From 13d3b038b83a7e59191828304231dd0a6c6f2f9c Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Wed, 16 Mar 2016 11:45:30 +0000
Subject: [PATCH] Makefile

---
 src/parser.c |   73 ++++++++++++++++++++++++++++++++++++
 1 files changed, 73 insertions(+), 0 deletions(-)

diff --git a/src/parser.c b/src/parser.c
index 97ce7a1..c109a14 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -160,6 +160,7 @@
 
     convolutional_layer layer = make_convolutional_layer(batch,h,w,c,n,size,stride,pad,activation, batch_normalize, binary);
     layer.flipped = option_find_int_quiet(options, "flipped", 0);
+    layer.dot = option_find_float_quiet(options, "dot", 0);
 
     char *weights = option_find_str(options, "weights", 0);
     char *biases = option_find_str(options, "biases", 0);
@@ -729,8 +730,44 @@
     fclose(fp);
 }
 
+void save_convolutional_weights_binary(layer l, FILE *fp)
+{
+#ifdef GPU
+    if(gpu_index >= 0){
+        pull_convolutional_layer(l);
+    }
+#endif
+    binarize_filters(l.filters, l.n, l.c*l.size*l.size, l.binary_filters);
+    int size = l.c*l.size*l.size;
+    int i, j, k;
+    fwrite(l.biases, sizeof(float), l.n, fp);
+    if (l.batch_normalize){
+        fwrite(l.scales, sizeof(float), l.n, fp);
+        fwrite(l.rolling_mean, sizeof(float), l.n, fp);
+        fwrite(l.rolling_variance, sizeof(float), l.n, fp);
+    }
+    for(i = 0; i < l.n; ++i){
+        float mean = l.binary_filters[i*size];
+        if(mean < 0) mean = -mean;
+        fwrite(&mean, sizeof(float), 1, fp);
+        for(j = 0; j < size/8; ++j){
+            int index = i*size + j*8;
+            unsigned char c = 0;
+            for(k = 0; k < 8; ++k){
+                if (j*8 + k >= size) break;
+                if (l.binary_filters[index + k] > 0) c = (c | 1<<k);
+            }
+            fwrite(&c, sizeof(char), 1, fp);
+        }
+    }
+}
+
 void save_convolutional_weights(layer l, FILE *fp)
 {
+    if(l.binary){
+        //save_convolutional_weights_binary(l, fp);
+        //return;
+    }
 #ifdef GPU
     if(gpu_index >= 0){
         pull_convolutional_layer(l);
@@ -842,8 +879,43 @@
 #endif
 }
 
+void load_convolutional_weights_binary(layer l, FILE *fp)
+{
+    fread(l.biases, sizeof(float), l.n, fp);
+    if (l.batch_normalize && (!l.dontloadscales)){
+        fread(l.scales, sizeof(float), l.n, fp);
+        fread(l.rolling_mean, sizeof(float), l.n, fp);
+        fread(l.rolling_variance, sizeof(float), l.n, fp);
+    }
+    int size = l.c*l.size*l.size;
+    int i, j, k;
+    for(i = 0; i < l.n; ++i){
+        float mean = 0;
+        fread(&mean, sizeof(float), 1, fp);
+        for(j = 0; j < size/8; ++j){
+            int index = i*size + j*8;
+            unsigned char c = 0;
+            fread(&c, sizeof(char), 1, fp);
+            for(k = 0; k < 8; ++k){
+                if (j*8 + k >= size) break;
+                l.filters[index + k] = (c & 1<<k) ? mean : -mean;
+            }
+        }
+    }
+    binarize_filters2(l.filters, l.n, l.c*l.size*l.size, l.cfilters, l.scales);
+#ifdef GPU
+    if(gpu_index >= 0){
+        push_convolutional_layer(l);
+    }
+#endif
+}
+
 void load_convolutional_weights(layer l, FILE *fp)
 {
+    if(l.binary){
+        //load_convolutional_weights_binary(l, fp);
+        //return;
+    }
     int num = l.n*l.c*l.size*l.size;
     fread(l.biases, sizeof(float), l.n, fp);
     if (l.batch_normalize && (!l.dontloadscales)){
@@ -855,6 +927,7 @@
     if (l.flipped) {
         transpose_matrix(l.filters, l.c*l.size*l.size, l.n);
     }
+    if (l.binary) binarize_filters(l.filters, l.n, l.c*l.size*l.size, l.filters);
 #ifdef GPU
     if(gpu_index >= 0){
         push_convolutional_layer(l);

--
Gitblit v1.10.0