From 81c23650e1b880279d29e9a6cef18d29e2cec69c Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Wed, 16 Dec 2015 19:46:39 +0000
Subject: [PATCH] missing file

---
 src/parser.c |  194 +++++++++++++++++++++++++++++++++---------------
 1 files changed, 132 insertions(+), 62 deletions(-)

diff --git a/src/parser.c b/src/parser.c
index 53e8461..8efafad 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -14,9 +14,10 @@
 #include "softmax_layer.h"
 #include "dropout_layer.h"
 #include "detection_layer.h"
-#include "region_layer.h"
 #include "avgpool_layer.h"
+#include "local_layer.h"
 #include "route_layer.h"
+#include "shortcut_layer.h"
 #include "list.h"
 #include "option_list.h"
 #include "utils.h"
@@ -28,6 +29,7 @@
 
 int is_network(section *s);
 int is_convolutional(section *s);
+int is_local(section *s);
 int is_deconvolutional(section *s);
 int is_connected(section *s);
 int is_maxpool(section *s);
@@ -36,9 +38,9 @@
 int is_softmax(section *s);
 int is_normalization(section *s);
 int is_crop(section *s);
+int is_shortcut(section *s);
 int is_cost(section *s);
 int is_detection(section *s);
-int is_region(section *s);
 int is_route(section *s);
 list *read_cfg(char *filename);
 
@@ -80,6 +82,7 @@
     int h;
     int w;
     int c;
+    int index;
 } size_params;
 
 deconvolutional_layer parse_deconvolutional(list *options, size_params params)
@@ -109,6 +112,27 @@
     return layer;
 }
 
+local_layer parse_local(list *options, size_params params)
+{
+    int n = option_find_int(options, "filters",1);
+    int size = option_find_int(options, "size",1);
+    int stride = option_find_int(options, "stride",1);
+    int pad = option_find_int(options, "pad",0);
+    char *activation_s = option_find_str(options, "activation", "logistic");
+    ACTIVATION activation = get_activation(activation_s);
+
+    int batch,h,w,c;
+    h = params.h;
+    w = params.w;
+    c = params.c;
+    batch=params.batch;
+    if(!(h && w && c)) error("Layer before local layer must output image.");
+
+    local_layer layer = make_local_layer(batch,h,w,c,n,size,stride,pad,activation);
+
+    return layer;
+}
+
 convolutional_layer parse_convolutional(list *options, size_params params)
 {
     int n = option_find_int(options, "filters",1);
@@ -124,8 +148,10 @@
     c = params.c;
     batch=params.batch;
     if(!(h && w && c)) error("Layer before convolutional layer must output image.");
+    int batch_normalize = option_find_int_quiet(options, "batch_normalize", 0);
 
-    convolutional_layer layer = make_convolutional_layer(batch,h,w,c,n,size,stride,pad,activation);
+    convolutional_layer layer = make_convolutional_layer(batch,h,w,c,n,size,stride,pad,activation, batch_normalize);
+    layer.flipped = option_find_int_quiet(options, "flipped", 0);
 
     char *weights = option_find_str(options, "weights", 0);
     char *biases = option_find_str(options, "biases", 0);
@@ -167,25 +193,19 @@
     int coords = option_find_int(options, "coords", 1);
     int classes = option_find_int(options, "classes", 1);
     int rescore = option_find_int(options, "rescore", 0);
-    int joint = option_find_int(options, "joint", 0);
-    int objectness = option_find_int(options, "objectness", 0);
-    int background = option_find_int(options, "background", 0);
-    detection_layer layer = make_detection_layer(params.batch, params.inputs, classes, coords, joint, rescore, background, objectness);
-    return layer;
-}
-
-region_layer parse_region(list *options, size_params params)
-{
-    int coords = option_find_int(options, "coords", 1);
-    int classes = option_find_int(options, "classes", 1);
-    int rescore = option_find_int(options, "rescore", 0);
     int num = option_find_int(options, "num", 1);
     int side = option_find_int(options, "side", 7);
-    region_layer layer = make_region_layer(params.batch, params.inputs, num, side, classes, coords, rescore);
-    int softmax = option_find_int(options, "softmax", 0);
-    int sqrt = option_find_int(options, "sqrt", 0);
-    layer.softmax = softmax;
-    layer.sqrt = sqrt;
+    detection_layer layer = make_detection_layer(params.batch, params.inputs, num, side, classes, coords, rescore);
+
+    layer.softmax = option_find_int(options, "softmax", 0);
+    layer.sqrt = option_find_int(options, "sqrt", 0);
+
+    layer.coord_scale = option_find_float(options, "coord_scale", 1);
+    layer.forced = option_find_int(options, "forced", 0);
+    layer.object_scale = option_find_float(options, "object_scale", 1);
+    layer.noobject_scale = option_find_float(options, "noobject_scale", 1);
+    layer.class_scale = option_find_float(options, "class_scale", 1);
+    layer.jitter = option_find_float(options, "jitter", .2);
     return layer;
 }
 
