Fixed some problems with visualizing networks

src/captcha.c

@@ -41,13 +41,13 @@ void train_captcha2(char *cfgfile, char *weightfile)
     //net.seen=0;
     int imgs = 1024;
     int i = net.seen/imgs;
-    int solved = 1;
+    int solved = 0;
     list *plist;
     char **labels = get_labels("/data/captcha/reimgs.labels2.list");
     if (solved){
         plist = get_paths("/data/captcha/reimgs.solved.list");
     }else{
-        plist = get_paths("/data/captcha/reimgs.train.list");
+        plist = get_paths("/data/captcha/reimgs.raw.list");
     }
     char **paths = (char **)list_to_array(plist);
     printf("%d\n", plist->size);
@@ -96,7 +96,6 @@ void test_captcha2(char *cfgfile, char *weightfile, char *filename)
     srand(2222222);
     int i = 0;
     char **names = get_labels("/data/captcha/reimgs.labels2.list");
-    clock_t time;
     char input[256];
     int indexes[26];
     while(1){
@@ -110,7 +109,6 @@ void test_captcha2(char *cfgfile, char *weightfile, char *filename)
         }
         image im = load_image_color(input, net.w, net.h);
         float *X = im.data;
-        time=clock();
         float *predictions = network_predict(net, X);
         top_predictions(net, 26, indexes);
         //printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
@@ -126,6 +124,47 @@ void test_captcha2(char *cfgfile, char *weightfile, char *filename)
     }
 }
 
+void valid_captcha(char *cfgfile, char *weightfile, char *filename)
+{
+    char **labels = get_labels("/data/captcha/reimgs.labels.list");
+    network net = parse_network_cfg(cfgfile);
+    if(weightfile){
+        load_weights(&net, weightfile);
+    }
+    list *plist = get_paths("/data/captcha/reimgs.fg.list");
+    char **paths = (char **)list_to_array(plist);
+    int N = plist->size;
+    int outputs = net.outputs;
+
+    set_batch_network(&net, 1);
+    srand(2222222);
+    int i, j;
+    for(i = 0; i < N; ++i){
+        if (i%100 == 0) fprintf(stderr, "%d\n", i);
+        image im = load_image_color(paths[i], net.w, net.h);
+        float *X = im.data;
+        float *predictions = network_predict(net, X);
+        //printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
+        int truth = -1;
+        for(j = 0; j < 13; ++j){
+            if (strstr(paths[i], labels[j])) truth = j;
+        }
+        if (truth == -1){
+            fprintf(stderr, "bad: %s\n", paths[i]);
+            return;
+        }
+        printf("%d, ", truth);
+        for(j = 0; j < outputs; ++j){
+            if (j != 0) printf(", ");
+            printf("%f", predictions[j]);
+        }
+        printf("\n");
+        fflush(stdout);
+        free_image(im);
+        if (filename) break;
+    }
+}
+
 void train_captcha(char *cfgfile, char *weightfile)
 {
     data_seed = time(0);
@@ -189,7 +228,6 @@ void test_captcha(char *cfgfile, char *weightfile, char *filename)
     srand(2222222);
     int i = 0;
     char **names = get_labels("/data/captcha/reimgs.labels.list");
-    clock_t time;
     char input[256];
     int indexes[13];
     while(1){
@@ -203,7 +241,6 @@ void test_captcha(char *cfgfile, char *weightfile, char *filename)
         }
         image im = load_image_color(input, net.w, net.h);
         float *X = im.data;
-        time=clock();
         float *predictions = network_predict(net, X);
         top_predictions(net, 13, indexes);
         //printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
@@ -400,6 +437,7 @@ void run_captcha(int argc, char **argv)
     char *filename = (argc > 5) ? argv[5]: 0;
     if(0==strcmp(argv[2], "train")) train_captcha2(cfg, weights);
     else if(0==strcmp(argv[2], "test")) test_captcha2(cfg, weights, filename);
+    else if(0==strcmp(argv[2], "valid")) valid_captcha(cfg, weights, filename);
     //if(0==strcmp(argv[2], "test")) test_captcha(cfg, weights);
     //else if(0==strcmp(argv[2], "encode")) encode_captcha(cfg, weights);
     //else if(0==strcmp(argv[2], "decode")) decode_captcha(cfg, weights);

src/convolutional_layer.c

@@ -248,6 +248,7 @@ image *get_filters(convolutional_layer l)
     int i;
     for(i = 0; i < l.n; ++i){
         filters[i] = copy_image(get_convolutional_filter(l, i));
+        normalize_image(filters[i]);
     }
     return filters;
 }

src/data.c

@@ -197,8 +197,6 @@ void fill_truth_detection(char *path, float *truth, int classes, int num_boxes,
         h = constrain(0, 1, h);
         if (w < .01 || h < .01) continue;
         if(1){
-            //w = sqrt(w);
-            //h = sqrt(h);
             w = pow(w, 1./2.);
             h = pow(h, 1./2.);
         }

src/image.c

@@ -188,7 +188,7 @@ void show_image_cv(image p, char *name)
     int x,y,k;
     image copy = copy_image(p);
     constrain_image(copy);
-    rgbgr_image(copy);
+    if(p.c == 3) rgbgr_image(copy);
     //normalize_image(copy);
 
     char buff[256];
@@ -849,8 +849,16 @@ image collapse_images_horz(image *ims, int n)
 void show_images(image *ims, int n, char *window)
 {
     image m = collapse_images_vert(ims, n);
-    save_image(m, window);
+    int w = 448;
-    show_image(m, window);
+    int h = ((float)m.h/m.w) * 448;
+    if(h > 896){
+        h = 896;
+        w = ((float)m.w/m.h) * 896;
+    }
+    image sized = resize_image(m, w, h);
+    save_image(sized, window);
+    show_image(sized, window);
+    free_image(sized);
     free_image(m);
 }
 

src/imagenet.c

@@ -47,7 +47,7 @@ void train_imagenet(char *cfgfile, char *weightfile)
         avg_loss = avg_loss*.9 + loss*.1;
         printf("%d: %f, %f avg, %lf seconds, %d images\n", i, loss, avg_loss, sec(clock()-time), net.seen);
         free_data(train);
-        if((i % 20000) == 0) net.learning_rate *= .1;
+        if((i % 30000) == 0) net.learning_rate *= .1;
         if(i%1000==0){
             char buff[256];
             sprintf(buff, "/home/pjreddie/imagenet_backup/%s_%d.weights",base, i);

src/network.c

@@ -125,13 +125,20 @@ float *get_network_output(network net)
 
 float get_network_cost(network net)
 {
+    int i;
+    float sum = 0;
+    int count = 0;
+    for(i = 0; i < net.n; ++i){
         if(net.layers[net.n-1].type == COST){
-        return net.layers[net.n-1].output[0];
+            sum += net.layers[net.n-1].output[0];
+            ++count;
         }
         if(net.layers[net.n-1].type == DETECTION){
-        return net.layers[net.n-1].cost[0];
+            sum += net.layers[net.n-1].cost[0];
+            ++count;
         }
-    return 0;
+    }
+    return sum/count;
 }
 
 int get_predicted_class_network(network net)
@@ -184,9 +191,9 @@ void backward_network(network net, network_state state)
 
 float train_network_datum(network net, float *x, float *y)
 {
-    #ifdef GPU
+#ifdef GPU
     if(gpu_index >= 0) return train_network_datum_gpu(net, x, y);
-    #endif
+#endif
     network_state state;
     state.input = x;
     state.delta = 0;