From d6fbe86e7a8c1bc389902c90c57ee7e80f5475b9 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Tue, 16 Dec 2014 19:40:05 +0000
Subject: [PATCH] updates?
---
src/cnn.c | 534 +++++++++++++++++++++++++++++++++++++++++++----------------
1 files changed, 390 insertions(+), 144 deletions(-)
diff --git a/src/cnn.c b/src/cnn.c
index 8a4899c..8c56bda 100644
--- a/src/cnn.c
+++ b/src/cnn.c
@@ -8,6 +8,8 @@
#include "matrix.h"
#include "utils.h"
#include "mini_blas.h"
+#include "matrix.h"
+#include "server.h"
#include <time.h>
#include <stdlib.h>
@@ -36,6 +38,7 @@
void test_convolutional_layer()
{
+/*
int i;
image dog = load_image("data/dog.jpg",224,224);
network net = parse_network_cfg("cfg/convolutional.cfg");
@@ -72,6 +75,7 @@
float *gpu_del = calloc(del_size, sizeof(float));
memcpy(gpu_del, get_network_delta_layer(net, 0), del_size*sizeof(float));
+ */
/*
start = clock();
@@ -97,6 +101,7 @@
*/
}
+/*
void test_col2im()
{
float col[] = {1,2,1,2,
@@ -116,13 +121,12 @@
int ksize = 3;
int stride = 1;
int pad = 0;
- col2im_gpu(col, batch,
- channels, height, width,
- ksize, stride, pad, im);
+ //col2im_gpu(col, batch,
+ // channels, height, width,
+ // ksize, stride, pad, im);
int i;
for(i = 0; i < 16; ++i)printf("%f,", im[i]);
printf("\n");
- /*
float data_im[] = {
1,2,3,4,
5,6,7,8,
@@ -134,8 +138,8 @@
ksize, stride, pad, data_col) ;
for(i = 0; i < 18; ++i)printf("%f,", data_col[i]);
printf("\n");
- */
}
+*/
#endif
@@ -158,7 +162,7 @@
int i;
clock_t start = clock(), end;
for(i = 0; i < 1000; ++i){
- im2col_cpu(dog.data,1, dog.c, dog.h, dog.w, size, stride, 0, matrix);
+ //im2col_cpu(dog.data,1, dog.c, dog.h, dog.w, size, stride, 0, matrix);
gemm(0,0,n,mw,mh,1,filters,mh,matrix,mw,1,edge.data,mw);
}
end = clock();
@@ -175,6 +179,7 @@
void verify_convolutional_layer()
{
+/*
srand(0);
int i;
int n = 1;
@@ -225,6 +230,7 @@
printf("%f %f\n", avg_image_layer(mj1,0), avg_image_layer(mj2,0));
show_image(mj1, "forward jacobian");
show_image(mj2, "backward jacobian");
+ */
}
void test_load()
@@ -288,7 +294,7 @@
while(1){
i += 1;
time=clock();
- data train = load_data_random(imgs*net.batch, paths, m, labels, 2, 256, 256);
+ data train = load_data(paths, imgs*net.batch, m, labels, 2, 256, 256);
normalize_data_rows(train);
printf("Loaded: %lf seconds\n", sec(clock()-time));
time=clock();
@@ -305,6 +311,44 @@
}
}
+void draw_detection(image im, float *box, int side)
+{
+ int j;
+ int r, c;
+ float amount[5];
+ for(r = 0; r < side*side; ++r){
+ for(j = 0; j < 5; ++j){
+ if(box[r*5] > amount[j]) {
+ amount[j] = box[r*5];
+ break;
+ }
+ }
+ }
+ float smallest = amount[0];
+ for(j = 1; j < 5; ++j) if(amount[j] < smallest) smallest = amount[j];
+
+ for(r = 0; r < side; ++r){
+ for(c = 0; c < side; ++c){
+ j = (r*side + c) * 5;
+ printf("Prob: %f\n", box[j]);
+ if(box[j] >= smallest){
+ int d = im.w/side;
+ int y = r*d+box[j+1]*d;
+ int x = c*d+box[j+2]*d;
+ int h = box[j+3]*256;
+ int w = box[j+4]*256;
+ printf("%f %f %f %f\n", box[j+1], box[j+2], box[j+3], box[j+4]);
+ printf("%d %d %d %d\n", x, y, w, h);
+ printf("%d %d %d %d\n", x-w/2, y-h/2, x+w/2, y+h/2);
+ draw_box(im, x-w/2, y-h/2, x+w/2, y+h/2);
+ }
+ }
+ }
+ show_image(im, "box");
+ cvWaitKey(0);
+}
+
+
void train_detection_net()
{
float avg_loss = 1;
@@ -313,6 +357,7 @@
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
int imgs = 1000/net.batch+1;
srand(time(0));
