From 1b5afb45838e603fa6780762eb8cc59246dc2d81 Mon Sep 17 00:00:00 2001
From: IlyaOvodov <b@ovdv.ru>
Date: Tue, 08 May 2018 11:09:35 +0000
Subject: [PATCH] Output improvements for detector results: When printing detector results, output was done in random order, obfuscating results for interpreting. Now: 1. Text output includes coordinates of rects in (left,right,top,bottom in pixels) along with label and score 2. Text output is sorted by rect lefts to simplify finding appropriate rects on image 3. If several class probs are > thresh for some detection, the most probable is written first and coordinates for others are not repeated 4. Rects are imprinted in image in order by their best class prob, so most probable rects are always on top and not overlayed by less probable ones 5. Most probable label for rect is always written first Also: 6. Message about low GPU memory include required amount
---
src/parser.c | 140 +++++++++++++++++++++++++++++++++++++++++++---
1 files changed, 130 insertions(+), 10 deletions(-)
diff --git a/src/parser.c b/src/parser.c
index ae9e194..7441ae2 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 +239,83 @@
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);
+ int max_boxes = option_find_int_quiet(options, "max", 30);
+ layer l = make_yolo_layer(params.batch, params.w, params.h, num, total, mask, classes, max_boxes);
+ assert(l.outputs == params.inputs);
+
+ //l.max_boxes = option_find_int_quiet(options, "max", 90);
+ l.jitter = option_find_float(options, "jitter", .2);
+ l.focal_loss = option_find_int_quiet(options, "focal_loss", 0);
+
+ 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 < total*2; ++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.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);
@@ -258,6 +327,7 @@
l.coord_scale = option_find_float(options, "coord_scale", 1);
l.object_scale = option_find_float(options, "object_scale", 1);
l.noobject_scale = option_find_float(options, "noobject_scale", 1);
+ l.mask_scale = option_find_float(options, "mask_scale", 1);
l.class_scale = option_find_float(options, "class_scale", 1);
l.bias_match = option_find_int_quiet(options, "bias_match",0);
@@ -274,7 +344,7 @@
for(i = 0; i < len; ++i){
if (a[i] == ',') ++n;
}
- for(i = 0; i < n; ++i){
+ for(i = 0; i < n && i < num*2; ++i){
float bias = atof(a);
l.biases[i] = bias;
a = strchr(a, ',')+1;
@@ -356,6 +426,23 @@
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 +534,15 @@
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");
@@ -526,18 +622,24 @@
net->inputs = option_find_int_quiet(options, "inputs", net->h * net->w * net->c);
net->max_crop = option_find_int_quiet(options, "max_crop",net->w*2);
net->min_crop = option_find_int_quiet(options, "min_crop",net->w);
+ net->flip = option_find_int_quiet(options, "flip", 1);
+ net->small_object = option_find_int_quiet(options, "small_object", 0);
net->angle = option_find_float_quiet(options, "angle", 0);
net->aspect = option_find_float_quiet(options, "aspect", 1);
net->saturation = option_find_float_quiet(options, "saturation", 1);
net->exposure = option_find_float_quiet(options, "exposure", 1);
net->hue = option_find_float_quiet(options, "hue", 0);
+ net->power = option_find_float_quiet(options, "power", 4);
if(!net->inputs && !(net->h && net->w && net->c)) error("No input parameters supplied");
char *policy_s = option_find_str(options, "policy", "constant");
net->policy = get_policy(policy_s);
net->burn_in = option_find_int_quiet(options, "burn_in", 0);
+#ifdef CUDNN_HALF
+ net->burn_in = 0;
+#endif
if(net->policy == STEP){
net->step = option_find_int(options, "step", 1);
net->scale = option_find_float(options, "scale", 1);
@@ -571,7 +673,7 @@
net->gamma = option_find_float(options, "gamma", 1);
net->step = option_find_int(options, "step", 1);
} else if (net->policy == POLY || net->policy == RANDOM){
- net->power = option_find_float(options, "power", 1);
+ //net->power = option_find_float(options, "power", 1);
}
net->max_batches = option_find_int(options, "max_batches", 0);
}
@@ -584,6 +686,11 @@
network parse_network_cfg(char *filename)
{
+ return parse_network_cfg_custom(filename, 0);
+}
+
+network parse_network_cfg_custom(char *filename, int batch)
+{
list *sections = read_cfg(filename);
node *n = sections->front;
if(!n) error("Config file has no sections");
@@ -600,6 +707,7 @@
params.w = net.w;
params.c = net.c;
params.inputs = net.inputs;
+ if (batch > 0) net.batch = batch;
params.batch = net.batch;
params.time_steps = net.time_steps;
params.net = net;
@@ -636,6 +744,8 @@
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){
@@ -648,11 +758,15 @@
}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){
@@ -666,6 +780,8 @@
}else{
fprintf(stderr, "Type not recognized: %s\n", s->type);
}
+ l.onlyforward = option_find_int_quiet(options, "onlyforward", 0);
+ l.stopbackward = option_find_int_quiet(options, "stopbackward", 0);
l.dontload = option_find_int_quiet(options, "dontload", 0);
l.dontloadscales = option_find_int_quiet(options, "dontloadscales", 0);
option_unused(options);
@@ -699,6 +815,8 @@
return net;
}
+
+
list *read_cfg(char *filename)
{
FILE *file = fopen(filename, "r");
@@ -836,7 +954,7 @@
fwrite(&major, sizeof(int), 1, fp);
fwrite(&minor, sizeof(int), 1, fp);
fwrite(&revision, sizeof(int), 1, fp);
- fwrite(net.seen, sizeof(uint64_t), 1, fp);
+ fwrite(net.seen, sizeof(int), 1, fp);
int i;
for(i = 0; i < net.n && i < cutoff; ++i){
@@ -1025,12 +1143,14 @@
fread(&minor, sizeof(int), 1, fp);
fread(&revision, sizeof(int), 1, fp);
if ((major * 10 + minor) >= 2) {
- fread(net->seen, sizeof(uint64_t), 1, fp);
+ printf("\n seen 64 \n");
+ uint64_t iseen = 0;
+ fread(&iseen, sizeof(uint64_t), 1, fp);
+ *net->seen = iseen;
}
else {
- int iseen = 0;
- fread(&iseen, sizeof(int), 1, fp);
- *net->seen = iseen;
+ printf("\n seen 32 \n");
+ fread(net->seen, sizeof(int), 1, fp);
}
int transpose = (major > 1000) || (minor > 1000);
--
Gitblit v1.10.0