From ac82bde55f3206a7a0d1b7a7580bea05096af32b Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Thu, 17 Apr 2014 22:07:00 +0000
Subject: [PATCH] New feature extraction method
---
src/connected_layer.c | 101 +++++++++++++++++++++++++++++++-------------------
1 files changed, 63 insertions(+), 38 deletions(-)
diff --git a/src/connected_layer.c b/src/connected_layer.c
index 6871b2e..16a39be 100644
--- a/src/connected_layer.c
+++ b/src/connected_layer.c
@@ -7,36 +7,60 @@
#include <stdlib.h>
#include <string.h>
-connected_layer *make_connected_layer(int inputs, int outputs, ACTIVATION activation)
+connected_layer *make_connected_layer(int batch, int inputs, int outputs, ACTIVATION activation)
{
fprintf(stderr, "Connected Layer: %d inputs, %d outputs\n", inputs, outputs);
int i;
connected_layer *layer = calloc(1, sizeof(connected_layer));
layer->inputs = inputs;
layer->outputs = outputs;
+ layer->batch=batch;
- layer->output = calloc(outputs, sizeof(double*));
- layer->delta = calloc(outputs, sizeof(double*));
+ layer->output = calloc(batch*outputs, sizeof(float*));
+ layer->delta = calloc(batch*outputs, sizeof(float*));
- layer->weight_updates = calloc(inputs*outputs, sizeof(double));
- layer->weight_momentum = calloc(inputs*outputs, sizeof(double));
- layer->weights = calloc(inputs*outputs, sizeof(double));
- double scale = 2./inputs;
+ layer->weight_updates = calloc(inputs*outputs, sizeof(float));
+ layer->weight_adapt = calloc(inputs*outputs, sizeof(float));
+ layer->weight_momentum = calloc(inputs*outputs, sizeof(float));
+ layer->weights = calloc(inputs*outputs, sizeof(float));
+ float scale = 1./inputs;
for(i = 0; i < inputs*outputs; ++i)
- layer->weights[i] = rand_normal()*scale;
+ layer->weights[i] = scale*(rand_uniform());
- layer->bias_updates = calloc(outputs, sizeof(double));
- layer->bias_momentum = calloc(outputs, sizeof(double));
- layer->biases = calloc(outputs, sizeof(double));
+ layer->bias_updates = calloc(outputs, sizeof(float));
+ layer->bias_adapt = calloc(outputs, sizeof(float));
+ layer->bias_momentum = calloc(outputs, sizeof(float));
+ layer->biases = calloc(outputs, sizeof(float));
for(i = 0; i < outputs; ++i)
//layer->biases[i] = rand_normal()*scale + scale;
- layer->biases[i] = 0;
+ layer->biases[i] = 1;
layer->activation = activation;
return layer;
}
-void update_connected_layer(connected_layer layer, double step, double momentum, double decay)
+/*
+void update_connected_layer(connected_layer layer, float step, float momentum, float decay)
+{
+ int i;
+ for(i = 0; i < layer.outputs; ++i){
+ float delta = layer.bias_updates[i];
+ layer.bias_adapt[i] += delta*delta;
+ layer.bias_momentum[i] = step/sqrt(layer.bias_adapt[i])*(layer.bias_updates[i]) + momentum*layer.bias_momentum[i];
+ layer.biases[i] += layer.bias_momentum[i];
+ }
+ for(i = 0; i < layer.outputs*layer.inputs; ++i){
+ float delta = layer.weight_updates[i];
+ layer.weight_adapt[i] += delta*delta;
+ layer.weight_momentum[i] = step/sqrt(layer.weight_adapt[i])*(layer.weight_updates[i] - decay*layer.weights[i]) + momentum*layer.weight_momentum[i];
+ layer.weights[i] += layer.weight_momentum[i];
+ }
+ memset(layer.bias_updates, 0, layer.outputs*sizeof(float));
+ memset(layer.weight_updates, 0, layer.outputs*layer.inputs*sizeof(float));
+}
+*/
+