@@ -217,6 +237,7 @@
     int noadjust = option_find_int_quiet(options, "noadjust",0);
 
     crop_layer l = make_crop_layer(batch,h,w,c,crop_height,crop_width,flip, angle, saturation, exposure);
+    l.shift = option_find_float(options, "shift", 0);
     l.noadjust = noadjust;
     return l;
 }
@@ -270,6 +291,20 @@
     return l;
 }
 
+layer parse_shortcut(list *options, size_params params, network net)
+{
+    char *l = option_find(options, "from");   
+    int index = atoi(l);
+    if(index < 0) index = params.index + index;
+
+    int batch = params.batch;
+    layer from = net.layers[index];
+
+    layer s = make_shortcut_layer(batch, index, params.w, params.h, params.c, from.out_w, from.out_h, from.out_c);
+    return s;
+}
+
+
 route_layer parse_route(list *options, size_params params, network net)
 {
     char *l = option_find(options, "layers");   
@@ -286,13 +321,14 @@
     for(i = 0; i < n; ++i){
         int index = atoi(l);
         l = strchr(l, ',')+1;
+        if(index < 0) index = params.index + index;
         layers[i] = index;
         sizes[i] = net.layers[index].outputs;
     }
     int batch = params.batch;
 
     route_layer layer = make_route_layer(batch, n, layers, sizes);
-    
+
     convolutional_layer first = net.layers[layers[0]];
     layer.out_w = first.out_w;
     layer.out_h = first.out_h;
@@ -402,12 +438,15 @@
     int count = 0;
     free_section(s);
     while(n){
+        params.index = count;
         fprintf(stderr, "%d: ", count);
         s = (section *)n->val;
         options = s->options;
         layer l = {0};
         if(is_convolutional(s)){
             l = parse_convolutional(options, params);
+        }else if(is_local(s)){
+            l = parse_local(options, params);
         }else if(is_deconvolutional(s)){
             l = parse_deconvolutional(options, params);
         }else if(is_connected(s)){
@@ -418,8 +457,6 @@
             l = parse_cost(options, params);
         }else if(is_detection(s)){
             l = parse_detection(options, params);
-        }else if(is_region(s)){
-            l = parse_region(options, params);
         }else if(is_softmax(s)){
             l = parse_softmax(options, params);
         }else if(is_normalization(s)){
@@ -430,6 +467,8 @@
             l = parse_avgpool(options, params);
         }else if(is_route(s)){
             l = parse_route(options, params, net);
+        }else if(is_shortcut(s)){
+            l = parse_shortcut(options, params, net);
         }else if(is_dropout(s)){
             l = parse_dropout(options, params);
             l.output = net.layers[count-1].output;
@@ -442,17 +481,18 @@
             fprintf(stderr, "Type not recognized: %s\n", s->type);
         }
         l.dontload = option_find_int_quiet(options, "dontload", 0);
+        l.dontloadscales = option_find_int_quiet(options, "dontloadscales", 0);
         option_unused(options);
         net.layers[count] = l;
         free_section(s);
         n = n->next;
+        ++count;
         if(n){
             params.h = l.out_h;
             params.w = l.out_w;
             params.c = l.out_c;
             params.inputs = l.outputs;
         }
-        ++count;
     }   
     free_list(sections);
     net.outputs = get_network_output_size(net);
@@ -460,6 +500,10 @@
     return net;
 }
 
+int is_shortcut(section *s)
+{
+    return (strcmp(s->type, "[shortcut]")==0);
+}
 int is_crop(section *s)
 {
     return (strcmp(s->type, "[crop]")==0);
@@ -472,9 +516,9 @@
 {
     return (strcmp(s->type, "[detection]")==0);
 }
-int is_region(section *s)
+int is_local(section *s)
 {
-    return (strcmp(s->type, "[region]")==0);
+    return (strcmp(s->type, "[local]")==0);
 }
 int is_deconvolutional(section *s)
 {
@@ -527,24 +571,6 @@
     return (strcmp(s->type, "[route]")==0);
 }
 
-int read_option(char *s, list *options)
-{
-    size_t i;
-    size_t len = strlen(s);
-    char *val = 0;
-    for(i = 0; i < len; ++i){
-        if(s[i] == '='){
-            s[i] = '\0';
-            val = s+i+1;
-            break;
-        }
-    }
-    if(i == len-1) return 0;
-    char *key = s;
-    option_insert(options, key, val);
-    return 1;
-}
-
 list *read_cfg(char *filename)
 {
     FILE *file = fopen(filename, "r");
@@ -625,9 +651,12 @@
     FILE *fp = fopen(filename, "w");
     if(!fp) file_error(filename);
 
