From af4e4f92dc9e5da160eb6c6870a7b38b863f1c6c Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Tue, 28 Oct 2014 02:45:06 +0000
Subject: [PATCH] getting rid of sub_arrays, nvidia driver memory leak
---
src/cnn.c | 263 ++++++++++++++++++++++++++++++++++------------------
1 files changed, 170 insertions(+), 93 deletions(-)
diff --git a/src/cnn.c b/src/cnn.c
index 472aa03..9e9e62b 100644
--- a/src/cnn.c
+++ b/src/cnn.c
@@ -278,29 +278,24 @@
free_data(train);
}
-void train_full()
+void train_assira()
{
- network net = parse_network_cfg("cfg/imagenet.cfg");
+ network net = parse_network_cfg("cfg/assira.cfg");
+ int imgs = 1000/net.batch+1;
+ //imgs = 1;
srand(2222222);
int i = 0;
char *labels[] = {"cat","dog"};
- float lr = .00001;
- float momentum = .9;
- float decay = 0.01;
+ clock_t time;
while(1){
i += 1000;
- data train = load_data_image_pathfile_random("images/assira/train.list", 1000, labels, 2, 256, 256);
- //image im = float_to_image(256, 256, 3,train.X.vals[0]);
- //visualize_network(net);
- //cvWaitKey(100);
- //show_image(im, "input");
- //cvWaitKey(100);
- //scale_data_rows(train, 1./255.);
+ time=clock();
+ data train = load_data_image_pathfile_random("data/assira/train.list", imgs*net.batch, labels, 2, 256, 256);
normalize_data_rows(train);
- clock_t start = clock(), end;
- float loss = train_network_sgd(net, train, 1000);
- end = clock();
- printf("%d: %f, Time: %lf seconds, LR: %f, Momentum: %f, Decay: %f\n", i, loss, (float)(end-start)/CLOCKS_PER_SEC, lr, momentum, decay);
+ printf("Loaded: %lf seconds\n", sec(clock()-time));
+ time=clock();
+ float loss = train_network_sgd(net, train, imgs);
+ printf("%d: %f, Time: %lf seconds\n", i, loss, sec(clock()-time));
free_data(train);
if(i%10000==0){
char buff[256];
@@ -311,47 +306,135 @@
}
}
+void train_imagenet()
+{
+ network net = parse_network_cfg("/home/pjreddie/imagenet_backup/imagenet_backup_slower_larger_870.cfg");
+ printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
+ int imgs = 1000/net.batch+1;
+ srand(986987);
+ 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;
+ while(1){
+ i += 1;
+ time=clock();
+ data train = load_data_random(imgs*net.batch, paths, plist->size, labels, 1000, 256, 256);
+ normalize_data_rows(train);
+ printf("Loaded: %lf seconds\n", sec(clock()-time));
+ time=clock();
+ #ifdef GPU
+ float loss = train_network_data_gpu(net, train, imgs);
+ printf("%d: %f, %lf seconds, %d images\n", i, 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_backup_larger_%d.cfg", i);
+ save_network(net, buff);
+ }
+ }
+}
+
+void train_imagenet_small()
+{
+ network net = parse_network_cfg("cfg/imagenet_small.cfg");
+ printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
+ int imgs=1;
+ srand(111222);
+ 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;
+
+ i += 1;
+ time=clock();
+ data train = load_data_random(imgs*net.batch, paths, plist->size, labels, 1000, 256, 256);
+ normalize_data_rows(train);
+ printf("Loaded: %lf seconds\n", sec(clock()-time));
+ time=clock();
+#ifdef GPU
+ float loss = train_network_data_gpu(net, train, imgs);
+ printf("%d: %f, %lf seconds, %d images\n", i, loss, sec(clock()-time), i*imgs*net.batch);
+#endif
+ free_data(train);
+ char buff[256];
+ sprintf(buff, "/home/pjreddie/imagenet_backup/imagenet_backup_slower_larger_%d.cfg", i);
+ save_network(net, buff);
+}
+
+void test_imagenet()
+{
+ network net = parse_network_cfg("cfg/imagenet_test.cfg");
+ //imgs=1;
+ srand(2222222);
+ int i = 0;
+ char **names = get_labels("cfg/shortnames.txt");
+ clock_t time;
+ char filename[256];
+ int indexes[10];
+ while(1){
+ gets(filename);
+ image im = load_image_color(filename, 256, 256);
+ 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));
+ for(i = 0; i < 10; ++i){
+ int index = indexes[i];
+ printf("%s: %f\n", names[index], predictions[index]);
+ }
+ free_image(im);
+ }
+}
+
void test_visualize()
{
- network net = parse_network_cfg("cfg/voc_imagenet.cfg");
- srand(2222222);
- visualize_network(net);
- cvWaitKey(0);
+ network net = parse_network_cfg("cfg/imagenet_test.cfg");
+ visualize_network(net);
+ cvWaitKey(0);
}
void test_full()
{
- network net = parse_network_cfg("cfg/backup_1300.cfg");
- srand(2222222);
- int i,j;
- int total = 100;
- char *labels[] = {"cat","dog"};
- FILE *fp = fopen("preds.txt","w");
- for(i = 0; i < total; ++i){
- visualize_network(net);
- cvWaitKey(100);
