From f996bd59a61338d8d51e2b19482d684f6dd04d0f Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Wed, 23 Sep 2015 21:16:48 +0000
Subject: [PATCH] more writing fixes
---
src/network.c | 67 ++++++++++++++++++++++++++++++---
1 files changed, 60 insertions(+), 7 deletions(-)
diff --git a/src/network.c b/src/network.c
index de3e569..7f19318 100644
--- a/src/network.c
+++ b/src/network.c
@@ -20,6 +20,41 @@
#include "dropout_layer.h"
#include "route_layer.h"
+int get_current_batch(network net)
+{
+ int batch_num = (*net.seen)/(net.batch*net.subdivisions);
+ return batch_num;
+}
+
+float get_current_rate(network net)
+{
+ int batch_num = get_current_batch(net);
+ int i;
+ float rate;
+ switch (net.policy) {
+ case CONSTANT:
+ return net.learning_rate;
+ case STEP:
+ return net.learning_rate * pow(net.scale, batch_num/net.step);
+ case STEPS:
+ rate = net.learning_rate;
+ for(i = 0; i < net.num_steps; ++i){
+ if(net.steps[i] > batch_num) return rate;
+ rate *= net.scales[i];
+ }
+ return rate;
+ case EXP:
+ return net.learning_rate * pow(net.gamma, batch_num);
+ case POLY:
+ return net.learning_rate * pow(1 - (float)batch_num / net.max_batches, net.power);
+ case SIG:
+ return net.learning_rate * (1./(1.+exp(net.gamma*(batch_num - net.step))));
+ default:
+ fprintf(stderr, "Policy is weird!\n");
+ return net.learning_rate;
+ }
+}
+
char *get_layer_string(LAYER_TYPE a)
{
switch(a){
@@ -60,6 +95,7 @@
network net = {0};
net.n = n;
net.layers = calloc(net.n, sizeof(layer));
+ net.seen = calloc(1, sizeof(int));
#ifdef GPU
net.input_gpu = calloc(1, sizeof(float *));
net.truth_gpu = calloc(1, sizeof(float *));
@@ -110,14 +146,15 @@
{
int i;
int update_batch = net.batch*net.subdivisions;
+ float rate = get_current_rate(net);
for(i = 0; i < net.n; ++i){
layer l = net.layers[i];
if(l.type == CONVOLUTIONAL){
- update_convolutional_layer(l, update_batch, net.learning_rate, net.momentum, net.decay);
+ update_convolutional_layer(l, update_batch, rate, net.momentum, net.decay);
} else if(l.type == DECONVOLUTIONAL){
- update_deconvolutional_layer(l, net.learning_rate, net.momentum, net.decay);
+ update_deconvolutional_layer(l, rate, net.momentum, net.decay);
} else if(l.type == CONNECTED){
- update_connected_layer(l, update_batch, net.learning_rate, net.momentum, net.decay);
+ update_connected_layer(l, update_batch, rate, net.momentum, net.decay);
}
}
}
@@ -203,6 +240,7 @@
float train_network_datum(network net, float *x, float *y)
{
+ *net.seen += net.batch;
#ifdef GPU
if(gpu_index >= 0) return train_network_datum_gpu(net, x, y);
#endif
@@ -214,7 +252,7 @@
forward_network(net, state);
backward_network(net, state);
float error = get_network_cost(net);
- if((net.seen/net.batch)%net.subdivisions == 0) update_network(net);
+ if(((*net.seen)/net.batch)%net.subdivisions == 0) update_network(net);
return error;
}
@@ -227,7 +265,6 @@
int i;
float sum = 0;
for(i = 0; i < n; ++i){
- net.seen += batch;
get_random_batch(d, batch, X, y);
float err = train_network_datum(net, X, y);
sum += err;
@@ -248,7 +285,6 @@
float sum = 0;
for(i = 0; i < n; ++i){
get_next_batch(d, batch, i*batch, X, y);
- net.seen += batch;
float err = train_network_datum(net, X, y);
sum += err;
}
@@ -294,6 +330,7 @@
//if(w == net->w && h == net->h) return 0;
net->w = w;
net->h = h;
+ int inputs = 0;
//fprintf(stderr, "Resizing to %d x %d...", w, h);
//fflush(stderr);
for (i = 0; i < net->n; ++i){
@@ -307,9 +344,12 @@
break;
}else if(l.type == NORMALIZATION){
resize_normalization_layer(&l, w, h);
+ }else if(l.type == COST){
+ resize_cost_layer(&l, inputs);
}else{
error("Cannot resize this type of layer");
}
+ inputs = l.outputs;
net->layers[i] = l;
w = l.out_w;
h = l.out_h;
@@ -519,4 +559,17 @@
return acc;
}
-
+void free_network(network net)
+{
+ int i;
+ for(i = 0; i < net.n; ++i){
+ free_layer(net.layers[i]);
+ }
+ free(net.layers);
+ #ifdef GPU
+ if(*net.input_gpu) cuda_free(*net.input_gpu);
+ if(*net.truth_gpu) cuda_free(*net.truth_gpu);
+ if(net.input_gpu) free(net.input_gpu);
+ if(net.truth_gpu) free(net.truth_gpu);
+ #endif
+}
--
Gitblit v1.10.0