updates and things

Joseph Redmon

2016-09-01 8f1b4e0962857d402f9d017fcbf387ef0eceb7c4

 src/coco.c

@@ -6,11 +6,14 @@
#include "utils.h"
#include "parser.h"
#include "box.h"
#include "demo.h"

#ifdef OPENCV
#include "opencv2/highgui/highgui_c.h"
#endif

void convert_detections(float *predictions, int classes, int num, int square, int side, int w, int h, float thresh, float **probs, box *boxes, int only_objectness);

char *coco_classes[] = {"person","bicycle","car","motorcycle","airplane","bus","train","truck","boat","traffic light","fire hydrant","stop sign","parking meter","bench","bird","cat","dog","horse","sheep","cow","elephant","bear","zebra","giraffe","backpack","umbrella","handbag","tie","suitcase","frisbee","skis","snowboard","sports ball","kite","baseball bat","baseball glove","skateboard","surfboard","tennis racket","bottle","wine glass","cup","fork","knife","spoon","bowl","banana","apple","sandwich","orange","broccoli","carrot","hot dog","pizza","donut","cake","chair","couch","potted plant","bed","dining table","toilet","tv","laptop","mouse","remote","keyboard","cell phone","microwave","oven","toaster","sink","refrigerator","book","clock","vase","scissors","teddy bear","hair drier","toothbrush"};

int coco_ids[] = {1,2,3,4,5,6,7,8,9,10,11,13,14,15,16,17,18,19,20,21,22,23,24,25,27,28,31,32,33,34,35,36,37,38,39,40,41,42,43,44,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,67,70,72,73,74,75,76,77,78,79,80,81,82,84,85,86,87,88,89,90};
@@ -22,6 +25,7 @@
    //char *train_images = "/home/pjreddie/data/voc/test/train.txt";
    //char *train_images = "/home/pjreddie/data/coco/train.txt";
    char *train_images = "data/coco.trainval.txt";
    //char *train_images = "data/bags.train.list";
    char *backup_directory = "/home/pjreddie/backup/";
    srand(time(0));
    data_seed = time(0);
@@ -60,6 +64,11 @@
    args.d = &buffer;
    args.type = REGION_DATA;

    args.angle = net.angle;
    args.exposure = net.exposure;
    args.saturation = net.saturation;
    args.hue = net.hue;

    pthread_t load_thread = load_data_in_thread(args);
    clock_t time;
    //while(i*imgs < N*120){
@@ -86,11 +95,16 @@
        avg_loss = avg_loss*.9 + loss*.1;

        printf("%d: %f, %f avg, %f rate, %lf seconds, %d images\n", i, loss, avg_loss, get_current_rate(net), sec(clock()-time), i*imgs);
        if(i%1000==0){
        if(i%1000==0 || (i < 1000 && i%100 == 0)){
            char buff[256];
            sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
            save_weights(net, buff);
        }
        if(i%100==0){
            char buff[256];
            sprintf(buff, "%s/%s.backup", backup_directory, base);
            save_weights(net, buff);
        }
        free_data(train);
    }
    char buff[256];
@@ -98,34 +112,6 @@
    save_weights(net, buff);
}

void convert_coco_detections(float *predictions, int classes, int num, int square, int side, int w, int h, float thresh, float **probs, box *boxes, int only_objectness)
{
    int i,j,n;
    //int per_cell = 5*num+classes;
    for (i = 0; i < side*side; ++i){
        int row = i / side;
        int col = i % side;
        for(n = 0; n < num; ++n){
            int index = i*num + n;
            int p_index = side*side*classes + i*num + n;
            float scale = predictions[p_index];
            int box_index = side*side*(classes + num) + (i*num + n)*4;
            boxes[index].x = (predictions[box_index + 0] + col) / side * w;
            boxes[index].y = (predictions[box_index + 1] + row) / side * h;
            boxes[index].w = pow(predictions[box_index + 2], (square?2:1)) * w;
            boxes[index].h = pow(predictions[box_index + 3], (square?2:1)) * h;
            for(j = 0; j < classes; ++j){
                int class_index = i*classes;
                float prob = scale*predictions[class_index+j];
                probs[index][j] = (prob > thresh) ? prob : 0;
            }
            if(only_objectness){
                probs[index][0] = scale;
            }
        }
    }
}

void print_cocos(FILE *fp, int image_id, box *boxes, float **probs, int num_boxes, int classes, int w, int h)
{
    int i, j;
@@ -235,7 +221,7 @@
            float *predictions = network_predict(net, X);
            int w = val[t].w;
            int h = val[t].h;
            convert_coco_detections(predictions, classes, l.n, square, side, w, h, thresh, probs, boxes, 0);
            convert_detections(predictions, classes, l.n, square, side, w, h, thresh, probs, boxes, 0);
            if (nms) do_nms_sort(boxes, probs, side*side*l.n, classes, iou_thresh);
            print_cocos(fp, image_id, boxes, probs, side*side*l.n, classes, w, h);
            free_image(val[t]);
@@ -298,7 +284,7 @@
        image sized = resize_image(orig, net.w, net.h);
        char *id = basecfg(path);
        float *predictions = network_predict(net, sized.data);
        convert_coco_detections(predictions, classes, l.n, square, side, 1, 1, thresh, probs, boxes, 1);
        convert_detections(predictions, classes, l.n, square, side, 1, 1, thresh, probs, boxes, 1);
        if (nms) do_nms(boxes, probs, side*side*l.n, 1, nms_thresh);

        char *labelpath = find_replace(path, "images", "labels");
@@ -370,12 +356,11 @@
        time=clock();
        float *predictions = network_predict(net, X);
        printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
        convert_coco_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, probs, boxes, 0);
        convert_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, probs, boxes, 0);
        if (nms) do_nms_sort(boxes, probs, l.side*l.side*l.n, l.classes, nms);
        draw_detections(im, l.side*l.side*l.n, thresh, boxes, probs, coco_classes, coco_labels, 80);
        save_image(im, "prediction");
        show_image(im, "predictions");

        show_image(sized, "resized");
        free_image(im);
        free_image(sized);
#ifdef OPENCV
@@ -386,16 +371,6 @@
    }
}

void demo_coco(char *cfgfile, char *weightfile, float thresh, int cam_index, char *filename);
static void demo(char *cfgfile, char *weightfile, float thresh, int cam_index, char* filename)
{
    #if defined(OPENCV) && defined(GPU)
        demo_coco(cfgfile, weightfile, thresh, cam_index, filename);
    #else
        fprintf(stderr, "Need to compile with GPU and OpenCV for demo.\n");
    #endif
}

void run_coco(int argc, char **argv)
{
    int i;
@@ -406,7 +381,7 @@
    }
    float thresh = find_float_arg(argc, argv, "-thresh", .2);
    int cam_index = find_int_arg(argc, argv, "-c", 0);
    char *file = find_char_arg(argc, argv, "-file", 0);
    int frame_skip = find_int_arg(argc, argv, "-s", 0);

    if(argc < 4){
        fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
@@ -420,5 +395,5 @@
    else if(0==strcmp(argv[2], "train")) train_coco(cfg, weights);
    else if(0==strcmp(argv[2], "valid")) validate_coco(cfg, weights);
    else if(0==strcmp(argv[2], "recall")) validate_coco_recall(cfg, weights);
    else if(0==strcmp(argv[2], "demo")) demo(cfg, weights, thresh, cam_index, file);
    else if(0==strcmp(argv[2], "demo")) demo(cfg, weights, thresh, cam_index, filename, coco_classes, coco_labels, 80, frame_skip);
}