From c7c1e0e7b719711ddaf13f128a18e6830d5941e3 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Fri, 05 Feb 2016 08:15:12 +0000
Subject: [PATCH] rnn stuff
---
src/utils.c | 415 ++++++++++++++++++++++++++++++++++++++++++++++++++---------
1 files changed, 350 insertions(+), 65 deletions(-)
diff --git a/src/utils.c b/src/utils.c
index 3b8b5a8..ec87a26 100644
--- a/src/utils.c
+++ b/src/utils.c
@@ -1,12 +1,179 @@
-#include "utils.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <math.h>
+#include <unistd.h>
+#include <float.h>
+#include <limits.h>
-void error(char *s)
+#include "utils.h"
+
+void sorta_shuffle(void *arr, size_t n, size_t size, size_t sections)
{
- fprintf(stderr, "Error: %s\n", s);
+ size_t i;
+ for(i = 0; i < sections; ++i){
+ size_t start = n*i/sections;
+ size_t end = n*(i+1)/sections;
+ size_t num = end-start;
+ shuffle(arr+(start*size), num, size);
+ }
+}
+
+void shuffle(void *arr, size_t n, size_t size)
+{
+ size_t i;
+ void *swp = calloc(1, size);
+ for(i = 0; i < n-1; ++i){
+ size_t j = i + rand()/(RAND_MAX / (n-i)+1);
+ memcpy(swp, arr+(j*size), size);
+ memcpy(arr+(j*size), arr+(i*size), size);
+ memcpy(arr+(i*size), swp, size);
+ }
+}
+
+void del_arg(int argc, char **argv, int index)
+{
+ int i;
+ for(i = index; i < argc-1; ++i) argv[i] = argv[i+1];
+ argv[i] = 0;
+}
+
+int find_arg(int argc, char* argv[], char *arg)
+{
+ int i;
+ for(i = 0; i < argc; ++i) {
+ if(!argv[i]) continue;
+ if(0==strcmp(argv[i], arg)) {
+ del_arg(argc, argv, i);
+ return 1;
+ }
+ }
+ return 0;
+}
+
+int find_int_arg(int argc, char **argv, char *arg, int def)
+{
+ int i;
+ for(i = 0; i < argc-1; ++i){
+ if(!argv[i]) continue;
+ if(0==strcmp(argv[i], arg)){
+ def = atoi(argv[i+1]);
+ del_arg(argc, argv, i);
+ del_arg(argc, argv, i);
+ break;
+ }
+ }
+ return def;
+}
+
+float find_float_arg(int argc, char **argv, char *arg, float def)
+{
+ int i;
+ for(i = 0; i < argc-1; ++i){
+ if(!argv[i]) continue;
+ if(0==strcmp(argv[i], arg)){
+ def = atof(argv[i+1]);
+ del_arg(argc, argv, i);
+ del_arg(argc, argv, i);
+ break;
+ }
+ }
+ return def;
+}
+
+char *find_char_arg(int argc, char **argv, char *arg, char *def)
+{
+ int i;
+ for(i = 0; i < argc-1; ++i){
+ if(!argv[i]) continue;
+ if(0==strcmp(argv[i], arg)){
+ def = argv[i+1];
+ del_arg(argc, argv, i);
+ del_arg(argc, argv, i);
+ break;
+ }
+ }
+ return def;
+}
+
+
+char *basecfg(char *cfgfile)
+{
+ char *c = cfgfile;
+ char *next;
+ while((next = strchr(c, '/')))
+ {
+ c = next+1;
+ }
+ c = copy_string(c);
+ next = strchr(c, '.');
+ if (next) *next = 0;
+ return c;
+}
+
+int alphanum_to_int(char c)
+{
+ return (c < 58) ? c - 48 : c-87;
+}
+char int_to_alphanum(int i)
+{
+ if (i == 36) return '.';
+ return (i < 10) ? i + 48 : i + 87;
+}
+
+void pm(int M, int N, float *A)
+{
+ int i,j;
+ for(i =0 ; i < M; ++i){
+ printf("%d ", i+1);
+ for(j = 0; j < N; ++j){
+ printf("%2.4f, ", A[i*N+j]);
+ }
+ printf("\n");
+ }
+ printf("\n");
+}
+
+char *find_replace(char *str, char *orig, char *rep)
+{
+ static char buffer[4096];
+ char *p;
+
+ if(!(p = strstr(str, orig))) // Is 'orig' even in 'str'?
