From 5bc62b14e06a3fcfda4e3a19fba77589920eddee Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Mon, 03 Jul 2017 11:12:52 +0000
Subject: [PATCH] Memory leak fixed
---
src/blas.c | 132 +++++++++++++++++++++++++++++++++++++++++---
1 files changed, 123 insertions(+), 9 deletions(-)
diff --git a/src/blas.c b/src/blas.c
index 941109e..31bd86b 100644
--- a/src/blas.c
+++ b/src/blas.c
@@ -1,15 +1,78 @@
#include "blas.h"
#include "math.h"
-
-void shortcut_cpu(float *out, int w, int h, int c, int batch, int sample, float *add, int stride, int c2)
+#include <assert.h>
+#include <float.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+void reorg_cpu(float *x, int w, int h, int c, int batch, int stride, int forward, float *out)
{
+ int b,i,j,k;
+ int out_c = c/(stride*stride);
+
+ for(b = 0; b < batch; ++b){
+ for(k = 0; k < c; ++k){
+ for(j = 0; j < h; ++j){
+ for(i = 0; i < w; ++i){
+ int in_index = i + w*(j + h*(k + c*b));
+ int c2 = k % out_c;
+ int offset = k / out_c;
+ int w2 = i*stride + offset % stride;
+ int h2 = j*stride + offset / stride;
+ int out_index = w2 + w*stride*(h2 + h*stride*(c2 + out_c*b));
+ if(forward) out[out_index] = x[in_index];
+ else out[in_index] = x[out_index];
+ }
+ }
+ }
+ }
+}
+
+void flatten(float *x, int size, int layers, int batch, int forward)
+{
+ float *swap = calloc(size*layers*batch, sizeof(float));
+ int i,c,b;
+ for(b = 0; b < batch; ++b){
+ for(c = 0; c < layers; ++c){
+ for(i = 0; i < size; ++i){
+ int i1 = b*layers*size + c*size + i;
+ int i2 = b*layers*size + i*layers + c;
+ if (forward) swap[i2] = x[i1];
+ else swap[i1] = x[i2];
+ }
+ }
+ }
+ memcpy(x, swap, size*layers*batch*sizeof(float));
+ free(swap);
+}
+
+void weighted_sum_cpu(float *a, float *b, float *s, int n, float *c)
+{
+ int i;
+ for(i = 0; i < n; ++i){
+ c[i] = s[i]*a[i] + (1-s[i])*(b ? b[i] : 0);
+ }
+}
+
+void shortcut_cpu(int batch, int w1, int h1, int c1, float *add, int w2, int h2, int c2, float *out)
+{
+ int stride = w1/w2;
+ int sample = w2/w1;
+ assert(stride == h1/h2);
+ assert(sample == h2/h1);
+ if(stride < 1) stride = 1;
+ if(sample < 1) sample = 1;
+ int minw = (w1 < w2) ? w1 : w2;
+ int minh = (h1 < h2) ? h1 : h2;
+ int minc = (c1 < c2) ? c1 : c2;
+
int i,j,k,b;
for(b = 0; b < batch; ++b){
- for(k = 0; k < c && k < c2; ++k){
- for(j = 0; j < h/sample; ++j){
- for(i = 0; i < w/sample; ++i){
- int out_index = i*sample + w*(j*sample + h*(k + c*b));
- int add_index = b*w*stride/sample*h*stride/sample*c2 + i*stride + w*stride/sample*(j*stride + h*stride/sample*k);
+ for(k = 0; k < minc; ++k){
+ for(j = 0; j < minh; ++j){
+ for(i = 0; i < minw; ++i){
+ int out_index = i*sample + w2*(j*sample + h2*(k + c2*b));
+ int add_index = i*stride + w1*(j*stride + h1*(k + c1*b));
out[out_index] += add[add_index];
}
}
@@ -35,7 +98,7 @@
void variance_cpu(float *x, float *mean, int batch, int filters, int spatial, float *variance)
{
- float scale = 1./(batch * spatial);
+ float scale = 1./(batch * spatial - 1);
int i,j,k;
for(i = 0; i < filters; ++i){
variance[i] = 0;
@@ -56,7 +119,7 @@
for(f = 0; f < filters; ++f){
for(i = 0; i < spatial; ++i){
int index = b*filters*spatial + f*spatial + i;
- x[index] = (x[index] - mean[f])/(sqrt(variance[f]));
+ x[index] = (x[index] - mean[f])/(sqrt(variance[f]) + .000001f);
}
}
}
@@ -92,12 +155,45 @@
for(i = 0; i < N; ++i) X[i*INCX] *= ALPHA;
}
+void fill_cpu(int N, float ALPHA, float *X, int INCX)
+{
+ int i;
+ for(i = 0; i < N; ++i) X[i*INCX] = ALPHA;
+}
+
void copy_cpu(int N, float *X, int INCX, float *Y, int INCY)
{
int i;
for(i = 0; i < N; ++i) Y[i*INCY] = X[i*INCX];
}
+void smooth_l1_cpu(int n, float *pred, float *truth, float *delta, float *error)
+{
+ int i;
+ for(i = 0; i < n; ++i){
+ float diff = truth[i] - pred[i];
+ float abs_val = fabs(diff);
+ if(abs_val < 1) {
+ error[i] = diff * diff;
+ delta[i] = diff;
+ }
+ else {
+ error[i] = 2*abs_val - 1;
+ delta[i] = (diff < 0) ? -1 : 1;
+ }
+ }
+}
+
+void l2_cpu(int n, float *pred, float *truth, float *delta, float *error)
+{
+ int i;
+ for(i = 0; i < n; ++i){
+ float diff = truth[i] - pred[i];
+ error[i] = diff * diff;
+ delta[i] = diff;
+ }
+}
+
float dot_cpu(int N, float *X, int INCX, float *Y, int INCY)
{
int i;
@@ -106,3 +202,21 @@
return dot;
}
+void softmax(float *input, int n, float temp, float *output)
+{
+ int i;
+ float sum = 0;
+ float largest = -FLT_MAX;
+ for(i = 0; i < n; ++i){
+ if(input[i] > largest) largest = input[i];
+ }
+ for(i = 0; i < n; ++i){
+ float e = exp(input[i]/temp - largest/temp);
+ sum += e;
+ output[i] = e;
+ }
+ for(i = 0; i < n; ++i){
+ output[i] /= sum;
+ }
+}
+
--
Gitblit v1.10.0