-    fwrite(&net.learning_rate, sizeof(float), 1, fp);
-    fwrite(&net.momentum, sizeof(float), 1, fp);
-    fwrite(&net.decay, sizeof(float), 1, fp);
+    int major = 0;
+    int minor = 1;
+    int revision = 0;
+    fwrite(&major, sizeof(int), 1, fp);
+    fwrite(&minor, sizeof(int), 1, fp);
+    fwrite(&revision, sizeof(int), 1, fp);
     fwrite(net.seen, sizeof(int), 1, fp);
 
     int i;
@@ -641,19 +670,13 @@
 #endif
             int num = l.n*l.c*l.size*l.size;
             fwrite(l.biases, sizeof(float), l.n, fp);
-            fwrite(l.filters, sizeof(float), num, fp);
-        }
-        if(l.type == DECONVOLUTIONAL){
-#ifdef GPU
-            if(gpu_index >= 0){
-                pull_deconvolutional_layer(l);
+            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);
             }
-#endif
-            int num = l.n*l.c*l.size*l.size;
-            fwrite(l.biases, sizeof(float), l.n, fp);
             fwrite(l.filters, sizeof(float), num, fp);
-        }
-        if(l.type == CONNECTED){
+        } if(l.type == CONNECTED){
 #ifdef GPU
             if(gpu_index >= 0){
                 pull_connected_layer(l);
@@ -661,6 +684,16 @@
 #endif
             fwrite(l.biases, sizeof(float), l.outputs, fp);
             fwrite(l.weights, sizeof(float), l.outputs*l.inputs, fp);
+        } if(l.type == LOCAL){
+#ifdef GPU
+            if(gpu_index >= 0){
+                pull_local_layer(l);
+            }
+#endif
+            int locations = l.out_w*l.out_h;
+            int size = l.size*l.size*l.c*l.n*locations;
+            fwrite(l.biases, sizeof(float), l.outputs, fp);
+            fwrite(l.filters, sizeof(float), size, fp);
         }
     }
     fclose(fp);
@@ -670,6 +703,19 @@
     save_weights_upto(net, filename, net.n);
 }
 
+void transpose_matrix(float *a, int rows, int cols)
+{
+    float *transpose = calloc(rows*cols, sizeof(float));
+    int x, y;
+    for(x = 0; x < rows; ++x){
+        for(y = 0; y < cols; ++y){
+            transpose[y*rows + x] = a[x*cols + y];
+        }
+    }
+    memcpy(a, transpose, rows*cols*sizeof(float));
+    free(transpose);
+}
+
 void load_weights_upto(network *net, char *filename, int cutoff)
 {
     fprintf(stderr, "Loading weights from %s...", filename);
@@ -677,10 +723,12 @@
     FILE *fp = fopen(filename, "r");
     if(!fp) file_error(filename);
 
-    float garbage;
-    fread(&garbage, sizeof(float), 1, fp);
-    fread(&garbage, sizeof(float), 1, fp);
-    fread(&garbage, sizeof(float), 1, fp);
+    int major;
+    int minor;
+    int revision;
+    fread(&major, sizeof(int), 1, fp);
+    fread(&minor, sizeof(int), 1, fp);
+    fread(&revision, sizeof(int), 1, fp);
     fread(net->seen, sizeof(int), 1, fp);
 
     int i;
@@ -690,7 +738,15 @@
         if(l.type == CONVOLUTIONAL){
             int num = l.n*l.c*l.size*l.size;
             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);
+            }
             fread(l.filters, sizeof(float), num, fp);
+            if (l.flipped) {
+                transpose_matrix(l.filters, l.c*l.size*l.size, l.n);
+            }
 #ifdef GPU
             if(gpu_index >= 0){
                 push_convolutional_layer(l);
@@ -710,12 +766,26 @@
         if(l.type == CONNECTED){
             fread(l.biases, sizeof(float), l.outputs, fp);
             fread(l.weights, sizeof(float), l.outputs*l.inputs, fp);
+            if(major > 1000 || minor > 1000){
+                transpose_matrix(l.weights, l.inputs, l.outputs);
+            }
 #ifdef GPU
             if(gpu_index >= 0){
                 push_connected_layer(l);
             }
 #endif
         }
+        if(l.type == LOCAL){
+            int locations = l.out_w*l.out_h;
+            int size = l.size*l.size*l.c*l.n*locations;
+            fread(l.biases, sizeof(float), l.outputs, fp);
+            fread(l.filters, sizeof(float), size, fp);
+#ifdef GPU
+            if(gpu_index >= 0){
+                push_local_layer(l);
+            }
+#endif
+        }
     }
     fprintf(stderr, "Done!\n");
     fclose(fp);

--
Gitblit v1.10.0