From cd8a3dcb4ca42f22ad8f46a95e00977c92be6bbd Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Thu, 08 Feb 2018 23:22:42 +0000
Subject: [PATCH] Compile fixes
---
src/network.c | 169 ++++++++++++++++----------------------------------------
1 files changed, 49 insertions(+), 120 deletions(-)
diff --git a/src/network.c b/src/network.c
index c9a198f..0c1b9af 100644
--- a/src/network.c
+++ b/src/network.c
@@ -1,5 +1,6 @@
#include <stdio.h>
#include <time.h>
+#include <assert.h>
#include "network.h"
#include "image.h"
#include "data.h"
@@ -14,7 +15,6 @@
#include "local_layer.h"
#include "convolutional_layer.h"
#include "activation_layer.h"
-#include "deconvolutional_layer.h"
#include "detection_layer.h"
#include "region_layer.h"
#include "normalization_layer.h"
@@ -41,7 +41,7 @@
net.momentum = 0;
net.decay = 0;
#ifdef GPU
- if(gpu_index >= 0) update_network_gpu(net);
+ //if(net.gpu_index >= 0) update_network_gpu(net);
#endif
}
@@ -50,6 +50,7 @@
int batch_num = get_current_batch(net);
int i;
float rate;
+ if (batch_num < net.burn_in) return net.learning_rate * pow((float)batch_num / net.burn_in, net.power);
switch (net.policy) {
case CONSTANT:
return net.learning_rate;
@@ -60,14 +61,15 @@
for(i = 0; i < net.num_steps; ++i){
if(net.steps[i] > batch_num) return rate;
rate *= net.scales[i];
- if(net.steps[i] > batch_num - 1) reset_momentum(net);
+ //if(net.steps[i] > batch_num - 1 && net.scales[i] > 1) reset_momentum(net);
}
return rate;
case EXP:
return net.learning_rate * pow(net.gamma, batch_num);
case POLY:
- if (batch_num < net.burn_in) return net.learning_rate * pow((float)batch_num / net.burn_in, net.power);
- return net.learning_rate * pow(1 - (float)batch_num / net.max_batches, net.power);
+ return net.learning_rate * pow(1 - (float)batch_num / net.max_batches, net.power);
+ //if (batch_num < net.burn_in) return net.learning_rate * pow((float)batch_num / net.burn_in, net.power);
+ //return net.learning_rate * pow(1 - (float)batch_num / net.max_batches, net.power);
case RANDOM:
return net.learning_rate * pow(rand_uniform(0,1), net.power);
case SIG:
@@ -152,49 +154,7 @@
if(l.delta){
scal_cpu(l.outputs * l.batch, 0, l.delta, 1);
}
- if(l.type == CONVOLUTIONAL){
- forward_convolutional_layer(l, state);
- } else if(l.type == DECONVOLUTIONAL){
- forward_deconvolutional_layer(l, state);
- } else if(l.type == ACTIVE){
- forward_activation_layer(l, state);
- } else if(l.type == LOCAL){
- forward_local_layer(l, state);
- } else if(l.type == NORMALIZATION){
- forward_normalization_layer(l, state);
- } else if(l.type == BATCHNORM){
- forward_batchnorm_layer(l, state);
- } else if(l.type == DETECTION){
- forward_detection_layer(l, state);
- } else if(l.type == REGION){
- forward_region_layer(l, state);
- } else if(l.type == CONNECTED){
- forward_connected_layer(l, state);
- } else if(l.type == RNN){
- forward_rnn_layer(l, state);
- } else if(l.type == GRU){
- forward_gru_layer(l, state);
- } else if(l.type == CRNN){
- forward_crnn_layer(l, state);
- } else if(l.type == CROP){
- forward_crop_layer(l, state);
- } else if(l.type == COST){
- forward_cost_layer(l, state);
- } else if(l.type == SOFTMAX){
- forward_softmax_layer(l, state);
- } else if(l.type == MAXPOOL){
- forward_maxpool_layer(l, state);
- } else if(l.type == REORG){
- forward_reorg_layer(l, state);
- } else if(l.type == AVGPOOL){
- forward_avgpool_layer(l, state);
- } else if(l.type == DROPOUT){
- forward_dropout_layer(l, state);
- } else if(l.type == ROUTE){
- forward_route_layer(l, net);
- } else if(l.type == SHORTCUT){
- forward_shortcut_layer(l, state);
- }
+ l.forward(l, state);
state.input = l.output;
}
}
@@ -206,29 +166,17 @@
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, rate, net.momentum, net.decay);
- } else if(l.type == DECONVOLUTIONAL){
- update_deconvolutional_layer(l, rate, net.momentum, net.decay);
- } else if(l.type == CONNECTED){
- update_connected_layer(l, update_batch, rate, net.momentum, net.decay);
- } else if(l.type == RNN){
- update_rnn_layer(l, update_batch, rate, net.momentum, net.decay);
- } else if(l.type == GRU){
- update_gru_layer(l, update_batch, rate, net.momentum, net.decay);
- } else if(l.type == CRNN){
- update_crnn_layer(l, update_batch, rate, net.momentum, net.decay);
