From 0c2cf402aff1b6eef47e8bdfae77472589c42e0c Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Fri, 09 May 2014 22:35:58 +0000
Subject: [PATCH] Some small fixes for frame

---
 src/connected_layer.c |   93 ++++++++++++++--------------------------------
 1 files changed, 28 insertions(+), 65 deletions(-)

diff --git a/src/connected_layer.c b/src/connected_layer.c
index 5f6631c..72cb3fb 100644
--- a/src/connected_layer.c
+++ b/src/connected_layer.c
@@ -7,30 +7,34 @@
 #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, float dropout, 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->dropout = dropout;
 
-    layer->output = calloc(outputs, sizeof(float*));
-    layer->delta = calloc(outputs, sizeof(float*));
+    layer->output = calloc(batch*outputs, sizeof(float*));
+    layer->delta = calloc(batch*outputs, sizeof(float*));
 
     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 = 2./inputs;
+    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(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;
@@ -51,84 +55,43 @@
     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 = 1;
+    int m = layer.batch;
     int k = layer.inputs;
     int n = layer.outputs;
     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){
-        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; ++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];
     }
     int m = layer.inputs;
-    int k = 1;
+    int k = layer.batch;
     int n = layer.outputs;
     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);
+
+    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 = 1;
-
-    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