+void update_connected_layer(connected_layer layer, float step, float momentum, float decay)
{
int i;
for(i = 0; i < layer.outputs; ++i){
@@ -47,58 +71,59 @@
layer.weight_momentum[i] = step*(layer.weight_updates[i] - decay*layer.weights[i]) + momentum*layer.weight_momentum[i];
layer.weights[i] += layer.weight_momentum[i];
}
- memset(layer.bias_updates, 0, layer.outputs*sizeof(double));
- memset(layer.weight_updates, 0, layer.outputs*layer.inputs*sizeof(double));
+ memset(layer.bias_updates, 0, layer.outputs*sizeof(float));
+ memset(layer.weight_updates, 0, layer.outputs*layer.inputs*sizeof(float));
}
-void forward_connected_layer(connected_layer layer, double *input)
+void forward_connected_layer(connected_layer layer, float *input)
{
int i;
- memcpy(layer.output, layer.biases, layer.outputs*sizeof(double));
- int m = 1;
+ memcpy(layer.output, layer.biases, layer.outputs*sizeof(float));
+ int m = layer.batch;
int k = layer.inputs;
int n = layer.outputs;
- double *a = input;
- double *b = layer.weights;
- double *c = layer.output;
+ float *a = input;
+ float *b = layer.weights;
+ float *c = layer.output;
gemm(0,0,m,n,k,1,a,k,b,n,1,c,n);
- for(i = 0; i < layer.outputs; ++i){
+ for(i = 0; i < layer.outputs*layer.batch; ++i){
layer.output[i] = activate(layer.output[i], layer.activation);
}
+ //for(i = 0; i < layer.outputs; ++i) if(i%(layer.outputs/10+1)==0) printf("%f, ", layer.output[i]); printf("\n");
}
-void learn_connected_layer(connected_layer layer, double *input)
+void learn_connected_layer(connected_layer layer, float *input)
{
int i;
- for(i = 0; i < layer.outputs; ++i){
+ for(i = 0; i < layer.outputs*layer.batch; ++i){
layer.delta[i] *= gradient(layer.output[i], layer.activation);
- layer.bias_updates[i] += layer.delta[i];
+ layer.bias_updates[i%layer.batch] += layer.delta[i]/layer.batch;
}
int m = layer.inputs;
- int k = 1;
+ int k = layer.batch;
int n = layer.outputs;
- double *a = input;
- double *b = layer.delta;
- double *c = layer.weight_updates;
+ float *a = input;
+ float *b = layer.delta;
+ float *c = layer.weight_updates;
gemm(0,0,m,n,k,1,a,k,b,n,1,c,n);
}
-void backward_connected_layer(connected_layer layer, double *input, double *delta)
+void backward_connected_layer(connected_layer layer, float *input, float *delta)
{
- memset(delta, 0, layer.inputs*sizeof(double));
+ memset(delta, 0, layer.inputs*sizeof(float));
int m = layer.inputs;
int k = layer.outputs;
- int n = 1;
+ int n = layer.batch;
- double *a = layer.weights;
- double *b = layer.delta;
- double *c = delta;
+ float *a = layer.weights;
+ float *b = layer.delta;
+ float *c = delta;
gemm(0,0,m,n,k,1,a,k,b,n,1,c,n);
}
/*
- void forward_connected_layer(connected_layer layer, double *input)
+ void forward_connected_layer(connected_layer layer, float *input)
{
int i, j;
for(i = 0; i < layer.outputs; ++i){
@@ -109,7 +134,7 @@
layer.output[i] = activate(layer.output[i], layer.activation);
}
}
- void learn_connected_layer(connected_layer layer, double *input)
+ void learn_connected_layer(connected_layer layer, float *input)
{
int i, j;
for(i = 0; i < layer.outputs; ++i){
@@ -120,7 +145,7 @@
}
}
}
- void backward_connected_layer(connected_layer layer, double *input, double *delta)
+ void backward_connected_layer(connected_layer layer, float *input, float *delta)
{
int i, j;
--
Gitblit v1.10.0