+ //srand(23410);
int i = 0;
list *plist = get_paths("/home/pjreddie/data/imagenet/horse.txt");
char **paths = (char **)list_to_array(plist);
@@ -321,8 +366,12 @@
while(1){
i += 1;
time=clock();
- data train = load_data_detection_random(imgs*net.batch, paths, plist->size, 256, 256, 8, 8, 256);
- //translate_data_rows(train, -144);
+ data train = load_data_detection_jitter_random(imgs*net.batch, paths, plist->size, 256, 256, 7, 7, 256);
+ /*
+ image im = float_to_image(224, 224, 3, train.X.vals[0]);
+ draw_detection(im, train.y.vals[0], 7);
+ */
+
normalize_data_rows(train);
printf("Loaded: %lf seconds\n", sec(clock()-time));
time=clock();
@@ -331,36 +380,81 @@
avg_loss = avg_loss*.9 + loss*.1;
printf("%d: %f, %f avg, %lf seconds, %d images\n", i, loss, avg_loss, sec(clock()-time), i*imgs*net.batch);
#endif
- free_data(train);
if(i%10==0){
char buff[256];
- sprintf(buff, "/home/pjreddie/imagenet_backup/imagenet_%d.cfg", i);
+ sprintf(buff, "/home/pjreddie/imagenet_backup/detnet_%d.cfg", i);
save_network(net, buff);
}
+ free_data(train);
}
}
-
-void train_imagenet()
+void train_imagenet_distributed(char *address)
{
float avg_loss = 1;
- //network net = parse_network_cfg("/home/pjreddie/imagenet_backup/alexnet_1270.cfg");
- network net = parse_network_cfg("cfg/trained_alexnet.cfg");
- printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
- int imgs = 1000/net.batch+1;
srand(time(0));
+ network net = parse_network_cfg("cfg/net.cfg");
+ set_learning_network(&net, 0, 1, 0);
+ printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
+ int imgs = 1;
int i = 0;
char **labels = get_labels("/home/pjreddie/data/imagenet/cls.labels.list");
list *plist = get_paths("/data/imagenet/cls.train.list");
char **paths = (char **)list_to_array(plist);
printf("%d\n", plist->size);
clock_t time;
+ data train, buffer;
+ pthread_t load_thread = load_data_thread(paths, imgs*net.batch, plist->size, labels, 1000, 224, 224, &buffer);
+ while(1){
+ i += 1;
+
+ time=clock();
+ client_update(net, address);
+ printf("Updated: %lf seconds\n", sec(clock()-time));
+
+ time=clock();
+ pthread_join(load_thread, 0);
+ train = buffer;
+ normalize_data_rows(train);
+ load_thread = load_data_thread(paths, imgs*net.batch, plist->size, labels, 1000, 224, 224, &buffer);
+ printf("Loaded: %lf seconds\n", sec(clock()-time));
+ time=clock();
+
+#ifdef GPU
+ float loss = train_network_data_gpu(net, train, imgs);
+ avg_loss = avg_loss*.9 + loss*.1;
+ printf("%d: %f, %f avg, %lf seconds, %d images\n", i, loss, avg_loss, sec(clock()-time), i*imgs*net.batch);
+#endif
+ free_data(train);
+ }
+}
+
+void train_imagenet(char *cfgfile)
+{
+ float avg_loss = 1;
+ //network net = parse_network_cfg("/home/pjreddie/imagenet_backup/alexnet_1270.cfg");
+ srand(time(0));
+ network net = parse_network_cfg(cfgfile);
+ set_learning_network(&net, .000001, .9, .0005);
+ printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
+ int imgs = 1000/net.batch+1;
+ int i = 20590;
+ char **labels = get_labels("/home/pjreddie/data/imagenet/cls.labels.list");
+ list *plist = get_paths("/data/imagenet/cls.train.list");
+ char **paths = (char **)list_to_array(plist);
+ printf("%d\n", plist->size);
+ clock_t time;
+ pthread_t load_thread;
+ data train;
+ data buffer;
+ load_thread = load_data_thread(paths, imgs*net.batch, plist->size, labels, 1000, 256, 256, &buffer);
