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/data.h | 78 ++++++++++++++++++++++++++++++++++-----
1 files changed, 68 insertions(+), 10 deletions(-)
diff --git a/src/data.h b/src/data.h
index bda804f..57f4702 100644
--- a/src/data.h
+++ b/src/data.h
@@ -2,10 +2,14 @@
#define DATA_H
#include <pthread.h>
+#if defined(_MSC_VER) && _MSC_VER < 1900
+ #define inline __inline
+#endif
+
#include "matrix.h"
#include "list.h"
-
-extern unsigned int data_seed;
+#include "image.h"
+#include "tree.h"
static inline float distance_from_edge(int x, int max)
{
@@ -18,34 +22,86 @@
return dist;
}
-
typedef struct{
+ int w, h;
matrix X;
matrix y;
int shallow;
+ int *num_boxes;
+ box **boxes;
} data;
+typedef enum {
+ CLASSIFICATION_DATA, DETECTION_DATA, CAPTCHA_DATA, REGION_DATA, IMAGE_DATA, LETTERBOX_DATA, COMPARE_DATA, WRITING_DATA, SWAG_DATA, TAG_DATA, OLD_CLASSIFICATION_DATA, STUDY_DATA, DET_DATA, SUPER_DATA
+} data_type;
+
+typedef struct load_args{
+ int threads;
+ char **paths;
+ char *path;
+ int n;
+ int m;
+ char **labels;
+ int h;
+ int w;
+ int out_w;
+ int out_h;
+ int nh;
+ int nw;
+ int num_boxes;
+ int min, max, size;
+ int classes;
+ int background;
+ int scale;
+ int small_object;
+ float jitter;
+ int flip;
+ float angle;
+ float aspect;
+ float saturation;
+ float exposure;
+ float hue;
+ data *d;
+ image *im;
+ image *resized;
+ data_type type;
+ tree *hierarchy;
+} load_args;
+
+typedef struct{
+ int id;
+ float x,y,w,h;
+ float left, right, top, bottom;
+} box_label;
void free_data(data d);
+pthread_t load_data(load_args args);
+
+pthread_t load_data_in_thread(load_args args);
+
void print_letters(float *pred, int n);
data load_data_captcha(char **paths, int n, int m, int k, int w, int h);
data load_data_captcha_encode(char **paths, int n, int m, int w, int h);
-data load_data(char **paths, int n, int m, char **labels, int k, int w, int h);
-pthread_t load_data_thread(char **paths, int n, int m, char **labels, int k, int w, int h, data *d);
+data load_data_old(char **paths, int n, int m, char **labels, int k, int w, int h);
+data load_data_detection(int n, char **paths, int m, int w, int h, int boxes, int classes, int use_flip, float jitter, float hue, float saturation, float exposure, int small_object);
+data load_data_tag(char **paths, int n, int m, int k, int use_flip, int min, int max, int size, float angle, float aspect, float hue, float saturation, float exposure);
+matrix load_image_augment_paths(char **paths, int n, int use_flip, int min, int max, int size, float angle, float aspect, float hue, float saturation, float exposure);
+data load_data_super(char **paths, int n, int m, int w, int h, int scale);
+data load_data_augment(char **paths, int n, int m, char **labels, int k, tree *hierarchy, int use_flip, int min, int max, int size, float angle, float aspect, float hue, float saturation, float exposure);
+data load_go(char *filename);
-pthread_t load_data_detection_thread(int n, char **paths, int m, int classes, int w, int h, int nh, int nw, int background, data *d);
-data load_data_detection_jitter_random(int n, char **paths, int m, int classes, int w, int h, int num_boxes, int background);
-pthread_t load_data_localization_thread(int n, char **paths, int m, int classes, int w, int h, data *d);
-
+box_label *read_boxes(char *filename, int *n);
data load_cifar10_data(char *filename);
data load_all_cifar10();
-data load_data_writing(char **paths, int n, int m, int w, int h);
+data load_data_writing(char **paths, int n, int m, int w, int h, int out_w, int out_h);
list *get_paths(char *filename);
char **get_labels(char *filename);
void get_random_batch(data d, int n, float *X, float *y);
+data get_data_part(data d, int part, int total);
+data get_random_data(data d, int num);
void get_next_batch(data d, int n, int offset, float *X, float *y);
data load_categorical_data_csv(char *filename, int target, int k);
void normalize_data_rows(data d);
@@ -54,5 +110,7 @@
void randomize_data(data d);
data *split_data(data d, int part, int total);
data concat_data(data d1, data d2);
+data concat_datas(data *d, int n);
+void fill_truth(char *path, char **labels, int k, float *truth);
#endif
--
Gitblit v1.10.0