From c40cdeb4021fc1a638969563972f13c9f5e90d74 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Fri, 09 Oct 2015 19:50:43 +0000
Subject: [PATCH] lots of comparator stuff

---
 src/swag.c |  197 ++++++++++++++++++++++++++++++++++++------------
 1 files changed, 147 insertions(+), 50 deletions(-)

diff --git a/src/swag.c b/src/swag.c
index 4dcf36b..8c9ce3c 100644
--- a/src/swag.c
+++ b/src/swag.c
@@ -1,4 +1,5 @@
 #include "network.h"
+#include "region_layer.h"
 #include "detection_layer.h"
 #include "cost_layer.h"
 #include "utils.h"
@@ -11,40 +12,37 @@
 
 char *voc_names[] = {"aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"};
 
-void draw_swag(image im, float *box, int side, int objectness, char *label, float thresh)
+void draw_swag(image im, float *predictions, int side, int num, char *label, float thresh)
 {
     int classes = 20;
-    int elems = 4+classes+objectness;
-    int j;
-    int r, c;
+    int i,n;
 
-    for(r = 0; r < side; ++r){
-        for(c = 0; c < side; ++c){
-            j = (r*side + c) * elems;
-            float scale = 1;
-            if(objectness) scale = 1 - box[j++];
-            int class = max_index(box+j, classes);
-            if(scale * box[j+class] > thresh){
-                int width = sqrt(scale*box[j+class])*5 + 1;
-                printf("%f %s\n", scale * box[j+class], voc_names[class]);
+    for(i = 0; i < side*side; ++i){
+        int row = i / side;
+        int col = i % side;
+        for(n = 0; n < num; ++n){
+            int p_index = side*side*classes + i*num + n;
+            int box_index = side*side*(classes + num) + (i*num + n)*4;
+            int class_index = i*classes;
+            float scale = predictions[p_index];
+            int class = max_index(predictions+class_index, classes);
+            float prob = scale * predictions[class_index + class];
+            if(prob > thresh){
+                int width = sqrt(prob)*5 + 1;
+                printf("%f %s\n", prob, voc_names[class]);
                 float red = get_color(0,class,classes);
                 float green = get_color(1,class,classes);
                 float blue = get_color(2,class,classes);
+                box b = float_to_box(predictions+box_index);
+                b.x = (b.x + col)/side;
+                b.y = (b.y + row)/side;
+                b.w = b.w*b.w;
+                b.h = b.h*b.h;
 
-                j += classes;
-                float x = box[j+0];
-                float y = box[j+1];
-                x = (x+c)/side;
-                y = (y+r)/side;
-                float w = box[j+2]; //*maxwidth;
-                float h = box[j+3]; //*maxheight;
-                h = h*h;
-                w = w*w;
-
-                int left  = (x-w/2)*im.w;
-                int right = (x+w/2)*im.w;
-                int top   = (y-h/2)*im.h;
-                int bot   = (y+h/2)*im.h;
+                int left  = (b.x-b.w/2)*im.w;
+                int right = (b.x+b.w/2)*im.w;
+                int top   = (b.y-b.h/2)*im.h;
+                int bot   = (b.y+b.h/2)*im.h;
                 draw_box_width(im, left, top, right, bot, width, red, green, blue);
             }
         }
@@ -75,9 +73,10 @@
 
     int side = l.side;
     int classes = l.classes;
+    float jitter = l.jitter;
 
     list *plist = get_paths(train_images);
-    int N = plist->size;
+    //int N = plist->size;
     char **paths = (char **)list_to_array(plist);
 
     load_args args = {0};
@@ -87,6 +86,7 @@
     args.n = imgs;
     args.m = plist->size;
     args.classes = classes;
+    args.jitter = jitter;
     args.num_boxes = side;
     args.d = &buffer;
     args.type = REGION_DATA;
@@ -103,13 +103,13 @@
 
         printf("Loaded: %lf seconds\n", sec(clock()-time));
 
-/*
-        image im = float_to_image(net.w, net.h, 3, train.X.vals[113]);
-        image copy = copy_image(im);
-        draw_swag(copy, train.y.vals[113], 7, "truth");
-        cvWaitKey(0);
-        free_image(copy);
-        */
+        /*
+           image im = float_to_image(net.w, net.h, 3, train.X.vals[113]);
+           image copy = copy_image(im);
+           draw_swag(copy, train.y.vals[113], 7, "truth");
+           cvWaitKey(0);
+           free_image(copy);
+         */
 
         time=clock();
         float loss = train_network(net, train);
@@ -129,26 +129,30 @@
     save_weights(net, buff);
 }
 
-void convert_swag_detections(float *predictions, int classes, int num, int square, int side, int w, int h, float thresh, float **probs, box *boxes)
+void convert_swag_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;
+    //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 offset = i*per_cell + 5*n;
-            float scale = predictions[offset];
             int index = i*num + n;
-            boxes[index].x = (predictions[offset + 1] + col) / side * w;
-            boxes[index].y = (predictions[offset + 2] + row) / side * h;
-            boxes[index].w = pow(predictions[offset + 3], (square?2:1)) * w;
-            boxes[index].h = pow(predictions[offset + 4], (square?2:1)) * h;
+            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){
-                offset = i*per_cell + 5*num;
-                float prob = scale*predictions[offset+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;
+            }
         }
     }
 }
@@ -251,7 +255,7 @@
             float *predictions = network_predict(net, X);
             int w = val[t].w;
             int h = val[t].h;
-            convert_swag_detections(predictions, classes, l.n, square, side, w, h, thresh, probs, boxes);
+            convert_swag_detections(predictions, classes, l.n, square, side, w, h, thresh, probs, boxes, 0);
             if (nms) do_nms(boxes, probs, side*side*l.n, classes, iou_thresh);
             print_swag_detections(fps, id, boxes, probs, side*side*l.n, classes, w, h);
             free(id);
@@ -262,6 +266,95 @@
     fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start));
 }
 