while(1){
i += 1;
time=clock();
- data train = load_data_random(imgs*net.batch, paths, plist->size, labels, 1000, 256, 256);
- //translate_data_rows(train, -144);
+ pthread_join(load_thread, 0);
+ train = buffer;
normalize_data_rows(train);
+ load_thread = load_data_thread(paths, imgs*net.batch, plist->size, labels, 1000, 256, 256, &buffer);
printf("Loaded: %lf seconds\n", sec(clock()-time));
time=clock();
#ifdef GPU
@@ -371,7 +465,7 @@
free_data(train);
if(i%10==0){
char buff[256];
- sprintf(buff, "/home/pjreddie/imagenet_backup/imagenet_%d.cfg", i);
+ sprintf(buff, "/home/pjreddie/imagenet_backup/net_%d.cfg", i);
save_network(net, buff);
}
}
@@ -379,7 +473,7 @@
void validate_imagenet(char *filename)
{
- int i;
+ int i = 0;
network net = parse_network_cfg(filename);
srand(time(0));
@@ -392,48 +486,89 @@
clock_t time;
float avg_acc = 0;
+ float avg_top5 = 0;
int splits = 50;
+ int num = (i+1)*m/splits - i*m/splits;
- for(i = 0; i < splits; ++i){
+ data val, buffer;
+ pthread_t load_thread = load_data_thread(paths, num, 0, labels, 1000, 256, 256, &buffer);
+ for(i = 1; i <= splits; ++i){
time=clock();
- char **part = paths+(i*m/splits);
- int num = (i+1)*m/splits - i*m/splits;
- data val = load_data(part, num, labels, 1000, 256, 256);
+
+ pthread_join(load_thread, 0);
+ val = buffer;
normalize_data_rows(val);
+
+ num = (i+1)*m/splits - i*m/splits;
+ char **part = paths+(i*m/splits);
+ if(i != splits) load_thread = load_data_thread(part, num, 0, labels, 1000, 256, 256, &buffer);
printf("Loaded: %d images in %lf seconds\n", val.X.rows, sec(clock()-time));
+
time=clock();
#ifdef GPU
- float acc = network_accuracy_gpu(net, val);
- avg_acc += acc;
- printf("%d: %f, %f avg, %lf seconds, %d images\n", i, acc, avg_acc/(i+1), sec(clock()-time), val.X.rows);
+ float *acc = network_accuracies_gpu(net, val);
+ avg_acc += acc[0];
+ avg_top5 += acc[1];
+ printf("%d: top1: %f, top5: %f, %lf seconds, %d images\n", i, avg_acc/i, avg_top5/i, sec(clock()-time), val.X.rows);
#endif
free_data(val);
}
}
-void test_detection()
+void test_detection(char *cfgfile)
{
- network net = parse_network_cfg("cfg/detnet_test.cfg");
- //imgs=1;
+ network net = parse_network_cfg(cfgfile);
+ set_batch_network(&net, 1);
srand(2222222);
- int i = 0;
clock_t time;
char filename[256];
- int indexes[10];
while(1){
fgets(filename, 256, stdin);
- image im = load_image_color(filename, 256, 256);
+ strtok(filename, "\n");
+ image im = load_image_color(filename, 224, 224);
z_normalize_image(im);
printf("%d %d %d\n", im.h, im.w, im.c);
float *X = im.data;
time=clock();
float *predictions = network_predict(net, X);
- top_predictions(net, 10, indexes);
printf("%s: Predicted in %f seconds.\n", filename, sec(clock()-time));
+ draw_detection(im, predictions, 7);
free_image(im);
}
}
+void test_init(char *cfgfile)
+{
+ network net = parse_network_cfg(cfgfile);
+ set_batch_network(&net, 1);
+ srand(2222222);
+ int i = 0;
+ char *filename = "data/test.jpg";
+
+ image im = load_image_color(filename, 224, 224);
+ z_normalize_image(im);
+ float *X = im.data;
+ forward_network(net, X, 0, 1);
+ for(i = 0; i < net.n; ++i){
+ if(net.types[i] == CONVOLUTIONAL){
+ convolutional_layer layer = *(convolutional_layer *)net.layers[i];
+ image output = get_convolutional_image(layer);
+ int size = output.h*output.w*output.c;
+ float v = variance_array(layer.output, size);
