blas.c

#include "blas.h"
#include "math.h"
#include <assert.h>

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 < 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];
                }
            }
        }
    }
}

void mean_cpu(float *x, int batch, int filters, int spatial, float *mean)
{
    float scale = 1./(batch * spatial);
    int i,j,k;
    for(i = 0; i < filters; ++i){
        mean[i] = 0;
        for(j = 0; j < batch; ++j){
            for(k = 0; k < spatial; ++k){
                int index = j*filters*spatial + i*spatial + k;
                mean[i] += x[index];
            }
        }
        mean[i] *= scale;
    }
}

void variance_cpu(float *x, float *mean, int batch, int filters, int spatial, float *variance)
{
    float scale = 1./(batch * spatial - 1);
    int i,j,k;
    for(i = 0; i < filters; ++i){
        variance[i] = 0;
        for(j = 0; j < batch; ++j){
            for(k = 0; k < spatial; ++k){
                int index = j*filters*spatial + i*spatial + k;
                variance[i] += pow((x[index] - mean[i]), 2);
            }
        }
        variance[i] *= scale;
    }
}

void normalize_cpu(float *x, float *mean, float *variance, int batch, int filters, int spatial)
{
    int b, f, i;
    for(b = 0; b < batch; ++b){
        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]) + .000001f);
            }
        }
    }
}

void const_cpu(int N, float ALPHA, float *X, int INCX)
{
    int i;
    for(i = 0; i < N; ++i) X[i*INCX] = ALPHA;
}

void mul_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 pow_cpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY)
{
    int i;
    for(i = 0; i < N; ++i) Y[i*INCY] = pow(X[i*INCX], ALPHA);
}

void axpy_cpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY)
{
    int i;
    for(i = 0; i < N; ++i) Y[i*INCY] += ALPHA*X[i*INCX];
}

void scal_cpu(int N, float ALPHA, float *X, int INCX)
{
    int i;
    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;
    float dot = 0;
    for(i = 0; i < N; ++i) dot += X[i*INCX] * Y[i*INCY];
    return dot;
}