- } else if(l.type == LOCAL){
- update_local_layer(l, update_batch, rate, net.momentum, net.decay);
+ if(l.update){
+ l.update(l, update_batch, rate, net.momentum, net.decay);
}
}
}
float *get_network_output(network net)
{
- #ifdef GPU
- if (gpu_index >= 0) return get_network_output_gpu(net);
- #endif
+#ifdef GPU
+ if (gpu_index >= 0) return get_network_output_gpu(net);
+#endif
int i;
for(i = net.n-1; i > 0; --i) if(net.layers[i].type != COST) break;
return net.layers[i].output;
@@ -272,57 +220,18 @@
state.delta = prev.delta;
}
layer l = net.layers[i];
- if(l.type == CONVOLUTIONAL){
- backward_convolutional_layer(l, state);
- } else if(l.type == DECONVOLUTIONAL){
- backward_deconvolutional_layer(l, state);
- } else if(l.type == ACTIVE){
- backward_activation_layer(l, state);
- } else if(l.type == NORMALIZATION){
- backward_normalization_layer(l, state);
- } else if(l.type == BATCHNORM){
- backward_batchnorm_layer(l, state);
- } else if(l.type == MAXPOOL){
- if(i != 0) backward_maxpool_layer(l, state);
- } else if(l.type == REORG){
- backward_reorg_layer(l, state);
- } else if(l.type == AVGPOOL){
- backward_avgpool_layer(l, state);
- } else if(l.type == DROPOUT){
- backward_dropout_layer(l, state);
- } else if(l.type == DETECTION){
- backward_detection_layer(l, state);
- } else if(l.type == REGION){
- backward_region_layer(l, state);
- } else if(l.type == SOFTMAX){
- if(i != 0) backward_softmax_layer(l, state);
- } else if(l.type == CONNECTED){
- backward_connected_layer(l, state);
- } else if(l.type == RNN){
- backward_rnn_layer(l, state);
- } else if(l.type == GRU){
- backward_gru_layer(l, state);
- } else if(l.type == CRNN){
- backward_crnn_layer(l, state);
- } else if(l.type == LOCAL){
- backward_local_layer(l, state);
- } else if(l.type == COST){
- backward_cost_layer(l, state);
- } else if(l.type == ROUTE){
- backward_route_layer(l, net);
- } else if(l.type == SHORTCUT){
- backward_shortcut_layer(l, state);
- }
+ if (l.stopbackward) break;
+ l.backward(l, state);
}
}
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
network_state state;
+ *net.seen += net.batch;
state.index = 0;
state.net = net;
state.input = x;
@@ -356,6 +265,7 @@
float train_network(network net, data d)
{
+ assert(d.X.rows % net.batch == 0);
int batch = net.batch;
int n = d.X.rows / batch;
float *X = calloc(batch*d.X.cols, sizeof(float));
@@ -404,16 +314,22 @@
int i;
for(i = 0; i < net->n; ++i){
net->layers[i].batch = b;
- #ifdef CUDNN
+#ifdef CUDNN
if(net->layers[i].type == CONVOLUTIONAL){
cudnn_convolutional_setup(net->layers + i);
}
- #endif
+#endif
}
}
int resize_network(network *net, int w, int h)
{
+#ifdef GPU
+ cuda_set_device(net->gpu_index);
+ if(gpu_index >= 0){
+ cuda_free(net->workspace);
+ }
+#endif
int i;
//if(w == net->w && h == net->h) return 0;
net->w = w;
@@ -430,6 +346,10 @@
resize_crop_layer(&l, w, h);
}else if(l.type == MAXPOOL){
resize_maxpool_layer(&l, w, h);
+ }else if(l.type == REGION){
+ resize_region_layer(&l, w, h);
+ }else if(l.type == ROUTE){
+ resize_route_layer(&l, net);
}else if(l.type == REORG){
resize_reorg_layer(&l, w, h);
}else if(l.type == AVGPOOL){
@@ -439,6 +359,7 @@
}else if(l.type == COST){
resize_cost_layer(&l, inputs);
}else{
+ fprintf(stderr, "Resizing type %d \n", (int)l.type);
error("Cannot resize this type of layer");
}
if(l.workspace_size > workspace_size) workspace_size = l.workspace_size;
@@ -450,7 +371,12 @@
}
#ifdef GPU
if(gpu_index >= 0){
- cuda_free(net->workspace);
+ if(net->input_gpu) {
+ cuda_free(*net->input_gpu);
+ *net->input_gpu = 0;
+ cuda_free(*net->truth_gpu);
+ *net->truth_gpu = 0;
+ }
net->workspace = cuda_make_array(0, (workspace_size-1)/sizeof(float)+1);
}else {
free(net->workspace);
@@ -658,7 +584,6 @@
return acc;
}
-
float network_accuracy_multi(network net, data d, int n)
{
matrix guess = network_predict_data_multi(net, d, n);
@@ -669,15 +594,19 @@
void free_network(network net)
{
- int i;
- for(i = 0; i < net.n; ++i){
- free_layer(net.layers[i]);
- }
- free(net.layers);
+ 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);
+ if (gpu_index >= 0) cuda_free(net.workspace);
+ else free(net.workspace);
+ 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);
+#else
+ free(net.workspace);
#endif
}
--
Gitblit v1.10.0