+ float m = mean_array(layer.output, size);
+ printf("%d: Convolutional, mean: %f, variance %f\n", i, m, v);
+ }
+ else if(net.types[i] == CONNECTED){
+ connected_layer layer = *(connected_layer *)net.layers[i];
+ int size = layer.outputs;
+ float v = variance_array(layer.output, size);
+ float m = mean_array(layer.output, size);
+ printf("%d: Connected, mean: %f, variance %f\n", i, m, v);
+ }
+ }
+ free_image(im);
+}
+
void test_imagenet()
{
network net = parse_network_cfg("cfg/imagenet_test.cfg");
@@ -446,6 +581,7 @@
int indexes[10];
while(1){
fgets(filename, 256, stdin);
+ strtok(filename, "\n");
image im = load_image_color(filename, 256, 256);
z_normalize_image(im);
printf("%d %d %d\n", im.h, im.w, im.c);
@@ -484,14 +620,14 @@
void train_cifar10()
{
srand(555555);
- network net = parse_network_cfg("cfg/cifar10.cfg");
+ network net = parse_network_cfg("cfg/cifar_ramp.part");
data test = load_cifar10_data("data/cifar10/test_batch.bin");
int count = 0;
int iters = 10000/net.batch;
data train = load_all_cifar10();
while(++count <= 10000){
clock_t start = clock(), end;
- float loss = train_network_sgd(net, train, iters);
+ float loss = train_network_sgd_gpu(net, train, iters);
end = clock();
//visualize_network(net);
//cvWaitKey(5000);
@@ -499,10 +635,10 @@
//float test_acc = network_accuracy(net, test);
//printf("%d: Loss: %f, Test Acc: %f, Time: %lf seconds, LR: %f, Momentum: %f, Decay: %f\n", count, loss, test_acc,(float)(end-start)/CLOCKS_PER_SEC, net.learning_rate, net.momentum, net.decay);
if(count%10 == 0){
- float test_acc = network_accuracy(net, test);
+ float test_acc = network_accuracy_gpu(net, test);
printf("%d: Loss: %f, Test Acc: %f, Time: %lf seconds, LR: %f, Momentum: %f, Decay: %f\n", count, loss, test_acc,(float)(end-start)/CLOCKS_PER_SEC, net.learning_rate, net.momentum, net.decay);
char buff[256];
- sprintf(buff, "/home/pjreddie/cifar/cifar10_2_%d.cfg", count);
+ sprintf(buff, "/home/pjreddie/cifar/cifar10_%d.cfg", count);
save_network(net, buff);
}else{
printf("%d: Loss: %f, Time: %lf seconds, LR: %f, Momentum: %f, Decay: %f\n", count, loss, (float)(end-start)/CLOCKS_PER_SEC, net.learning_rate, net.momentum, net.decay);
@@ -540,14 +676,14 @@
}
-void test_nist()
+void test_nist(char *path)
{
srand(222222);
- network net = parse_network_cfg("cfg/nist_final.cfg");
+ network net = parse_network_cfg(path);
data test = load_categorical_data_csv("data/mnist/mnist_test.csv",0,10);
- translate_data_rows(test, -144);
+ normalize_data_rows(test);
clock_t start = clock(), end;
- float test_acc = network_accuracy_multi(net, test,16);
+ float test_acc = network_accuracy_gpu(net, test);
end = clock();
printf("Accuracy: %f, Time: %lf seconds\n", test_acc,(float)(end-start)/CLOCKS_PER_SEC);
}
@@ -558,19 +694,43 @@
network net = parse_network_cfg("cfg/nist.cfg");
data train = load_categorical_data_csv("data/mnist/mnist_train.csv", 0, 10);
data test = load_categorical_data_csv("data/mnist/mnist_test.csv",0,10);
- translate_data_rows(train, -144);
- translate_data_rows(test, -144);
+ normalize_data_rows(train);
+ normalize_data_rows(test);
int count = 0;
- int iters = 50000/net.batch;
+ int iters = 60000/net.batch + 1;
+ //iters = 6000/net.batch + 1;
while(++count <= 2000){
clock_t start = clock(), end;
- float loss = train_network_sgd(net, train, iters);
+ float loss = train_network_sgd_gpu(net, train, iters);
