| | |
| | | #include "blas.h" |
| | | #include "math.h" |
| | | #include <assert.h> |
| | | #include <stdio.h> |
| | | #include <stdlib.h> |
| | | #include <string.h> |
| | | |
| | | void reorg(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) |
| | | { |
| | |
| | | |
| | | 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; |
| | |
| | | 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]) + .00001f); |
| | | x[index] = (x[index] - mean[f])/(sqrt(variance[f]) + .000001f); |
| | | } |
| | | } |
| | | } |