+void validate_swag_recall(char *cfgfile, char *weightfile)
+{
+    network net = parse_network_cfg(cfgfile);
+    if(weightfile){
+        load_weights(&net, weightfile);
+    }
+    set_batch_network(&net, 1);
+    fprintf(stderr, "Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
+    srand(time(0));
+
+    char *base = "results/comp4_det_test_";
+    list *plist = get_paths("/home/pjreddie/data/voc/test/2007_test.txt");
+    char **paths = (char **)list_to_array(plist);
+
+    layer l = net.layers[net.n-1];
+    int classes = l.classes;
+    int square = l.sqrt;
+    int side = l.side;
+
+    int j, k;
+    FILE **fps = calloc(classes, sizeof(FILE *));
+    for(j = 0; j < classes; ++j){
+        char buff[1024];
+        snprintf(buff, 1024, "%s%s.txt", base, voc_names[j]);
+        fps[j] = fopen(buff, "w");
+    }
+    box *boxes = calloc(side*side*l.n, sizeof(box));
+    float **probs = calloc(side*side*l.n, sizeof(float *));
+    for(j = 0; j < side*side*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
+
+    int m = plist->size;
+    int i=0;
+
+    float thresh = .001;
+    int nms = 0;
+    float iou_thresh = .5;
+    float nms_thresh = .5;
+
+    int total = 0;
+    int correct = 0;
+    int proposals = 0;
+    float avg_iou = 0;
+
+    for(i = 0; i < m; ++i){
+        char *path = paths[i];
+        image orig = load_image_color(path, 0, 0);
+        image sized = resize_image(orig, net.w, net.h);
+        char *id = basecfg(path);
+        float *predictions = network_predict(net, sized.data);
+        int w = orig.w;
+        int h = orig.h;
+        convert_swag_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");
+        labelpath = find_replace(labelpath, "JPEGImages", "labels");
+        labelpath = find_replace(labelpath, ".jpg", ".txt");
+        labelpath = find_replace(labelpath, ".JPEG", ".txt");
+
+        int num_labels = 0;
+        box_label *truth = read_boxes(labelpath, &num_labels);
+        for(k = 0; k < side*side*l.n; ++k){
+            if(probs[k][0] > thresh){
+                ++proposals;
+            }
+        }
+        for (j = 0; j < num_labels; ++j) {
+            ++total;
+            box t = {truth[j].x, truth[j].y, truth[j].w, truth[j].h};
+            float best_iou = 0;
+            for(k = 0; k < side*side*l.n; ++k){
+                float iou = box_iou(boxes[k], t);
+                if(probs[k][0] > thresh && iou > best_iou){
+                    best_iou = iou;
+                }
+            }
+            avg_iou += best_iou;
+            if(best_iou > iou_thresh){
+                ++correct;
+            }
+        }
+
+        fprintf(stderr, "%5d %5d %5d\tRPs/Img: %.2f\tIOU: %.2f%%\tRecall:%.2f%%\n", i, correct, total, (float)proposals/(i+1), avg_iou*100/total, 100.*correct/total);
+        free(id);
+        free_image(orig);
+        free_image(sized);
+    }
+}
+
 void test_swag(char *cfgfile, char *weightfile, char *filename, float thresh)
 {
 
@@ -269,18 +362,20 @@
     if(weightfile){
         load_weights(&net, weightfile);
     }
-    detection_layer layer = get_network_detection_layer(net);
+    region_layer layer = net.layers[net.n-1];
     set_batch_network(&net, 1);
     srand(2222222);
     clock_t time;
-    char input[256];
+    char buff[256];
+    char *input = buff;
     while(1){
         if(filename){
             strncpy(input, filename, 256);
         } else {
             printf("Enter Image Path: ");
             fflush(stdout);
-            fgets(input, 256, stdin);
+            input = fgets(input, 256, stdin);
+            if(!input) return;
             strtok(input, "\n");
         }
         image im = load_image_color(input,0,0);
@@ -289,7 +384,8 @@
         time=clock();
         float *predictions = network_predict(net, X);
         printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
-        draw_swag(im, predictions, 7, layer.objectness, "predictions", thresh);
+        draw_swag(im, predictions, layer.side, layer.n, "predictions", thresh);
+        show_image(sized, "resized");
         free_image(im);
         free_image(sized);
 #ifdef OPENCV
@@ -314,4 +410,5 @@
     if(0==strcmp(argv[2], "test")) test_swag(cfg, weights, filename, thresh);
     else if(0==strcmp(argv[2], "train")) train_swag(cfg, weights);
     else if(0==strcmp(argv[2], "valid")) validate_swag(cfg, weights);
+    else if(0==strcmp(argv[2], "recall")) validate_swag_recall(cfg, weights);
 }

--
Gitblit v1.10.0