From cd8d53df21f3ad2810add2a8cff766c745f55a17 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Fri, 09 May 2014 22:14:52 +0000
Subject: [PATCH] So there WAS this huge bug. Gone now
---
src/connected_layer.c | 96 ++++++++---------------------------------------
1 files changed, 17 insertions(+), 79 deletions(-)
diff --git a/src/connected_layer.c b/src/connected_layer.c
index 16a39be..72cb3fb 100644
--- a/src/connected_layer.c
+++ b/src/connected_layer.c
@@ -7,7 +7,7 @@
#include <stdlib.h>
#include <string.h>
-connected_layer *make_connected_layer(int batch, int inputs, int outputs, ACTIVATION activation)
+connected_layer *make_connected_layer(int batch, int inputs, int outputs, float dropout, ACTIVATION activation)
{
fprintf(stderr, "Connected Layer: %d inputs, %d outputs\n", inputs, outputs);
int i;
@@ -15,6 +15,7 @@
layer->inputs = inputs;
layer->outputs = outputs;
layer->batch=batch;
+ layer->dropout = dropout;
layer->output = calloc(batch*outputs, sizeof(float*));
layer->delta = calloc(batch*outputs, sizeof(float*));
@@ -39,27 +40,6 @@
return layer;
}
-/*
-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;
@@ -75,9 +55,9 @@
memset(layer.weight_updates, 0, layer.outputs*layer.inputs*sizeof(float));
}
-void forward_connected_layer(connected_layer layer, float *input)
+void forward_connected_layer(connected_layer layer, float *input, int train)
{
- int i;
+ if(!train) layer.dropout = 0;
memcpy(layer.output, layer.biases, layer.outputs*sizeof(float));
int m = layer.batch;
int k = layer.inputs;
@@ -86,18 +66,15 @@
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*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");
+ activate_array(layer.output, layer.outputs*layer.batch, layer.activation, layer.dropout);
}
-void learn_connected_layer(connected_layer layer, float *input)
+void backward_connected_layer(connected_layer layer, float *input, float *delta)
{
int i;
for(i = 0; i < layer.outputs*layer.batch; ++i){
layer.delta[i] *= gradient(layer.output[i], layer.activation);
- layer.bias_updates[i%layer.batch] += layer.delta[i]/layer.batch;
+ layer.bias_updates[i%layer.batch] += layer.delta[i];
}
int m = layer.inputs;
int k = layer.batch;
@@ -106,54 +83,15 @@
float *b = layer.delta;
float *c = layer.weight_updates;
gemm(0,0,m,n,k,1,a,k,b,n,1,c,n);
+
+ m = layer.inputs;
+ k = layer.outputs;
+ n = layer.batch;
+
+ a = layer.weights;
+ b = layer.delta;
+ c = delta;
+
+ if(c) gemm(0,0,m,n,k,1,a,k,b,n,0,c,n);
}
-void backward_connected_layer(connected_layer layer, float *input, float *delta)
-{
- memset(delta, 0, layer.inputs*sizeof(float));
-
- int m = layer.inputs;
- int k = layer.outputs;
- int n = layer.batch;
-
- 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, float *input)
- {
- int i, j;
- for(i = 0; i < layer.outputs; ++i){
- layer.output[i] = layer.biases[i];
- for(j = 0; j < layer.inputs; ++j){
- layer.output[i] += input[j]*layer.weights[i*layer.inputs + j];
- }
- layer.output[i] = activate(layer.output[i], layer.activation);
- }
- }
- void learn_connected_layer(connected_layer layer, float *input)
- {
- int i, j;
- for(i = 0; i < layer.outputs; ++i){
- layer.delta[i] *= gradient(layer.output[i], layer.activation);
- layer.bias_updates[i] += layer.delta[i];
- for(j = 0; j < layer.inputs; ++j){
- layer.weight_updates[i*layer.inputs + j] += layer.delta[i]*input[j];
- }
- }
- }
- void backward_connected_layer(connected_layer layer, float *input, float *delta)
- {
- int i, j;
-
- for(j = 0; j < layer.inputs; ++j){
- delta[j] = 0;
- for(i = 0; i < layer.outputs; ++i){
- delta[j] += layer.delta[i]*layer.weights[i*layer.inputs + j];
- }
- }
- }
- */
--
Gitblit v1.10.0