From 76ee68f96d864a27312c9aa09856ddda559a5cd9 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Thu, 28 Aug 2014 02:11:46 +0000
Subject: [PATCH] Trying some stuff w/ dropout
---
src/data.c | 291 +++++++++++++++++++++++++++++++++++++++++++++-------------
1 files changed, 226 insertions(+), 65 deletions(-)
diff --git a/src/data.c b/src/data.c
index 7ef0d80..aa8fecf 100644
--- a/src/data.c
+++ b/src/data.c
@@ -1,27 +1,16 @@
#include "data.h"
-#include "list.h"
#include "utils.h"
+#include "image.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
-batch make_batch(int n, int k)
-{
- batch b;
- b.n = n;
- if(k < 3) k = 1;
- b.images = calloc(n, sizeof(image));
- b.truth = calloc(n, sizeof(double *));
- int i;
- for(i =0 ; i < n; ++i) b.truth[i] = calloc(k, sizeof(double));
- return b;
-}
-
list *get_paths(char *filename)
{
char *path;
FILE *file = fopen(filename, "r");
+ if(!file) file_error(filename);
list *lines = make_list();
while((path=fgetl(file))){
list_insert(lines, path);
@@ -30,79 +19,251 @@
return lines;
}
-int get_truth(char *path)
-{
- if(strstr(path, "dog")) return 1;
- return 0;
-}
-
-batch load_list(list *paths)
-{
- char *path;
- batch data = make_batch(paths->size, 2);
- node *n = paths->front;
- int i;
- for(i = 0; i < data.n; ++i){
- path = (char *)n->val;
- data.images[i] = load_image(path);
- data.truth[i][0] = get_truth(path);
- n = n->next;
- }
- return data;
-}
-
-batch get_all_data(char *filename)
-{
- list *paths = get_paths(filename);
- batch b = load_list(paths);
- free_list_contents(paths);
- free_list(paths);
- return b;
-}
-
-void free_batch(batch b)
+void fill_truth(char *path, char **labels, int k, float *truth)
{
int i;
- for(i = 0; i < b.n; ++i){
- free_image(b.images[i]);
- free(b.truth[i]);
+ memset(truth, 0, k*sizeof(float));
+ for(i = 0; i < k; ++i){
+ if(strstr(path, labels[i])){
+ truth[i] = 1;
+ }
}
- free(b.images);
- free(b.truth);
}
-batch get_batch(char *filename, int curr, int total)
+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(float*));
+ d.X.cols = 0;
+ d.y = make_matrix(n, k);
+
+ for(i = 0; i < n; ++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]);
+ }
+ return d;
+}
+
+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);
- int i;
- int start = curr*plist->size/total;
- int end = (curr+1)*plist->size/total;
- batch b = make_batch(end-start, 2);
- for(i = start; i < end; ++i){
- b.images[i-start] = load_image(paths[i]);
- b.truth[i-start][0] = get_truth(paths[i]);
- }
+ data d = load_data_image_paths(paths, plist->size, labels, k, h, w);
free_list_contents(plist);
free_list(plist);
free(paths);
- return b;
+ return d;
}
-batch random_batch(char *filename, int n)
+void free_data(data d)
+{
+ if(!d.shallow){
+ free_matrix(d.X);
+ free_matrix(d.y);
+ }else{
+ free(d.X.vals);
+ free(d.y.vals);
+ }
+}
+
+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, 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, int h, int w)
+{
int i;
- batch b = make_batch(n, 2);
+ list *plist = get_paths(filename);
+ char **paths = (char **)list_to_array(plist);
+ char **random_paths = calloc(n, sizeof(char*));
for(i = 0; i < n; ++i){
int index = rand()%plist->size;
- b.images[i] = load_image(paths[index]);
- normalize_image(b.images[i]);
