| | | int classes = option_find_int(options, "classes", 20); |
| | | int num = option_find_int(options, "num", 1); |
| | | int max_boxes = option_find_int_quiet(options, "max", 30); |
| | | |
| | | layer l = make_region_layer(params.batch, params.w, params.h, num, classes, coords); |
| | | layer l = make_region_layer(params.batch, params.w, params.h, num, classes, coords, max_boxes); |
| | | assert(l.outputs == params.inputs); |
| | | |
| | | l.log = option_find_int_quiet(options, "log", 0); |
| | | l.sqrt = option_find_int_quiet(options, "sqrt", 0); |
| | | |
| | | l.small_object = option_find_int(options, "small_object", 0); |
| | | l.small_object = option_find_int_quiet(options, "small_object", 0); |
| | | l.softmax = option_find_int(options, "softmax", 0); |
| | | l.max_boxes = option_find_int_quiet(options, "max",30); |
| | | //l.max_boxes = option_find_int_quiet(options, "max",30); |
| | | l.jitter = option_find_float(options, "jitter", .2); |
| | | l.rescore = option_find_int_quiet(options, "rescore",0); |
| | | |
| | |
| | | |
| | | #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; |
| | |
| | | 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]; |
| | |
| | | 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; |
| | |
| | | |
| | | typedef layer region_layer; |
| | | |
| | | region_layer make_region_layer(int batch, int h, int w, int n, int classes, int coords); |
| | | region_layer make_region_layer(int batch, int h, int w, int n, int classes, int coords, int max_boxes); |
| | | void forward_region_layer(const region_layer l, network_state state); |
| | | void backward_region_layer(const region_layer l, network_state state); |
| | | void get_region_boxes(layer l, int w, int h, float thresh, float **probs, box *boxes, int only_objectness, int *map); |