From 787d5345609459f21fd65d2d8b4fcd55201e21a1 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Mon, 13 Oct 2014 07:31:10 +0000
Subject: [PATCH] Convolutional working on GPU
---
src/connected_layer.c | 141 ++++++++++++++++++++++++++---------------------
1 files changed, 78 insertions(+), 63 deletions(-)
diff --git a/src/connected_layer.c b/src/connected_layer.c
index fe904ba..95db5d5 100644
--- a/src/connected_layer.c
+++ b/src/connected_layer.c
@@ -1,92 +1,107 @@
#include "connected_layer.h"
+#include "utils.h"
+#include "mini_blas.h"
+#include <math.h>
+#include <stdio.h>
#include <stdlib.h>
#include <string.h>
-double activation(double x)
+connected_layer *make_connected_layer(int batch, int inputs, int outputs, ACTIVATION activation, float learning_rate, float momentum, float decay)
{
- return x*(x>0);
-}
-
-double gradient(double x)
-{
- return (x>=0);
-}
-
-connected_layer make_connected_layer(int inputs, int outputs)
-{
+ fprintf(stderr, "Connected Layer: %d inputs, %d outputs\n", inputs, outputs);
int i;
- connected_layer layer;
- layer.inputs = inputs;
- layer.outputs = outputs;
+ connected_layer *layer = calloc(1, sizeof(connected_layer));
- layer.output = calloc(outputs, sizeof(double*));
+ layer->learning_rate = learning_rate;
+ layer->momentum = momentum;
+ layer->decay = decay;
- layer.weight_updates = calloc(inputs*outputs, sizeof(double));
- layer.weights = calloc(inputs*outputs, sizeof(double));
+ layer->inputs = inputs;
+ layer->outputs = outputs;
+ layer->batch=batch;
+
+ 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 = 1./inputs;
+ scale = .05;
for(i = 0; i < inputs*outputs; ++i)
- layer.weights[i] = .5 - (double)rand()/RAND_MAX;
+ layer->weights[i] = scale*2*(rand_uniform()-.5);
- layer.bias_updates = calloc(outputs, sizeof(double));
- layer.biases = calloc(outputs, sizeof(double));
- for(i = 0; i < outputs; ++i)
- layer.biases[i] = (double)rand()/RAND_MAX;
+ 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] = 1;
+ }
+ #ifdef GPU
+ #endif
+ layer->activation = activation;
return layer;
}
-void run_connected_layer(double *input, connected_layer layer)
+void update_connected_layer(connected_layer layer)
{
- int i, j;
+ int i;
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.outputs + j];
- }
- layer.output[i] = activation(layer.output[i]);
+ layer.bias_momentum[i] = layer.learning_rate*(layer.bias_updates[i]) + layer.momentum*layer.bias_momentum[i];
+ layer.biases[i] += layer.bias_momentum[i];
}
+ for(i = 0; i < layer.outputs*layer.inputs; ++i){
+ layer.weight_momentum[i] = layer.learning_rate*(layer.weight_updates[i] - layer.decay*layer.weights[i]) + layer.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 backpropagate_connected_layer(double *input, connected_layer layer)
+void forward_connected_layer(connected_layer layer, float *input)
{
- int i, j;
- double *old_input = calloc(layer.inputs, sizeof(double));
- memcpy(old_input, input, layer.inputs*sizeof(double));
- memset(input, 0, layer.inputs*sizeof(double));
-
- for(i = 0; i < layer.outputs; ++i){
- for(j = 0; j < layer.inputs; ++j){
- input[j] += layer.output[i]*layer.weights[i*layer.outputs + j];
- }
+ int i;
+ for(i = 0; i < layer.batch; ++i){
+ memcpy(layer.output+i*layer.outputs, layer.biases, layer.outputs*sizeof(float));
}
- for(j = 0; j < layer.inputs; ++j){
- input[j] = input[j]*gradient(old_input[j]);
- }
- free(old_input);
+ 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);
+ activate_array(layer.output, layer.outputs*layer.batch, layer.activation);
}
-void calculate_updates_connected_layer(double *input, connected_layer layer)
+void backward_connected_layer(connected_layer layer, float *input, float *delta)
{
- int i, j;
- for(i = 0; i < layer.outputs; ++i){
- layer.bias_updates[i] += layer.output[i];
- for(j = 0; j < layer.inputs; ++j){
- layer.weight_updates[i*layer.outputs + j] += layer.output[i]*input[j];
- }
+ 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.outputs] += layer.delta[i];
}
-}
+ int m = layer.inputs;
+ int k = layer.batch;
+ int n = layer.outputs;
+ float *a = input;
+ float *b = layer.delta;
+ float *c = layer.weight_updates;
+ gemm(1,0,m,n,k,1,a,m,b,n,1,c,n);
-void update_connected_layer(connected_layer layer, double step)
-{
- int i,j;
- for(i = 0; i < layer.outputs; ++i){
- layer.biases[i] += step*layer.bias_updates[i];
- for(j = 0; j < layer.inputs; ++j){
- int index = i*layer.outputs+j;
- layer.weights[index] = layer.weight_updates[index];
- }
- }
- memset(layer.bias_updates, 0, layer.outputs*sizeof(double));
- memset(layer.weight_updates, 0, layer.outputs*layer.inputs*sizeof(double));
+ m = layer.batch;
+ k = layer.outputs;
+ n = layer.inputs;
+
+ a = layer.delta;
+ b = layer.weights;
+ c = delta;
+
+ if(c) gemm(0,1,m,n,k,1,a,k,b,k,0,c,n);
}
--
Gitblit v1.10.0