no mean on input binarization

src/convolutional_kernels.cu

@@ -82,9 +82,7 @@ void forward_convolutional_layer_gpu(convolutional_layer l, network_state state)
     if(l.xnor){
         binarize_filters_gpu(l.filters_gpu, l.n, l.c*l.size*l.size, l.binary_filters_gpu);
         swap_binary(&l);
-        for(i = 0; i < l.batch; ++i){
+        binarize_gpu(state.input, l.c*l.h*l.w*l.batch, l.binary_input_gpu);
-            binarize_input_gpu(state.input + i*l.inputs, l.c, l.h*l.w, l.binary_input_gpu + i*l.inputs);
-        }
         state.input = l.binary_input_gpu;
     }
 

src/convolutional_layer.c

@@ -45,6 +45,14 @@ void binarize_filters(float *filters, int n, int size, float *binary)
     }
 }
 
+void binarize_cpu(float *input, int n, float *binary)
+{
+    int i;
+    for(i = 0; i < n; ++i){
+        binary[i] = (input[i] > 0) ? 1 : -1;
+    }
+}
+
 void binarize_input(float *input, int n, int size, float *binary)
 {
     int i, s;
@@ -426,12 +434,10 @@ void forward_convolutional_layer(convolutional_layer l, network_state state)
        }
      */
 
-    if(l.xnor && (l.c%32 != 0 || !AI2)){
+    if(l.xnor ){
         binarize_filters(l.filters, l.n, l.c*l.size*l.size, l.binary_filters);
         swap_binary(&l);
-        for(i = 0; i < l.batch; ++i){
+        binarize_cpu(state.input, l.c*l.h*l.w*l.batch, l.binary_input);
-            binarize_input(state.input + i*l.inputs, l.c, l.h*l.w, l.binary_input + i*l.inputs);
-        }
         state.input = l.binary_input;
     }
 

src/darknet.c

@@ -88,6 +88,23 @@ void average(int argc, char *argv[])
     save_weights(sum, outfile);
 }
 
+void operations(char *cfgfile)
+{
+    gpu_index = -1;
+    network net = parse_network_cfg(cfgfile);
+    int i;
+    long ops = 0;
+    for(i = 0; i < net.n; ++i){
+        layer l = net.layers[i];
+        if(l.type == CONVOLUTIONAL){
+            ops += 2 * l.n * l.size*l.size*l.c * l.out_h*l.out_w;
+        } else if(l.type == CONNECTED){
+            ops += 2 * l.inputs * l.outputs;
+        }
+    }
+    printf("Floating Point Operations: %ld\n", ops);
+}
+
 void partial(char *cfgfile, char *weightfile, char *outfile, int max)
 {
     gpu_index = -1;
@@ -288,8 +305,12 @@ int main(int argc, char **argv)
         normalize_net(argv[2], argv[3], argv[4]);
     } else if (0 == strcmp(argv[1], "rescale")){
         rescale_net(argv[2], argv[3], argv[4]);
+    } else if (0 == strcmp(argv[1], "ops")){
+        operations(argv[2]);
     } else if (0 == strcmp(argv[1], "partial")){
         partial(argv[2], argv[3], argv[4], atoi(argv[5]));
+    } else if (0 == strcmp(argv[1], "average")){
+        average(argc, argv);
     } else if (0 == strcmp(argv[1], "stacked")){
         stacked(argv[2], argv[3], argv[4]);
     } else if (0 == strcmp(argv[1], "visualize")){

src/detection_layer.c

@@ -133,9 +133,11 @@ void forward_detection_layer(const detection_layer l, network_state state)
                         best_index = 0;
                     }
                 }
+                /*
                 if(1 && *(state.net.seen) < 100000){
                     best_index = rand()%l.n;
                 }
+                */
 
                 int box_index = index + locations*(l.classes + l.n) + (i*l.n + best_index) * l.coords;
                 int tbox_index = truth_index + 1 + l.classes;

src/xnor_layer.c

@@ -66,7 +66,7 @@ void forward_xnor_layer(const layer l, network_state state)
     ai2_bin_conv_layer al = ai2_make_bin_conv_layer(b, c, ix, iy, wx, wy, s, pad);
 
     // OPTIONAL: You need to set the real-valued input like:
-    ai2_setFltInput(&al, state.input);
+    ai2_setFltInput_unpadded(&al, state.input);
     // The above function will automatically binarize the input for the layer (channel wise).
     // If commented: using the default 0-valued input.