end = clock();
- float test_acc = network_accuracy(net, test);
+ float test_acc = 0;
+ if(count%1 == 0) test_acc = network_accuracy_gpu(net, test);
printf("%d: Loss: %f, Test Acc: %f, Time: %lf seconds\n", count, loss, test_acc,(float)(end-start)/CLOCKS_PER_SEC);
}
}
+void train_nist_distributed(char *address)
+{
+ srand(time(0));
+ network net = parse_network_cfg("cfg/nist.client");
+ data train = load_categorical_data_csv("data/mnist/mnist_train.csv", 0, 10);
+ //data test = load_categorical_data_csv("data/mnist/mnist_test.csv",0,10);
+ normalize_data_rows(train);
+ //normalize_data_rows(test);
+ int count = 0;
+ int iters = 50000/net.batch;
+ iters = 1000/net.batch + 1;
+ while(++count <= 2000){
+ clock_t start = clock(), end;
+ float loss = train_network_sgd_gpu(net, train, iters);
+ client_update(net, address);
+ end = clock();
+ //float test_acc = network_accuracy_gpu(net, test);
+ //float test_acc = 0;
+ printf("%d: Loss: %f, Time: %lf seconds\n", count, loss, (float)(end-start)/CLOCKS_PER_SEC);
+ }
+}
+
void test_ensemble()
{
int i;
@@ -597,14 +757,14 @@
lr /= 2;
}
matrix partial = network_predict_data(net, test);
- float acc = matrix_accuracy(test.y, partial);
+ float acc = matrix_topk_accuracy(test.y, partial,1);
printf("Model Accuracy: %lf\n", acc);
matrix_add_matrix(partial, prediction);
- acc = matrix_accuracy(test.y, prediction);
+ acc = matrix_topk_accuracy(test.y, prediction,1);
printf("Current Ensemble Accuracy: %lf\n", acc);
free_matrix(partial);
}
- float acc = matrix_accuracy(test.y, prediction);
+ float acc = matrix_topk_accuracy(test.y, prediction,1);
printf("Full Ensemble Accuracy: %lf\n", acc);
}
@@ -660,25 +820,27 @@
printf("%d, %d, %d\n", train.X.rows, split[0].X.rows, split[1].X.rows);
}
-void test_im2row()
-{
- int h = 20;
- int w = 20;
- int c = 3;
- int stride = 1;
- int size = 11;
- image test = make_random_image(h,w,c);
- int mc = 1;
- int mw = ((h-size)/stride+1)*((w-size)/stride+1);
- int mh = (size*size*c);
- int msize = mc*mw*mh;
- float *matrix = calloc(msize, sizeof(float));
- int i;
- for(i = 0; i < 1000; ++i){
- im2col_cpu(test.data,1, c, h, w, size, stride, 0, matrix);
- //image render = float_to_image(mh, mw, mc, matrix);
- }
+/*
+ void test_im2row()
+ {
+ int h = 20;
+ int w = 20;
+ int c = 3;
+ int stride = 1;
+ int size = 11;
+ image test = make_random_image(h,w,c);
+ int mc = 1;
+ int mw = ((h-size)/stride+1)*((w-size)/stride+1);
+ int mh = (size*size*c);
+ int msize = mc*mw*mh;
+ float *matrix = calloc(msize, sizeof(float));
+ int i;
+ for(i = 0; i < 1000; ++i){
+//im2col_cpu(test.data,1, c, h, w, size, stride, 0, matrix);
+//image render = float_to_image(mh, mw, mc, matrix);
}
+}
+ */
void flip_network()
{
@@ -731,6 +893,76 @@
#endif
}
+void test_correct_alexnet()
+{
+ char **labels = get_labels("/home/pjreddie/data/imagenet/cls.labels.list");
+ list *plist = get_paths("/data/imagenet/cls.train.list");
+ char **paths = (char **)list_to_array(plist);
+ printf("%d\n", plist->size);
+ clock_t time;
+ int count = 0;
+ network net;
+ int imgs = 1000/net.batch+1;
+ imgs = 1;
+#ifdef GPU
+ count = 0;
+ srand(222222);
+ net = parse_network_cfg("cfg/net.cfg");
+ while(++count <= 5){
+ time=clock();
+ data train = load_data(paths, imgs*net.batch, plist->size, labels, 1000, 256, 256);
+ //translate_data_rows(train, -144);
+ normalize_data_rows(train);
