From cc06817efa24f20811ef6b32143c6700a91c5f2a Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Fri, 11 Apr 2014 08:00:27 +0000
Subject: [PATCH] Attempt at visualizing ImageNet Features
---
src/network.c | 171 +++++++++++++++++++++++++++++++++++++++++++++++++++++----
1 files changed, 159 insertions(+), 12 deletions(-)
diff --git a/src/network.c b/src/network.c
index 29e22e4..edae3c7 100644
--- a/src/network.c
+++ b/src/network.c
@@ -10,10 +10,11 @@
#include "maxpool_layer.h"
#include "softmax_layer.h"
-network make_network(int n)
+network make_network(int n, int batch)
{
network net;
net.n = n;
+ net.batch = batch;
net.layers = calloc(net.n, sizeof(void *));
net.types = calloc(net.n, sizeof(LAYER_TYPE));
net.outputs = 0;
@@ -21,6 +22,78 @@
return net;
}
+void print_convolutional_cfg(FILE *fp, convolutional_layer *l, int first)
+{
+ int i;
+ fprintf(fp, "[convolutional]\n");
+ if(first) fprintf(fp, "batch=%d\n"
+ "height=%d\n"
+ "width=%d\n"
+ "channels=%d\n",
+ l->batch,l->h, l->w, l->c);
+ fprintf(fp, "filters=%d\n"
+ "size=%d\n"
+ "stride=%d\n"
+ "activation=%s\n",
+ l->n, l->size, l->stride,
+ get_activation_string(l->activation));
+ fprintf(fp, "data=");
+ for(i = 0; i < l->n; ++i) fprintf(fp, "%g,", l->biases[i]);
+ for(i = 0; i < l->n*l->c*l->size*l->size; ++i) fprintf(fp, "%g,", l->filters[i]);
+ fprintf(fp, "\n\n");
+}
+void print_connected_cfg(FILE *fp, connected_layer *l, int first)
+{
+ int i;
+ fprintf(fp, "[connected]\n");
+ if(first) fprintf(fp, "batch=%d\ninput=%d\n", l->batch, l->inputs);
+ fprintf(fp, "output=%d\n"
+ "activation=%s\n",
+ l->outputs,
+ get_activation_string(l->activation));
+ fprintf(fp, "data=");
+ for(i = 0; i < l->outputs; ++i) fprintf(fp, "%g,", l->biases[i]);
+ for(i = 0; i < l->inputs*l->outputs; ++i) fprintf(fp, "%g,", l->weights[i]);
+ fprintf(fp, "\n\n");
+}
+
+void print_maxpool_cfg(FILE *fp, maxpool_layer *l, int first)
+{
+ fprintf(fp, "[maxpool]\n");
+ if(first) fprintf(fp, "batch=%d\n"
+ "height=%d\n"
+ "width=%d\n"
+ "channels=%d\n",
+ l->batch,l->h, l->w, l->c);
+ fprintf(fp, "stride=%d\n\n", l->stride);
+}
+
+void print_softmax_cfg(FILE *fp, softmax_layer *l, int first)
+{
+ fprintf(fp, "[softmax]\n");
+ if(first) fprintf(fp, "batch=%d\ninput=%d\n", l->batch, l->inputs);
+ fprintf(fp, "\n");
+}
+
+void save_network(network net, char *filename)
+{
+ FILE *fp = fopen(filename, "w");
+ if(!fp) file_error(filename);
+ int i;
+ for(i = 0; i < net.n; ++i)
+ {
+ if(net.types[i] == CONVOLUTIONAL)
+ print_convolutional_cfg(fp, (convolutional_layer *)net.layers[i], i==0);
+ else if(net.types[i] == CONNECTED)
+ print_connected_cfg(fp, (connected_layer *)net.layers[i], i==0);
+ else if(net.types[i] == MAXPOOL)
+ print_maxpool_cfg(fp, (maxpool_layer *)net.layers[i], i==0);
+ else if(net.types[i] == SOFTMAX)
+ print_softmax_cfg(fp, (softmax_layer *)net.layers[i], i==0);
+ }
+ fclose(fp);
+}
+
void forward_network(network net, float *input)
{
int i;
@@ -64,7 +137,7 @@
}
else if(net.types[i] == CONNECTED){
connected_layer layer = *(connected_layer *)net.layers[i];
- update_connected_layer(layer, step, momentum, 0);
+ update_connected_layer(layer, step, momentum, decay);
}
}
}
@@ -121,9 +194,11 @@
float *out = get_network_output(net);
int i, k = get_network_output_size(net);
for(i = 0; i < k; ++i){
+ //printf("%f, ", out[i]);
delta[i] = truth[i] - out[i];
sum += delta[i]*delta[i];
}
+ //printf("\n");
return sum;
}
@@ -173,26 +248,39 @@
