From cb1f33c6ae840e8dc0f43518daf76e6ed01034f0 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Mon, 08 Dec 2014 19:48:57 +0000
Subject: [PATCH] Fixed race condition in server
---
src/connected_layer.c | 197 +++++++++++++++++++++++++++++++++++-------------
1 files changed, 142 insertions(+), 55 deletions(-)
diff --git a/src/connected_layer.c b/src/connected_layer.c
index d769e1f..85bf5c8 100644
--- a/src/connected_layer.c
+++ b/src/connected_layer.c
@@ -1,90 +1,177 @@
#include "connected_layer.h"
#include "utils.h"
+#include "mini_blas.h"
#include <math.h>
#include <stdio.h>
#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, float learning_rate, float momentum, float decay)
{
- fprintf(stderr, "Connected Layer: %d inputs, %d outputs\n", inputs, outputs);
int i;
connected_layer *layer = calloc(1, sizeof(connected_layer));
+
+ layer->learning_rate = learning_rate;
+ layer->momentum = momentum;
+ layer->decay = decay;
+
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;
- for(i = 0; i < inputs*outputs; ++i)
- layer->weights[i] = rand_normal()*scale;
+ layer->weight_updates = calloc(inputs*outputs, sizeof(float));
+ layer->weights = calloc(inputs*outputs, sizeof(float));
+ float scale = 1./inputs;
+ scale = .01;
+ for(i = 0; i < inputs*outputs; ++i){
+ layer->weights[i] = scale*rand_normal();
+ }
- layer->bias_updates = calloc(outputs, sizeof(double));
- layer->bias_momentum = calloc(outputs, sizeof(double));
- layer->biases = calloc(outputs, sizeof(double));
- for(i = 0; i < outputs; ++i)
- //layer->biases[i] = rand_normal()*scale + scale;
- layer->biases[i] = 0;
+ layer->bias_updates = calloc(outputs, sizeof(float));
+ layer->biases = calloc(outputs, sizeof(float));
+ for(i = 0; i < outputs; ++i){
+ layer->biases[i] = .01;
+ }
+#ifdef GPU
+ layer->weights_cl = cl_make_array(layer->weights, inputs*outputs);
+ layer->biases_cl = cl_make_array(layer->biases, outputs);
+
+ layer->weight_updates_cl = cl_make_array(layer->weight_updates, inputs*outputs);
+ layer->bias_updates_cl = cl_make_array(layer->bias_updates, outputs);
+
+ layer->output_cl = cl_make_array(layer->output, outputs*batch);
+ layer->delta_cl = cl_make_array(layer->delta, outputs*batch);
+#endif
layer->activation = activation;
+ fprintf(stderr, "Connected Layer: %d inputs, %d outputs\n", inputs, outputs);
return layer;
}
-void forward_connected_layer(connected_layer layer, double *input)
+void update_connected_layer(connected_layer layer)
{
- 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);
- }
+ axpy_cpu(layer.outputs, layer.learning_rate, layer.bias_updates, 1, layer.biases, 1);
+ scal_cpu(layer.outputs, layer.momentum, layer.bias_updates, 1);
+
+ axpy_cpu(layer.inputs*layer.outputs, -layer.decay, layer.weights, 1, layer.weight_updates, 1);
+ axpy_cpu(layer.inputs*layer.outputs, layer.learning_rate, layer.weight_updates, 1, layer.weights, 1);
+ scal_cpu(layer.inputs*layer.outputs, layer.momentum, layer.weight_updates, 1);
}
-void learn_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){
- 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];
- }
+ int i;
+ for(i = 0; i < layer.batch; ++i){
+ copy_cpu(layer.outputs, layer.biases, 1, layer.output + i*layer.outputs, 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);
+ activate_array(layer.output, layer.outputs*layer.batch, layer.activation);
}
-void update_connected_layer(connected_layer layer, double step, double momentum, double decay)
+void backward_connected_layer(connected_layer layer, float *input, float *delta)
{
- int i,j;
- for(i = 0; i < layer.outputs; ++i){
- layer.bias_momentum[i] = step*(layer.bias_updates[i]) + momentum*layer.bias_momentum[i];
