From d9ae3dd681ed1c98e807ff937dbbb9cfc4d19fe0 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Tue, 27 Mar 2018 23:59:03 +0000
Subject: [PATCH] Added Yolo v3
---
src/parser.c | 106 +++++++++++++++++++++++++++++++++++++++++++++++++++-
1 files changed, 103 insertions(+), 3 deletions(-)
diff --git a/src/parser.c b/src/parser.c
index 2a1ea3b..a37ef1c 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -24,11 +24,14 @@
#include "parser.h"
#include "region_layer.h"
#include "reorg_layer.h"
+#include "reorg_old_layer.h"
#include "rnn_layer.h"
#include "route_layer.h"
#include "shortcut_layer.h"
#include "softmax_layer.h"
#include "utils.h"
+#include "upsample_layer.h"
+#include "yolo_layer.h"
#include <stdint.h>
typedef struct{
@@ -46,6 +49,7 @@
if (strcmp(type, "[cost]")==0) return COST;
if (strcmp(type, "[detection]")==0) return DETECTION;
if (strcmp(type, "[region]")==0) return REGION;
+ if (strcmp(type, "[yolo]") == 0) return YOLO;
if (strcmp(type, "[local]")==0) return LOCAL;
if (strcmp(type, "[conv]")==0
|| strcmp(type, "[convolutional]")==0) return CONVOLUTIONAL;
@@ -60,6 +64,7 @@
if (strcmp(type, "[max]")==0
|| strcmp(type, "[maxpool]")==0) return MAXPOOL;
if (strcmp(type, "[reorg]")==0) return REORG;
+ if (strcmp(type, "[reorg_old]") == 0) return REORG_OLD;
if (strcmp(type, "[avg]")==0
|| strcmp(type, "[avgpool]")==0) return AVGPOOL;
if (strcmp(type, "[dropout]")==0) return DROPOUT;
@@ -69,6 +74,7 @@
if (strcmp(type, "[soft]")==0
|| strcmp(type, "[softmax]")==0) return SOFTMAX;
if (strcmp(type, "[route]")==0) return ROUTE;
+ if (strcmp(type, "[upsample]") == 0) return UPSAMPLE;
return BLANK;
}
@@ -233,20 +239,82 @@
return layer;
}
+int *parse_yolo_mask(char *a, int *num)
+{
+ int *mask = 0;
+ if (a) {
+ int len = strlen(a);
+ int n = 1;
+ int i;
+ for (i = 0; i < len; ++i) {
+ if (a[i] == ',') ++n;
+ }
+ mask = calloc(n, sizeof(int));
+ for (i = 0; i < n; ++i) {
+ int val = atoi(a);
+ mask[i] = val;
+ a = strchr(a, ',') + 1;
+ }
+ *num = n;
+ }
+ return mask;
+}
+
+layer parse_yolo(list *options, size_params params)
+{
+ int classes = option_find_int(options, "classes", 20);
+ int total = option_find_int(options, "num", 1);
+ int num = total;
+
+ char *a = option_find_str(options, "mask", 0);
+ int *mask = parse_yolo_mask(a, &num);
+ layer l = make_yolo_layer(params.batch, params.w, params.h, num, total, mask, classes);
+ assert(l.outputs == params.inputs);
+
+ l.max_boxes = option_find_int_quiet(options, "max", 90);
+ l.jitter = option_find_float(options, "jitter", .2);
+
+ l.ignore_thresh = option_find_float(options, "ignore_thresh", .5);
+ l.truth_thresh = option_find_float(options, "truth_thresh", 1);
+ l.random = option_find_int_quiet(options, "random", 0);
+
+ char *map_file = option_find_str(options, "map", 0);
+ if (map_file) l.map = read_map(map_file);
+
+ a = option_find_str(options, "anchors", 0);
+ if (a) {
+ int len = strlen(a);
+ int n = 1;
+ int i;
+ for (i = 0; i < len; ++i) {
+ if (a[i] == ',') ++n;
+ }
+ for (i = 0; i < n; ++i) {
+ float bias = atof(a);
+ l.biases[i] = bias;
+ a = strchr(a, ',') + 1;
+ }
+ }
+ return l;
+}
+
layer parse_region(list *options, size_params params)
{
int coords = option_find_int(options, "coords", 4);
int classes = option_find_int(options, "classes", 20);
int num = option_find_int(options, "num", 1);
+ int max_boxes = option_find_int_quiet(options, "max", 30);
- layer l = make_region_layer(params.batch, params.w, params.h, num, classes, coords);
+ layer l = make_region_layer(params.batch, params.w, params.h, num, classes, coords, max_boxes);
assert(l.outputs == params.inputs);
l.log = option_find_int_quiet(options, "log", 0);
l.sqrt = option_find_int_quiet(options, "sqrt", 0);
+ l.small_object = option_find_int_quiet(options, "small_object", 0);
l.softmax = option_find_int(options, "softmax", 0);
- l.max_boxes = option_find_int_quiet(options, "max",30);
+ l.focal_loss = option_find_int_quiet(options, "focal_loss", 0);
+ //l.max_boxes = option_find_int_quiet(options, "max",30);
l.jitter = option_find_float(options, "jitter", .2);
l.rescore = option_find_int_quiet(options, "rescore",0);
@@ -356,6 +424,23 @@
return layer;
}
+layer parse_reorg_old(list *options, size_params params)
+{
+ printf("\n reorg_old \n");
+ int stride = option_find_int(options, "stride", 1);
+ int reverse = option_find_int_quiet(options, "reverse", 0);
+
+ int batch, h, w, c;
+ h = params.h;
+ w = params.w;
+ c = params.c;
+ batch = params.batch;
+ if (!(h && w && c)) error("Layer before reorg layer must output image.");
+
+ layer layer = make_reorg_old_layer(batch, w, h, c, stride, reverse);
+ return layer;
+}
+
maxpool_layer parse_maxpool(list *options, size_params params)
{
int stride = option_find_int(options, "stride",1);
@@ -447,6 +532,15 @@
return l;
}
+layer parse_upsample(list *options, size_params params, network net)
+{
+
+ int stride = option_find_int(options, "stride", 2);
+ layer l = make_upsample_layer(params.batch, params.w, params.h, params.c, stride);
+ l.scale = option_find_float_quiet(options, "scale", 1);
+ return l;
+}
+
route_layer parse_route(list *options, size_params params, network net)
{
char *l = option_find(options, "layers");
@@ -643,6 +737,8 @@
l = parse_cost(options, params);
}else if(lt == REGION){
l = parse_region(options, params);
+ }else if (lt == YOLO) {
+ l = parse_yolo(options, params);
}else if(lt == DETECTION){
l = parse_detection(options, params);
}else if(lt == SOFTMAX){
@@ -655,11 +751,15 @@
}else if(lt == MAXPOOL){
l = parse_maxpool(options, params);
}else if(lt == REORG){
- l = parse_reorg(options, params);
+ l = parse_reorg(options, params); }
+ else if (lt == REORG_OLD) {
+ l = parse_reorg_old(options, params);
}else if(lt == AVGPOOL){
l = parse_avgpool(options, params);
}else if(lt == ROUTE){
l = parse_route(options, params, net);
+ }else if (lt == UPSAMPLE) {
+ l = parse_upsample(options, params, net);
}else if(lt == SHORTCUT){
l = parse_shortcut(options, params, net);
}else if(lt == DROPOUT){
--
Gitblit v1.10.0