diff --git a/src/avgpool_layer.c b/src/avgpool_layer.c
index c6db477e..b6932fe7 100644
--- a/src/avgpool_layer.c
+++ b/src/avgpool_layer.c
@@ -4,7 +4,7 @@
 
 avgpool_layer make_avgpool_layer(int batch, int w, int h, int c)
 {
-    fprintf(stderr, "Avgpool Layer: %d x %d x %d image\n", w,h,c);
+    fprintf(stderr, "avg                     %4d x%4d x%4d   ->  %4d\n",  w, h, c, c);
     avgpool_layer l = {0};
     l.type = AVGPOOL;
     l.batch = batch;
diff --git a/src/connected_layer.c b/src/connected_layer.c
index 26942292..b678ed0d 100644
--- a/src/connected_layer.c
+++ b/src/connected_layer.c
@@ -100,7 +100,7 @@ connected_layer make_connected_layer(int batch, int inputs, int outputs, ACTIVAT
     }
 #endif
     l.activation = activation;
-    fprintf(stderr, "Connected Layer: %d inputs, %d outputs\n", inputs, outputs);
+    fprintf(stderr, "connected                            %4d  ->  %4d\n", inputs, outputs);
     return l;
 }
 
diff --git a/src/convolutional_layer.c b/src/convolutional_layer.c
index 86285e03..3864c1bc 100644
--- a/src/convolutional_layer.c
+++ b/src/convolutional_layer.c
@@ -300,7 +300,7 @@ convolutional_layer make_convolutional_layer(int batch, int h, int w, int c, int
     l.workspace_size = get_workspace_size(l);
     l.activation = activation;
 
-    fprintf(stderr, "Convolutional Layer: %d x %d x %d image, %d filters -> %d x %d x %d image\n", h,w,c,n, out_h, out_w, n);
+    fprintf(stderr, "conv  %5d %2d x%2d /%2d  %4d x%4d x%4d   ->  %4d x%4d x%4d\n", n, size, size, stride, w, h, c, l.out_w, l.out_h, l.out_c);
 
     return l;
 }
diff --git a/src/cost_layer.c b/src/cost_layer.c
index f266c6a1..39d2398b 100644
--- a/src/cost_layer.c
+++ b/src/cost_layer.c
@@ -31,7 +31,7 @@ char *get_cost_string(COST_TYPE a)
 
 cost_layer make_cost_layer(int batch, int inputs, COST_TYPE cost_type, float scale)
 {
-    fprintf(stderr, "Cost Layer: %d inputs\n", inputs);
+    fprintf(stderr, "cost                                           %4d\n",  inputs);
     cost_layer l = {0};
     l.type = COST;
 
diff --git a/src/detector.c b/src/detector.c
index 3853ebb3..a513816c 100644
--- a/src/detector.c
+++ b/src/detector.c
@@ -136,15 +136,19 @@ void train_detector(char *datacfg, char *cfgfile, char *weightfile, int *gpus, i
 
         i = get_current_batch(net);
         printf("%d: %f, %f avg, %f rate, %lf seconds, %d images\n", get_current_batch(net), loss, avg_loss, get_current_rate(net), sec(clock()-time), i*imgs);
-        if(i%100==0 || (i < 1000 && i%100 == 0)){
+        if(i%1000==0 || (i < 1000 && i%100 == 0)){
+#ifdef GPU
             if(ngpus != 1) sync_nets(nets, ngpus, 0);
+#endif
             char buff[256];
             sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
             save_weights(net, buff);
         }
         free_data(train);
     }
+#ifdef GPU
     if(ngpus != 1) sync_nets(nets, ngpus, 0);
+#endif
     char buff[256];
     sprintf(buff, "%s/%s_final.weights", backup_directory, base);
     save_weights(net, buff);
diff --git a/src/dropout_layer.c b/src/dropout_layer.c
index 82be64b1..b1381e63 100644
--- a/src/dropout_layer.c
+++ b/src/dropout_layer.c
@@ -6,7 +6,6 @@
 
 dropout_layer make_dropout_layer(int batch, int inputs, float probability)
 {
-    fprintf(stderr, "Dropout Layer: %d inputs, %f probability\n", inputs, probability);
     dropout_layer l = {0};
     l.type = DROPOUT;
     l.probability = probability;
@@ -22,6 +21,7 @@ dropout_layer make_dropout_layer(int batch, int inputs, float probability)
     l.backward_gpu = backward_dropout_layer_gpu;
     l.rand_gpu = cuda_make_array(l.rand, inputs*batch);
     #endif
+    fprintf(stderr, "dropout       p = %.2f               %4d  ->  %4d\n", probability, inputs, inputs);
     return l;
 } 
 
diff --git a/src/maxpool_layer.c b/src/maxpool_layer.c
index 49cfeaf5..d1fbacb9 100644
--- a/src/maxpool_layer.c
+++ b/src/maxpool_layer.c
@@ -20,7 +20,6 @@ image get_maxpool_delta(maxpool_layer l)
 
 maxpool_layer make_maxpool_layer(int batch, int h, int w, int c, int size, int stride, int padding)
 {
-    fprintf(stderr, "Maxpool Layer: %d x %d x %d image, %d size, %d stride\n", h,w,c,size,stride);
     maxpool_layer l = {0};
     l.type = MAXPOOL;
     l.batch = batch;
@@ -48,6 +47,7 @@ maxpool_layer make_maxpool_layer(int batch, int h, int w, int c, int size, int s
     l.output_gpu  = cuda_make_array(l.output, output_size);
     l.delta_gpu   = cuda_make_array(l.delta, output_size);
     #endif
+    fprintf(stderr, "max          %d x %d / %d  %4d x%4d x%4d   ->  %4d x%4d x%4d\n", size, size, stride, w, h, c, l.out_w, l.out_h, l.out_c);
     return l;
 }
 
diff --git a/src/parser.c b/src/parser.c
index db4cf368..cde06b4b 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -610,9 +610,10 @@ network parse_network_cfg(char *filename)
     n = n->next;
     int count = 0;
     free_section(s);
+    fprintf(stderr, "layer     filters    size              input                output\n");
     while(n){
         params.index = count;
-        fprintf(stderr, "%d: ", count);
+        fprintf(stderr, "%5d ", count);
         s = (section *)n->val;
         options = s->options;
         layer l = {0};
diff --git a/src/softmax_layer.c b/src/softmax_layer.c
index 0aa9047f..5d153148 100644
--- a/src/softmax_layer.c
+++ b/src/softmax_layer.c
@@ -10,7 +10,7 @@
 softmax_layer make_softmax_layer(int batch, int inputs, int groups)
 {
     assert(inputs%groups == 0);
-    fprintf(stderr, "Softmax Layer: %d inputs\n", inputs);
+    fprintf(stderr, "softmax                                        %4d\n",  inputs);
     softmax_layer l = {0};
     l.type = SOFTMAX;
     l.batch = batch;