From b32a287e38f4c6a41828f18b4669dec9f3af4943 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Thu, 17 Jul 2014 17:17:52 +0000
Subject: [PATCH] Merge branch 'master' of pjreddie.com:jnet
---
src/connected_layer.c | 37 ++++++++++++++++++-------------------
1 files changed, 18 insertions(+), 19 deletions(-)
diff --git a/src/connected_layer.c b/src/connected_layer.c
index 792f20b..bebf2d9 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*));
@@ -54,10 +55,13 @@
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;
- memcpy(layer.output, layer.biases, layer.outputs*sizeof(float));
+ if(!train) layer.dropout = 0;
+ for(i = 0; i < layer.batch; ++i){
+ memcpy(layer.output+i*layer.outputs, layer.biases, layer.outputs*sizeof(float));
+ }
int m = layer.batch;
int k = layer.inputs;
int n = layer.outputs;
@@ -65,17 +69,15 @@
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);
- }
+ 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.outputs] += layer.delta[i];
}
int m = layer.inputs;
int k = layer.batch;
@@ -83,19 +85,16 @@
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);
-}
+ gemm(1,0,m,n,k,1,a,m,b,n,1,c,n);
-void backward_connected_layer(connected_layer layer, float *input, float *delta)
-{
- int m = layer.inputs;
- int k = layer.outputs;
- int n = layer.batch;
+ m = layer.batch;
+ k = layer.outputs;
+ n = layer.inputs;
- float *a = layer.weights;
- float *b = layer.delta;
- float *c = delta;
+ a = layer.delta;
+ b = layer.weights;
+ c = delta;
- gemm(0,0,m,n,k,1,a,k,b,n,0,c,n);
+ if(c) gemm(0,1,m,n,k,1,a,k,b,k,0,c,n);
}
--
Gitblit v1.10.0