From 054e2b1954aafb15b0e983180dda309cfd5d831f Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Thu, 12 May 2016 20:36:11 +0000
Subject: [PATCH] not sure
---
src/convolutional_layer.c | 77 ++++----------------------------------
1 files changed, 9 insertions(+), 68 deletions(-)
diff --git a/src/convolutional_layer.c b/src/convolutional_layer.c
index cdc8bd3..d76dfcd 100644
--- a/src/convolutional_layer.c
+++ b/src/convolutional_layer.c
@@ -1,5 +1,6 @@
#include "convolutional_layer.h"
#include "utils.h"
+#include "batchnorm_layer.h"
#include "im2col.h"
#include "col2im.h"
#include "blas.h"
@@ -87,65 +88,7 @@
return float_to_image(w,h,c,l.delta);
}
-void backward_scale_cpu(float *x_norm, float *delta, int batch, int n, int size, float *scale_updates)
-{
- int i,b,f;
- for(f = 0; f < n; ++f){
- float sum = 0;
- for(b = 0; b < batch; ++b){
- for(i = 0; i < size; ++i){
- int index = i + size*(f + n*b);
- sum += delta[index] * x_norm[index];
- }
- }
- scale_updates[f] += sum;
- }
-}
-
-void mean_delta_cpu(float *delta, float *variance, int batch, int filters, int spatial, float *mean_delta)
-{
-
- int i,j,k;
- for(i = 0; i < filters; ++i){
- mean_delta[i] = 0;
- for (j = 0; j < batch; ++j) {
- for (k = 0; k < spatial; ++k) {
- int index = j*filters*spatial + i*spatial + k;
- mean_delta[i] += delta[index];
- }
- }
- mean_delta[i] *= (-1./sqrt(variance[i] + .00001f));
- }
-}
-void variance_delta_cpu(float *x, float *delta, float *mean, float *variance, int batch, int filters, int spatial, float *variance_delta)
-{
-
- int i,j,k;
- for(i = 0; i < filters; ++i){
- variance_delta[i] = 0;
- for(j = 0; j < batch; ++j){
- for(k = 0; k < spatial; ++k){
- int index = j*filters*spatial + i*spatial + k;
- variance_delta[i] += delta[index]*(x[index] - mean[i]);
- }
- }
- variance_delta[i] *= -.5 * pow(variance[i] + .00001f, (float)(-3./2.));
- }
-}
-void normalize_delta_cpu(float *x, float *mean, float *variance, float *mean_delta, float *variance_delta, int batch, int filters, int spatial, float *delta)
-{
- int f, j, k;
- for(j = 0; j < batch; ++j){
- for(f = 0; f < filters; ++f){
- for(k = 0; k < spatial; ++k){
- int index = j*filters*spatial + f*spatial + k;
- delta[index] = delta[index] * 1./(sqrt(variance[f]) + .00001f) + variance_delta[f] * 2. * (x[index] - mean[f]) / (spatial * batch) + mean_delta[f]/(spatial*batch);
- }
- }
- }
-}
-
-convolutional_layer make_convolutional_layer(int batch, int h, int w, int c, int n, int size, int stride, int pad, ACTIVATION activation, int batch_normalize, int binary)
+convolutional_layer make_convolutional_layer(int batch, int h, int w, int c, int n, int size, int stride, int pad, ACTIVATION activation, int batch_normalize, int binary, int xnor)
{
int i;
convolutional_layer l = {0};
@@ -220,6 +163,11 @@
if(binary){
l.binary_filters_gpu = cuda_make_array(l.filters, c*n*size*size);
}
+ if(xnor){
+ l.binary_filters_gpu = cuda_make_array(l.filters, c*n*size*size);
+ l.binary_input_gpu = cuda_make_array(0, l.inputs*l.batch);
+ }
+ l.xnor = xnor;
if(batch_normalize){
l.mean_gpu = cuda_make_array(l.mean, n);
@@ -256,7 +204,7 @@
void test_convolutional_layer()
{
- convolutional_layer l = make_convolutional_layer(1, 5, 5, 3, 2, 5, 2, 1, LEAKY, 1, 0);
+ convolutional_layer l = make_convolutional_layer(1, 5, 5, 3, 2, 5, 2, 1, LEAKY, 1, 0, 0);
l.batch_normalize = 1;
float data[] = {1,1,1,1,1,
1,1,1,1,1,
@@ -397,14 +345,7 @@
}
if(l.batch_normalize){
- if(state.train){
- mean_cpu(l.output, l.batch, l.n, l.out_h*l.out_w, l.mean);
- variance_cpu(l.output, l.mean, l.batch, l.n, l.out_h*l.out_w, l.variance);
- normalize_cpu(l.output, l.mean, l.variance, l.batch, l.n, l.out_h*l.out_w);
- } else {
- normalize_cpu(l.output, l.rolling_mean, l.rolling_variance, l.batch, l.n, l.out_h*l.out_w);
- }
- scale_bias(l.output, l.scales, l.batch, l.n, out_h*out_w);
+ forward_batchnorm_layer(l, state);
}
add_bias(l.output, l.biases, l.batch, l.n, out_h*out_w);
--
Gitblit v1.10.0