+ return str;
+
+ strncpy(buffer, str, p-str); // Copy characters from 'str' start to 'orig' st$
+ buffer[p-str] = '\0';
+
+ sprintf(buffer+(p-str), "%s%s", rep, p+strlen(orig));
+
+ return buffer;
+}
+
+float sec(clock_t clocks)
+{
+ return (float)clocks/CLOCKS_PER_SEC;
+}
+
+void top_k(float *a, int n, int k, int *index)
+{
+ int i,j;
+ for(j = 0; j < k; ++j) index[j] = -1;
+ for(i = 0; i < n; ++i){
+ int curr = i;
+ for(j = 0; j < k; ++j){
+ if((index[j] < 0) || a[curr] > a[index[j]]){
+ int swap = curr;
+ curr = index[j];
+ index[j] = swap;
+ }
+ }
+ }
+}
+
+void error(const char *s)
+{
+ perror(s);
exit(0);
}
@@ -24,8 +191,8 @@
list *split_str(char *s, char delim)
{
- int i;
- int len = strlen(s);
+ size_t i;
+ size_t len = strlen(s);
list *l = make_list();
list_insert(l, s);
for(i = 0; i < len; ++i){
@@ -39,9 +206,9 @@
void strip(char *s)
{
- int i;
- int len = strlen(s);
- int offset = 0;
+ size_t i;
+ size_t len = strlen(s);
+ size_t offset = 0;
for(i = 0; i < len; ++i){
char c = s[i];
if(c==' '||c=='\t'||c=='\n') ++offset;
@@ -52,9 +219,9 @@
void strip_char(char *s, char bad)
{
- int i;
- int len = strlen(s);
- int offset = 0;
+ size_t i;
+ size_t len = strlen(s);
+ size_t offset = 0;
for(i = 0; i < len; ++i){
char c = s[i];
if(c==bad) ++offset;
@@ -63,30 +230,65 @@
s[len-offset] = '\0';
}
+void free_ptrs(void **ptrs, int n)
+{
+ int i;
+ for(i = 0; i < n; ++i) free(ptrs[i]);
+ free(ptrs);
+}
+
char *fgetl(FILE *fp)
{
if(feof(fp)) return 0;
- int size = 512;
+ size_t size = 512;
char *line = malloc(size*sizeof(char));
if(!fgets(line, size, fp)){
free(line);
return 0;
}
- int curr = strlen(line);
-
- while(line[curr-1]!='\n'){
- size *= 2;
- line = realloc(line, size*sizeof(char));
- if(!line) malloc_error();
- fgets(&line[curr], size-curr, fp);
+ size_t curr = strlen(line);
+
+ while((line[curr-1] != '\n') && !feof(fp)){
+ if(curr == size-1){
+ size *= 2;
+ line = realloc(line, size*sizeof(char));
+ if(!line) {
+ printf("%ld\n", size);
+ malloc_error();
+ }
+ }
+ size_t readsize = size-curr;
+ if(readsize > INT_MAX) readsize = INT_MAX-1;
+ fgets(&line[curr], readsize, fp);
curr = strlen(line);
}
- line[curr-1] = '\0';
+ if(line[curr-1] == '\n') line[curr-1] = '\0';
return line;
}
+void read_all(int fd, char *buffer, size_t bytes)
+{
+ size_t n = 0;
+ while(n < bytes){
+ int next = read(fd, buffer + n, bytes-n);
+ if(next <= 0) error("read failed");
+ n += next;
+ }
+}
+
+void write_all(int fd, char *buffer, size_t bytes)
+{
+ size_t n = 0;
+ while(n < bytes){
+ size_t next = write(fd, buffer + n, bytes-n);
+ if(next <= 0) error("write failed");
+ n += next;
+ }
+}
+
+
char *copy_string(char *s)
{
char *copy = malloc(strlen(s)+1);
@@ -113,66 +315,94 @@
int count_fields(char *line)
{
- int count = 0;
- int done = 0;
+ int count = 0;
+ int done = 0;
char *c;
- for(c = line; !done; ++c){
- done = (*c == '\0');
- if(*c == ',' || done) ++count;
- }
- return count;
+ for(c = line; !done; ++c){
+ done = (*c == '\0');
+ if(*c == ',' || done) ++count;
+ }
+ return count;
}
-double *parse_fields(char *line, int n)
+float *parse_fields(char *line, int n)
{
- double *field = calloc(n, sizeof(double));
- char *c, *p, *end;
- int count = 0;
- int done = 0;
- for(c = line, p = line; !done; ++c){
- done = (*c == '\0');
- if(*c == ',' || done){
- *c = '\0';
- field[count] = strtod(p, &end);
- if(p == c) field[count] = nan("");
- if(end != c && (end != c-1 || *end != '\r')) field[count] = nan(""); //DOS file formats!
- p = c+1;
- ++count;
- }
- }
- return field;
+ float *field = calloc(n, sizeof(float));
+ char *c, *p, *end;
+ int count = 0;
+ int done = 0;
+ for(c = line, p = line; !done; ++c){
+ done = (*c == '\0');
+ if(*c == ',' || done){
+ *c = '\0';
+ field[count] = strtod(p, &end);
+ if(p == c) field[count] = nan("");
+ if(end != c && (end != c-1 || *end != '\r')) field[count] = nan(""); //DOS file formats!
