From b4b729a15e577c68f64e0ac69fb299de6f5f706c Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Thu, 17 Apr 2014 16:58:24 +0000
Subject: [PATCH] Merge branch 'master' of pjreddie.com:jnet
---
src/data.c | 71 ++++++++++++++++++++++++++---------
1 files changed, 52 insertions(+), 19 deletions(-)
diff --git a/src/data.c b/src/data.c
index 0b396d7..39ece11 100644
--- a/src/data.c
+++ b/src/data.c
@@ -1,5 +1,4 @@
#include "data.h"
-#include "list.h"
#include "utils.h"
#include "image.h"
@@ -11,6 +10,7 @@
{
char *path;
FILE *file = fopen(filename, "r");
+ if(!file) file_error(filename);
list *lines = make_list();
while((path=fgetl(file))){
list_insert(lines, path);
@@ -19,10 +19,10 @@
return lines;
}
-void fill_truth(char *path, char **labels, int k, double *truth)
+void fill_truth(char *path, char **labels, int k, float *truth)
{
int i;
- memset(truth, 0, k*sizeof(double));
+ memset(truth, 0, k*sizeof(float));
for(i = 0; i < k; ++i){
if(strstr(path, labels[i])){
truth[i] = 1;
@@ -30,17 +30,17 @@
}
}
-data load_data_image_paths(char **paths, int n, char **labels, int k)
+data load_data_image_paths(char **paths, int n, char **labels, int k, int h, int w)
{
int i;
data d;
d.shallow = 0;
d.X.rows = n;
- d.X.vals = calloc(d.X.rows, sizeof(double*));
+ d.X.vals = calloc(d.X.rows, sizeof(float*));
d.y = make_matrix(n, k);
for(i = 0; i < n; ++i){
- image im = load_image(paths[i]);
+ image im = load_image(paths[i], h, w);
d.X.vals[i] = im.data;
d.X.cols = im.h*im.w*im.c;
fill_truth(paths[i], labels, k, d.y.vals[i]);
@@ -48,11 +48,11 @@
return d;
}
-data load_data_image_pathfile(char *filename, char **labels, int k)
+data load_data_image_pathfile(char *filename, char **labels, int k, int h, int w)
{
list *plist = get_paths(filename);
char **paths = (char **)list_to_array(plist);
- data d = load_data_image_paths(paths, plist->size, labels, k);
+ data d = load_data_image_paths(paths, plist->size, labels, k, h, w);
free_list_contents(plist);
free_list(plist);
free(paths);
@@ -70,20 +70,20 @@
}
}
-data load_data_image_pathfile_part(char *filename, int part, int total, char **labels, int k)
+data load_data_image_pathfile_part(char *filename, int part, int total, char **labels, int k, int h, int w)
{
list *plist = get_paths(filename);
char **paths = (char **)list_to_array(plist);
int start = part*plist->size/total;
int end = (part+1)*plist->size/total;
- data d = load_data_image_paths(paths+start, end-start, labels, k);
+ data d = load_data_image_paths(paths+start, end-start, labels, k, h, w);
free_list_contents(plist);
free_list(plist);
free(paths);
return d;
}
-data load_data_image_pathfile_random(char *filename, int n, char **labels, int k)
+data load_data_image_pathfile_random(char *filename, int n, char **labels, int k, int h, int w)
{
int i;
list *plist = get_paths(filename);
@@ -92,8 +92,9 @@
for(i = 0; i < n; ++i){
int index = rand()%plist->size;
random_paths[i] = paths[index];
+ if(i == 0) printf("%s\n", paths[index]);
}
- data d = load_data_image_paths(random_paths, n, labels, k);
+ data d = load_data_image_paths(random_paths, n, labels, k, h, w);
free_list_contents(plist);
free_list(plist);
free(paths);
@@ -106,8 +107,8 @@
data d;
d.shallow = 0;
matrix X = csv_to_matrix(filename);
- double *truth_1d = pop_column(&X, target);
- double **truth = one_hot_encode(truth_1d, X.rows, k);
+ float *truth_1d = pop_column(&X, target);
+ float **truth = one_hot_encode(truth_1d, X.rows, k);
matrix y;
y.rows = X.rows;
y.cols = k;
@@ -118,12 +119,36 @@
return d;
}
+data load_cifar10_data(char *filename)
+{
+ data d;
+ d.shallow = 0;
+ unsigned long i,j;
+ matrix X = make_matrix(10000, 3072);
+ matrix y = make_matrix(10000, 10);
+ d.X = X;
+ d.y = y;
+
+ FILE *fp = fopen(filename, "rb");
+ for(i = 0; i < 10000; ++i){
+ unsigned char bytes[3073];
+ fread(bytes, 1, 3073, fp);
+ int class = bytes[0];
+ y.vals[i][class] = 1;
+ for(j = 0; j < X.cols; ++j){
+ X.vals[i][j] = (double)bytes[j+1];
+ }
+ }
+ fclose(fp);
+ return d;
+}
+
void randomize_data(data d)
{
int i;
for(i = d.X.rows-1; i > 0; --i){
int index = rand()%i;
- double *swap = d.X.vals[index];
+ float *swap = d.X.vals[index];
d.X.vals[index] = d.X.vals[i];
d.X.vals[i] = swap;
@@ -133,6 +158,14 @@
}
}
+void scale_data_rows(data d, float s)
+{
+ int i;
+ for(i = 0; i < d.X.rows; ++i){
+ scale_array(d.X.vals[i], d.X.cols, s);
+ }
+}
+
void normalize_data_rows(data d)
{
int i;
@@ -156,10 +189,10 @@
train.X.cols = test.X.cols = d.X.cols;
train.y.cols = test.y.cols = d.y.cols;
- train.X.vals = calloc(train.X.rows, sizeof(double*));
- test.X.vals = calloc(test.X.rows, sizeof(double*));
- train.y.vals = calloc(train.y.rows, sizeof(double*));
- test.y.vals = calloc(test.y.rows, sizeof(double*));
+ train.X.vals = calloc(train.X.rows, sizeof(float*));
+ test.X.vals = calloc(test.X.rows, sizeof(float*));
+ train.y.vals = calloc(train.y.rows, sizeof(float*));
+ test.y.vals = calloc(test.y.rows, sizeof(float*));
for(i = 0; i < start; ++i){
train.X.vals[i] = d.X.vals[i];
--
Gitblit v1.10.0