- b.truth[i][0] = get_truth(paths[index]);
+ random_paths[i] = paths[index];
+ if(i == 0) printf("%s\n", paths[index]);
}
+ data d = load_data_image_paths(random_paths, n, labels, k, h, w);
free_list_contents(plist);
free_list(plist);
free(paths);
- return b;
+ free(random_paths);
+ return d;
}
+
+data load_categorical_data_csv(char *filename, int target, int k)
+{
+ data d;
+ d.shallow = 0;
+ matrix X = csv_to_matrix(filename);
+ 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;
+ y.vals = truth;
+ d.X = X;
+ d.y = y;
+ free(truth_1d);
+ return d;
+}
+
+data load_cifar10_data(char *filename)
+{
+ data d;
+ d.shallow = 0;
+ 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");
+ if(!fp) file_error(filename);
+ 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];
+ }
+ }
+ translate_data_rows(d, -144);
+ scale_data_rows(d, 1./128);
+ //normalize_data_rows(d);
+ fclose(fp);
+ return d;
+}
+
+void get_batch(data d, int n, float *X, float *y)
+{
+ int j;
+ for(j = 0; j < n; ++j){
+ int index = rand()%d.X.rows;
+ memcpy(X+j*d.X.cols, d.X.vals[index], d.X.cols*sizeof(float));
+ memcpy(y+j*d.y.cols, d.y.vals[index], d.y.cols*sizeof(float));
+ }
+}
+
+data load_all_cifar10()
+{
+ data d;
+ d.shallow = 0;
+ int i,j,b;
+ matrix X = make_matrix(50000, 3072);
+ matrix y = make_matrix(50000, 10);
+ d.X = X;
+ d.y = y;
+
+
+ for(b = 0; b < 5; ++b){
+ char buff[256];
+ sprintf(buff, "data/cifar10/data_batch_%d.bin", b+1);
+ FILE *fp = fopen(buff, "rb");
+ if(!fp) file_error(buff);
+ for(i = 0; i < 10000; ++i){
+ unsigned char bytes[3073];
+ fread(bytes, 1, 3073, fp);
+ int class = bytes[0];
+ y.vals[i+b*10000][class] = 1;
+ for(j = 0; j < X.cols; ++j){
+ X.vals[i+b*10000][j] = (double)bytes[j+1];
+ }
+ }
+ fclose(fp);
+ }
+ //normalize_data_rows(d);
+ translate_data_rows(d, -144);
+ scale_data_rows(d, 1./128);
+ return d;
+}
+
+void randomize_data(data d)
+{
+ int i;
+ for(i = d.X.rows-1; i > 0; --i){
+ int index = rand()%i;
+ float *swap = d.X.vals[index];
+ d.X.vals[index] = d.X.vals[i];
+ d.X.vals[i] = swap;
+
+ swap = d.y.vals[index];
+ d.y.vals[index] = d.y.vals[i];
+ d.y.vals[i] = swap;
+ }
+}
+
+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 translate_data_rows(data d, float s)
+{
+ int i;
+ for(i = 0; i < d.X.rows; ++i){
+ translate_array(d.X.vals[i], d.X.cols, s);
+ }
+}
+
+void normalize_data_rows(data d)
+{
+ int i;
+ for(i = 0; i < d.X.rows; ++i){
+ normalize_array(d.X.vals[i], d.X.cols);
+ }
+}
+
+data *split_data(data d, int part, int total)
+{
+ data *split = calloc(2, sizeof(data));
+ int i;
+ int start = part*d.X.rows/total;
+ int end = (part+1)*d.X.rows/total;
+ data train;
+ data test;
+ train.shallow = test.shallow = 1;
+
+ test.X.rows = test.y.rows = end-start;
+ train.X.rows = train.y.rows = d.X.rows - (end-start);
+ 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(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];
+ train.y.vals[i] = d.y.vals[i];
+ }
+ for(i = start; i < end; ++i){
+ test.X.vals[i-start] = d.X.vals[i];
+ test.y.vals[i-start] = d.y.vals[i];
+ }
+ for(i = end; i < d.X.rows; ++i){
+ train.X.vals[i-(end-start)] = d.X.vals[i];
+ train.y.vals[i-(end-start)] = d.y.vals[i];
+ }
+ split[0] = train;
+ split[1] = test;
+ return split;
+}
+
--
Gitblit v1.10.0