Precompute part of expensive multiplication

3dEYE · Aug 18, 2020 · 6a2d50f · 6a2d50f
1 parent 05dee78
commit 6a2d50f
Showing 1 changed file with 3 additions and 1 deletion.
diff --git a/src/network.c b/src/network.c
@@ -1240,12 +1240,14 @@ void fuse_conv_batchnorm(network net)
                 {
                     l->biases[f] = l->biases[f] - (double)l->scales[f] * l->rolling_mean[f] / (sqrt((double)l->rolling_variance[f] + .00001));
 
+                    double precomputed = l->scales[f] / (sqrt((double)l->rolling_variance[f] + .00001));
+
                     const size_t filter_size = l->size*l->size*l->c / l->groups;
                     int i;
                     for (i = 0; i < filter_size; ++i) {
                         int w_index = f*filter_size + i;
 
-                        l->weights[w_index] = (double)l->weights[w_index] * l->scales[f] / (sqrt((double)l->rolling_variance[f] + .00001));
+                        l->weights[w_index] *= precomputed;
                     }
                 }