float train_network_datum(network net, float *x, float *y, float step, float momentum, float decay)
{
- forward_network(net, x);
- int class = get_predicted_class_network(net);
- float error = backward_network(net, x, y);
- update_network(net, step, momentum, decay);
- //return (y[class]?1:0);
- return error;
+ forward_network(net, x);
+ //int class = get_predicted_class_network(net);
+ float error = backward_network(net, x, y);
+ update_network(net, step, momentum, decay);
+ //return (y[class]?1:0);
+ return error;
}
float train_network_sgd(network net, data d, int n, float step, float momentum,float decay)
{
int i;
float error = 0;
+ int correct = 0;
+ int pos = 0;
for(i = 0; i < n; ++i){
int index = rand()%d.X.rows;
- error += train_network_datum(net, d.X.vals[index], d.y.vals[index], step, momentum, decay);
+ float err = train_network_datum(net, d.X.vals[index], d.y.vals[index], step, momentum, decay);
+ float *y = d.y.vals[index];
+ int class = get_predicted_class_network(net);
+ correct += (y[class]?1:0);
+ if(y[1]){
+ error += err;
+ ++pos;
+ }
+
+
+ //printf("%d %f %f\n", i,net.output[0], d.y.vals[index][0]);
//if((i+1)%10 == 0){
// printf("%d: %f\n", (i+1), (float)correct/(i+1));
//}
}
- return error/n;
+ //printf("Accuracy: %f\n",(float) correct/n);
+ return error/pos;
}
float train_network_batch(network net, data d, int n, float step, float momentum,float decay)
{
@@ -226,7 +314,7 @@
}
visualize_network(net);
cvWaitKey(100);
- printf("Accuracy: %f\n", (float)correct/d.X.rows);
+ fprintf(stderr, "Accuracy: %f\n", (float)correct/d.X.rows);
}
int get_network_output_size_layer(network net, int i)
@@ -252,6 +340,63 @@
return 0;
}
+/*
+int resize_network(network net, int h, int w, int c)
+{
+ int i;
+ for (i = 0; i < net.n; ++i){
+ if(net.types[i] == CONVOLUTIONAL){
+ convolutional_layer *layer = (convolutional_layer *)net.layers[i];
+ layer->h = h;
+ layer->w = w;
+ layer->c = c;
+ image output = get_convolutional_image(*layer);
+ h = output.h;
+ w = output.w;
+ c = output.c;
+ }
+ else if(net.types[i] == MAXPOOL){
+ maxpool_layer *layer = (maxpool_layer *)net.layers[i];
+ layer->h = h;
+ layer->w = w;
+ layer->c = c;
+ image output = get_maxpool_image(*layer);
+ h = output.h;
+ w = output.w;
+ c = output.c;
+ }
+ }
+ return 0;
+}
+*/
+
+int resize_network(network net, int h, int w, int c)
+{
+ int i;
+ for (i = 0; i < net.n; ++i){
+ if(net.types[i] == CONVOLUTIONAL){
+ convolutional_layer *layer = (convolutional_layer *)net.layers[i];
+ resize_convolutional_layer(layer, h, w, c);
+ image output = get_convolutional_image(*layer);
+ h = output.h;
+ w = output.w;
+ c = output.c;
+ }
+ else if(net.types[i] == MAXPOOL){
+ maxpool_layer *layer = (maxpool_layer *)net.layers[i];
+ resize_maxpool_layer(layer, h, w, c);
+ image output = get_maxpool_image(*layer);
+ h = output.h;
+ w = output.w;
+ c = output.c;
+ }
+ else{
+ error("Cannot resize this type of layer");
+ }
+ }
+ return 0;
+}
+
int get_network_output_size(network net)
{
int i = net.n-1;
@@ -283,13 +428,14 @@
void visualize_network(network net)
{
+ image *prev = 0;
int i;
char buff[256];
for(i = 0; i < net.n; ++i){
sprintf(buff, "Layer %d", i);
if(net.types[i] == CONVOLUTIONAL){
convolutional_layer layer = *(convolutional_layer *)net.layers[i];
- visualize_convolutional_layer(layer, buff);
+ prev = visualize_convolutional_layer(layer, buff, prev);
}
}
}
@@ -361,3 +507,4 @@
return acc;
}
+
--
Gitblit v1.10.0