- layer.biases[i] += layer.bias_momentum[i];
- for(j = 0; j < layer.inputs; ++j){
- int index = i*layer.inputs+j;
- layer.weight_momentum[index] = step*(layer.weight_updates[index] - decay*layer.weights[index]) + momentum*layer.weight_momentum[index];
- layer.weights[index] += layer.weight_momentum[index];
- //layer.weights[index] = constrain(layer.weights[index], 100.);
- }
+ int i;
+ gradient_array(layer.output, layer.outputs*layer.batch, layer.activation, layer.delta);
+ for(i = 0; i < layer.batch; ++i){
+ axpy_cpu(layer.outputs, 1, layer.delta + i*layer.outputs, 1, layer.bias_updates, 1);
}
- memset(layer.bias_updates, 0, layer.outputs*sizeof(double));
- memset(layer.weight_updates, 0, layer.outputs*layer.inputs*sizeof(double));
+ 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);
+
+ 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);
}
-void backward_connected_layer(connected_layer layer, double *input, double *delta)
-{
- int i, j;
+#ifdef GPU
- 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];
- }
- }
+void pull_connected_layer(connected_layer layer)
+{
+ cl_read_array(layer.weights_cl, layer.weights, layer.inputs*layer.outputs);
+ cl_read_array(layer.biases_cl, layer.biases, layer.outputs);
+ cl_read_array(layer.weight_updates_cl, layer.weight_updates, layer.inputs*layer.outputs);
+ cl_read_array(layer.bias_updates_cl, layer.bias_updates, layer.outputs);
}
+void push_connected_layer(connected_layer layer)
+{
+ cl_write_array(layer.weights_cl, layer.weights, layer.inputs*layer.outputs);
+ cl_write_array(layer.biases_cl, layer.biases, layer.outputs);
+ cl_write_array(layer.weight_updates_cl, layer.weight_updates, layer.inputs*layer.outputs);
+ cl_write_array(layer.bias_updates_cl, layer.bias_updates, layer.outputs);
+}
+
+void update_connected_layer_gpu(connected_layer layer)
+{
+ axpy_ongpu(layer.outputs, layer.learning_rate, layer.bias_updates_cl, 1, layer.biases_cl, 1);
+ scal_ongpu(layer.outputs, layer.momentum, layer.bias_updates_cl, 1);
+
+ axpy_ongpu(layer.inputs*layer.outputs, -layer.decay, layer.weights_cl, 1, layer.weight_updates_cl, 1);
+ axpy_ongpu(layer.inputs*layer.outputs, layer.learning_rate, layer.weight_updates_cl, 1, layer.weights_cl, 1);
+ scal_ongpu(layer.inputs*layer.outputs, layer.momentum, layer.weight_updates_cl, 1);
+ pull_connected_layer(layer);
+}
+
+void forward_connected_layer_gpu(connected_layer layer, cl_mem input)
+{
+ int i;
+ for(i = 0; i < layer.batch; ++i){
+ copy_ongpu_offset(layer.outputs, layer.biases_cl, 0, 1, layer.output_cl, i*layer.outputs, 1);
+ }
+ int m = layer.batch;
+ int k = layer.inputs;
+ int n = layer.outputs;
+ cl_mem a = input;
+ cl_mem b = layer.weights_cl;
+ cl_mem c = layer.output_cl;
+ gemm_ongpu(0,0,m,n,k,1,a,k,b,n,1,c,n);
+ activate_array_ongpu(layer.output_cl, layer.outputs*layer.batch, layer.activation);
+}
+
+void backward_connected_layer_gpu(connected_layer layer, cl_mem input, cl_mem delta)
+{
+ int i;
+ gradient_array_ongpu(layer.output_cl, layer.outputs*layer.batch, layer.activation, layer.delta_cl);
+ for(i = 0; i < layer.batch; ++i){
+ axpy_ongpu_offset(layer.outputs, 1, layer.delta_cl, i*layer.outputs, 1, layer.bias_updates_cl, 0, 1);
+ }
+ int m = layer.inputs;
+ int k = layer.batch;
+ int n = layer.outputs;
+ cl_mem a = input;
+ cl_mem b = layer.delta_cl;
+ cl_mem c = layer.weight_updates_cl;
+ gemm_ongpu(1,0,m,n,k,1,a,m,b,n,1,c,n);
+
+ m = layer.batch;
+ k = layer.outputs;
+ n = layer.inputs;
+
+ a = layer.delta_cl;
+ b = layer.weights_cl;
+ c = delta;
+
+ if(c) gemm_ongpu(0,1,m,n,k,1,a,k,b,k,0,c,n);
+}
+#endif
--
Gitblit v1.10.0