+ p = c+1;
+ ++count;
+ }
+ }
+ return field;
}
-double mean_array(double *a, int n)
+float sum_array(float *a, int n)
{
int i;
- double sum = 0;
+ float sum = 0;
for(i = 0; i < n; ++i) sum += a[i];
- return sum/n;
+ return sum;
}
-double variance_array(double *a, int n)
+float mean_array(float *a, int n)
+{
+ return sum_array(a,n)/n;
+}
+
+void mean_arrays(float **a, int n, int els, float *avg)
{
int i;
- double sum = 0;
- double mean = mean_array(a, n);
+ int j;
+ memset(avg, 0, els*sizeof(float));
+ for(j = 0; j < n; ++j){
+ for(i = 0; i < els; ++i){
+ avg[i] += a[j][i];
+ }
+ }
+ for(i = 0; i < els; ++i){
+ avg[i] /= n;
+ }
+}
+
+float variance_array(float *a, int n)
+{
+ int i;
+ float sum = 0;
+ float mean = mean_array(a, n);
for(i = 0; i < n; ++i) sum += (a[i] - mean)*(a[i]-mean);
- double variance = sum/n;
+ float variance = sum/n;
return variance;
}
-double constrain(double a, double max)
+float constrain(float min, float max, float a)
{
- if(a > abs(max)) return abs(max);
- if(a < -abs(max)) return -abs(max);
+ if (a < min) return min;
+ if (a > max) return max;
return a;
}
-void normalize_array(double *a, int n)
+float mse_array(float *a, int n)
{
int i;
- double mu = mean_array(a,n);
- double sigma = sqrt(variance_array(a,n));
+ float sum = 0;
+ for(i = 0; i < n; ++i) sum += a[i]*a[i];
+ return sqrt(sum/n);
+}
+
+void normalize_array(float *a, int n)
+{
+ int i;
+ float mu = mean_array(a,n);
+ float sigma = sqrt(variance_array(a,n));
for(i = 0; i < n; ++i){
a[i] = (a[i] - mu)/sigma;
}
@@ -180,7 +410,7 @@
sigma = sqrt(variance_array(a,n));
}
-void translate_array(double *a, int n, double s)
+void translate_array(float *a, int n, float s)
{
int i;
for(i = 0; i < n; ++i){
@@ -188,18 +418,29 @@
}
}
-void scale_array(double *a, int n, double s)
+float mag_array(float *a, int n)
+{
+ int i;
+ float sum = 0;
+ for(i = 0; i < n; ++i){
+ sum += a[i]*a[i];
+ }
+ return sqrt(sum);
+}
+
+void scale_array(float *a, int n, float s)
{
int i;
for(i = 0; i < n; ++i){
a[i] *= s;
}
}
-int max_index(double *a, int n)
+
+int max_index(float *a, int n)
{
if(n <= 0) return -1;
int i, max_i = 0;
- double max = a[0];
+ float max = a[0];
for(i = 1; i < n; ++i){
if(a[i] > max){
max = a[i];
@@ -209,10 +450,54 @@
return max_i;
}
-double rand_normal()
+// From http://en.wikipedia.org/wiki/Box%E2%80%93Muller_transform
+#define TWO_PI 6.2831853071795864769252866
+float rand_normal()
+{
+ static int haveSpare = 0;
+ static double rand1, rand2;
+
+ if(haveSpare)
+ {
+ haveSpare = 0;
+ return sqrt(rand1) * sin(rand2);
+ }
+
+ haveSpare = 1;
+
+ rand1 = rand() / ((double) RAND_MAX);
+ if(rand1 < 1e-100) rand1 = 1e-100;
+ rand1 = -2 * log(rand1);
+ rand2 = (rand() / ((double) RAND_MAX)) * TWO_PI;
+
+ return sqrt(rand1) * cos(rand2);
+}
+
+/*
+ float rand_normal()
+ {
+ int n = 12;
+ int i;
+ float sum= 0;
+ for(i = 0; i < n; ++i) sum += (float)rand()/RAND_MAX;
+ return sum-n/2.;
+ }
+ */
+
+float rand_uniform(float min, float max)
+{
+ return ((float)rand()/RAND_MAX * (max - min)) + min;
+}
+
+float **one_hot_encode(float *a, int n, int k)
{
int i;
- double sum= 0;
- for(i = 0; i < 12; ++i) sum += (double)rand()/RAND_MAX;
- return sum-6.;
+ float **t = calloc(n, sizeof(float*));
+ for(i = 0; i < n; ++i){
+ t[i] = calloc(k, sizeof(float));
+ int index = (int)a[i];
+ t[i][index] = 1;
+ }
+ return t;
}
+
--
Gitblit v1.10.0