+ printf("Loaded: %lf seconds\n", sec(clock()-time));
+ time=clock();
+ float loss = train_network_data_gpu(net, train, imgs);
+ printf("%d: %f, %lf seconds, %d images\n", count, loss, sec(clock()-time), imgs*net.batch);
+ free_data(train);
+ }
+#endif
+ count = 0;
+ srand(222222);
+ net = parse_network_cfg("cfg/net.cfg");
+ printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
+ while(++count <= 5){
+ time=clock();
+ data train = load_data(paths, imgs*net.batch, plist->size, labels, 1000, 256,256);
+ //translate_data_rows(train, -144);
+ normalize_data_rows(train);
+ printf("Loaded: %lf seconds\n", sec(clock()-time));
+ time=clock();
+ float loss = train_network_data_cpu(net, train, imgs);
+ printf("%d: %f, %lf seconds, %d images\n", count, loss, sec(clock()-time), imgs*net.batch);
+ free_data(train);
+ }
+}
+
+void run_server()
+{
+ srand(time(0));
+ network net = parse_network_cfg("cfg/net.cfg");
+ set_batch_network(&net, 1);
+ server_update(net);
+}
+void test_client()
+{
+ network net = parse_network_cfg("cfg/alexnet.client");
+ clock_t time=clock();
+ client_update(net, "localhost");
+ printf("1\n");
+ client_update(net, "localhost");
+ printf("2\n");
+ client_update(net, "localhost");
+ printf("3\n");
+ printf("Transfered: %lf seconds\n", sec(clock()-time));
+}
+
+int find_int_arg(int argc, char* argv[], char *arg)
+{
+ int i;
+ for(i = 0; i < argc-1; ++i) if(0==strcmp(argv[i], arg)) return atoi(argv[i+1]);
+ return 0;
+}
int main(int argc, char *argv[])
{
@@ -738,95 +970,109 @@
fprintf(stderr, "usage: %s <function>\n", argv[0]);
return 0;
}
- if(0==strcmp(argv[1], "train")) train_imagenet();
- else if(0==strcmp(argv[1], "detection")) train_detection_net();
+ int index = find_int_arg(argc, argv, "-i");
+#ifdef GPU
+ cl_setup(index);
+#endif
+ if(0==strcmp(argv[1], "detection")) train_detection_net();
else if(0==strcmp(argv[1], "asirra")) train_asirra();
else if(0==strcmp(argv[1], "nist")) train_nist();
- else if(0==strcmp(argv[1], "test_correct")) test_gpu_net();
+ else if(0==strcmp(argv[1], "cifar")) train_cifar10();
+ else if(0==strcmp(argv[1], "test_correct")) test_correct_alexnet();
else if(0==strcmp(argv[1], "test")) test_imagenet();
- else if(0==strcmp(argv[1], "visualize")) test_visualize(argv[2]);
- else if(0==strcmp(argv[1], "valid")) validate_imagenet(argv[2]);
+ else if(0==strcmp(argv[1], "server")) run_server();
#ifdef GPU
else if(0==strcmp(argv[1], "test_gpu")) test_gpu_blas();
#endif
+ else if(argc < 3){
+ fprintf(stderr, "usage: %s <function> <filename>\n", argv[0]);
+ return 0;
+ }
+ else if(0==strcmp(argv[1], "train")) train_imagenet(argv[2]);
+ else if(0==strcmp(argv[1], "client")) train_imagenet_distributed(argv[2]);
+ else if(0==strcmp(argv[1], "detect")) test_detection(argv[2]);
+ else if(0==strcmp(argv[1], "init")) test_init(argv[2]);
+ else if(0==strcmp(argv[1], "visualize")) test_visualize(argv[2]);
+ else if(0==strcmp(argv[1], "valid")) validate_imagenet(argv[2]);
+ else if(0==strcmp(argv[1], "testnist")) test_nist(argv[2]);
fprintf(stderr, "Success!\n");
return 0;
}
/*
-void visualize_imagenet_topk(char *filename)
-{
- int i,j,k,l;
- int topk = 10;
- network net = parse_network_cfg("cfg/voc_imagenet.cfg");
- list *plist = get_paths(filename);
- node *n = plist->front;
- int h = voc_size(1), w = voc_size(1);
- int num = get_network_image(net).c;