- data test = load_data_image_pathfile_part("images/assira/test.list", i, total, labels, 2, 256, 256);
- image im = float_to_image(256, 256, 3,test.X.vals[0]);
- show_image(im, "input");
- cvWaitKey(100);
- normalize_data_rows(test);
- for(j = 0; j < test.X.rows; ++j){
- float *x = test.X.vals[j];
- forward_network(net, x, 0, 0);
- int class = get_predicted_class_network(net);
- fprintf(fp, "%d\n", class);
- }
- free_data(test);
- }
- fclose(fp);
+ network net = parse_network_cfg("cfg/backup_1300.cfg");
+ srand(2222222);
+ int i,j;
+ int total = 100;
+ char *labels[] = {"cat","dog"};
+ FILE *fp = fopen("preds.txt","w");
+ for(i = 0; i < total; ++i){
+ visualize_network(net);
+ cvWaitKey(100);
+ data test = load_data_image_pathfile_part("data/assira/test.list", i, total, labels, 2, 256, 256);
+ image im = float_to_image(256, 256, 3,test.X.vals[0]);
+ show_image(im, "input");
+ cvWaitKey(100);
+ normalize_data_rows(test);
+ for(j = 0; j < test.X.rows; ++j){
+ float *x = test.X.vals[j];
+ forward_network(net, x, 0, 0);
+ int class = get_predicted_class_network(net);
+ fprintf(fp, "%d\n", class);
+ }
+ free_data(test);
+ }
+ fclose(fp);
}
void test_cifar10()
{
network net = parse_network_cfg("cfg/cifar10_part5.cfg");
data test = load_cifar10_data("data/cifar10/test_batch.bin");
- clock_t start = clock(), end;
+ clock_t start = clock(), end;
float test_acc = network_accuracy(net, test);
- end = clock();
+ end = clock();
printf("%f in %f Sec\n", test_acc, (float)(end-start)/CLOCKS_PER_SEC);
visualize_network(net);
cvWaitKey(0);
@@ -369,8 +452,8 @@
clock_t start = clock(), end;
float loss = train_network_sgd(net, train, iters);
end = clock();
- visualize_network(net);
- cvWaitKey(5000);
+ //visualize_network(net);
+ //cvWaitKey(5000);
//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);
@@ -378,7 +461,7 @@
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);
char buff[256];
- sprintf(buff, "/home/pjreddie/cifar/cifar2_%d.cfg", count);
+ sprintf(buff, "/home/pjreddie/cifar/cifar10_2_%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);
@@ -899,57 +982,51 @@
cvWaitKey(0);
}
+void test_gpu_net()
+{
+ srand(222222);
+ 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);
+ int count = 0;
+ int iters = 10000/net.batch;
+ while(++count <= 5){
+ clock_t start = clock(), end;
+ float loss = train_network_sgd(net, train, iters);
+ end = clock();
+ 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);
+ }
+ count = 0;
+ srand(222222);
+ net = parse_network_cfg("cfg/nist.cfg");
+ while(++count <= 5){
+ clock_t start = clock(), end;
+ float loss = train_network_sgd_gpu(net, train, iters);
+ end = clock();
+ 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);
+ }
+}
+
int main(int argc, char *argv[])
{
- //train_full();
- //test_distribution();
- //feenableexcept(FE_DIVBYZERO | FE_INVALID | FE_OVERFLOW);
-
- //test_blas();
- //test_visualize();
+ if(argc != 2){
+ fprintf(stderr, "usage: %s <function>\n", argv[0]);
+ return 0;
+ }
+ if(0==strcmp(argv[1], "train")) train_imagenet();
+ else if(0==strcmp(argv[1], "train_small")) train_imagenet_small();
+ else if(0==strcmp(argv[1], "test_gpu")) test_gpu_blas();
+ else if(0==strcmp(argv[1], "test")) test_gpu_net();
//test_gpu_blas();
- //test_blas();
- //test_convolve_matrix();
- // test_im2row();
- //test_split();
- //test_ensemble();
- //test_nist_single();
- //test_nist();
+ //train_imagenet_small();
+ //test_imagenet();
//train_nist();
- test_convolutional_layer();
- //test_col2im();
- //test_cifar10();
- //train_cifar10();
- //test_vince();
- //test_full();
- //tune_VOC();
- //features_VOC_image(argv[1], argv[2], argv[3], 0);
- //features_VOC_image(argv[1], argv[2], argv[3], 1);
- //train_VOC();
- //features_VOC_image(argv[1], argv[2], argv[3], 0, 4);
- //features_VOC_image(argv[1], argv[2], argv[3], 1, 4);
- //features_VOC_image_size(argv[1], atoi(argv[2]), atoi(argv[3]));
- //visualize_imagenet_features("data/assira/train.list");
- //visualize_imagenet_topk("data/VOC2012.list");
- //visualize_cat();
- //flip_network();
//test_visualize();
- //test_parser();
fprintf(stderr, "Success!\n");
- //test_random_preprocess();
- //test_random_classify();
- //test_parser();
- //test_backpropagate();
- //test_ann();
- //test_convolve();
- //test_upsample();
- //test_rotate();
- //test_load();
- //test_network();
- //test_convolutional_layer();
- //verify_convolutional_layer();
- //test_color();
- //cvWaitKey(0);
return 0;
}
--
Gitblit v1.10.0