- image **vizs = calloc(num, sizeof(image*));
- float **score = calloc(num, sizeof(float *));
- for(i = 0; i < num; ++i){
- vizs[i] = calloc(topk, sizeof(image));
- for(j = 0; j < topk; ++j) vizs[i][j] = make_image(h,w,3);
- score[i] = calloc(topk, sizeof(float));
- }
+ void visualize_imagenet_topk(char *filename)
+ {
+ int i,j,k,l;
+ int topk = 10;
+ network net = parse_network_cfg("cfg/voc_imagenet.cfg");
+ list *plist = get_paths(filename);
+ node *n = plist->front;
+ int h = voc_size(1), w = voc_size(1);
+ int num = get_network_image(net).c;
+ image **vizs = calloc(num, sizeof(image*));
+ float **score = calloc(num, sizeof(float *));
+ for(i = 0; i < num; ++i){
+ vizs[i] = calloc(topk, sizeof(image));
+ for(j = 0; j < topk; ++j) vizs[i][j] = make_image(h,w,3);
+ score[i] = calloc(topk, sizeof(float));
+ }
- int count = 0;
- while(n){
- ++count;
- char *image_path = (char *)n->val;
- image im = load_image(image_path, 0, 0);
- n = n->next;
- if(im.h < 200 || im.w < 200) continue;
- printf("Processing %dx%d image\n", im.h, im.w);
- resize_network(net, im.h, im.w, im.c);
- //scale_image(im, 1./255);
- translate_image(im, -144);
- forward_network(net, im.data, 0, 0);
- image out = get_network_image(net);
+ int count = 0;
+ while(n){
+ ++count;
+ char *image_path = (char *)n->val;
+ image im = load_image(image_path, 0, 0);
+ n = n->next;
+ if(im.h < 200 || im.w < 200) continue;
+ printf("Processing %dx%d image\n", im.h, im.w);
+ resize_network(net, im.h, im.w, im.c);
+//scale_image(im, 1./255);
+translate_image(im, -144);
+forward_network(net, im.data, 0, 0);
+image out = get_network_image(net);
- int dh = (im.h - h)/(out.h-1);
- int dw = (im.w - w)/(out.w-1);
- //printf("%d %d\n", dh, dw);
- for(k = 0; k < out.c; ++k){
- float topv = 0;
- int topi = -1;
- int topj = -1;
- for(i = 0; i < out.h; ++i){
- for(j = 0; j < out.w; ++j){
- float val = get_pixel(out, i, j, k);
- if(val > topv){
- topv = val;
- topi = i;
- topj = j;
- }
- }
- }
- if(topv){
- image sub = get_sub_image(im, dh*topi, dw*topj, h, w);
- for(l = 0; l < topk; ++l){
- if(topv > score[k][l]){
- float swap = score[k][l];
- score[k][l] = topv;
- topv = swap;
+int dh = (im.h - h)/(out.h-1);
+int dw = (im.w - w)/(out.w-1);
+//printf("%d %d\n", dh, dw);
+for(k = 0; k < out.c; ++k){
+float topv = 0;
+int topi = -1;
+int topj = -1;
+for(i = 0; i < out.h; ++i){
+for(j = 0; j < out.w; ++j){
+float val = get_pixel(out, i, j, k);
+if(val > topv){
+topv = val;
+topi = i;
+topj = j;
+}
+}
+}
+if(topv){
+image sub = get_sub_image(im, dh*topi, dw*topj, h, w);
+for(l = 0; l < topk; ++l){
+if(topv > score[k][l]){
+float swap = score[k][l];
+score[k][l] = topv;
+topv = swap;
- image swapi = vizs[k][l];
- vizs[k][l] = sub;
- sub = swapi;
- }
- }
- free_image(sub);
- }
- }
- free_image(im);
- if(count%50 == 0){
- image grid = grid_images(vizs, num, topk);
- //show_image(grid, "IMAGENET Visualization");
- save_image(grid, "IMAGENET Grid Single Nonorm");
- free_image(grid);
- }
- }
- //cvWaitKey(0);
+image swapi = vizs[k][l];
+vizs[k][l] = sub;
+sub = swapi;
+}
+}
+free_image(sub);
+}
+}
+free_image(im);
+if(count%50 == 0){
+image grid = grid_images(vizs, num, topk);
+//show_image(grid, "IMAGENET Visualization");
+save_image(grid, "IMAGENET Grid Single Nonorm");
+free_image(grid);
+}
+}
+//cvWaitKey(0);
}
void visualize_imagenet_features(char *filename)
--
Gitblit v1.10.0