From 7c120aef23fde5b215b0fb6eef3074a15f16ff69 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Wed, 19 Nov 2014 22:03:51 +0000
Subject: [PATCH] stable, dropout on gpu
---
src/cnn.c | 332 ++++++++++++++++++++++++++++++++++++-------------------
1 files changed, 217 insertions(+), 115 deletions(-)
diff --git a/src/cnn.c b/src/cnn.c
index bfba26a..f77b8f0 100644
--- a/src/cnn.c
+++ b/src/cnn.c
@@ -265,10 +265,8 @@
void test_parser()
{
- network net = parse_network_cfg("cfg/test_parser.cfg");
- save_network(net, "cfg/test_parser_1.cfg");
- network net2 = parse_network_cfg("cfg/test_parser_1.cfg");
- save_network(net2, "cfg/test_parser_2.cfg");
+ network net = parse_network_cfg("cfg/trained_imagenet.cfg");
+ save_network(net, "cfg/trained_imagenet_smaller.cfg");
}
void test_data()
@@ -278,71 +276,195 @@
free_data(train);
}
-void train_assira()
+void train_asirra()
{
- network net = parse_network_cfg("cfg/assira.cfg");
+ network net = parse_network_cfg("cfg/imagenet.cfg");
+ int imgs = 1000/net.batch+1;
+ //imgs = 1;
srand(2222222);
int i = 0;
char *labels[] = {"cat","dog"};
+ clock_t time;
while(1){
- i += 1000;
- data train = load_data_image_pathfile_random("data/assira/train.list", 1000, labels, 2, 256, 256);
+ i += 1;
+ 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_gpu(net, train, 10);
- end = clock();
- printf("%d: %f, Time: %lf seconds\n", i, loss, (float)(end-start)/CLOCKS_PER_SEC );
+ printf("Loaded: %lf seconds\n", sec(clock()-time));
+ time=clock();
+ //float loss = train_network_data(net, train, imgs);
+ float loss = 0;
+ printf("%d: %f, Time: %lf seconds\n", i*net.batch*imgs, loss, sec(clock()-time));
free_data(train);
- if(i%10000==0){
+ if(i%10==0){
char buff[256];
- sprintf(buff, "cfg/assira_backup_%d.cfg", i);
+ sprintf(buff, "cfg/asirra_backup_%d.cfg", i);
save_network(net, buff);
}
//lr *= .99;
}
}
-void test_visualize()
+void train_imagenet()
{
- network net = parse_network_cfg("cfg/voc_imagenet.cfg");
- srand(2222222);
- visualize_network(net);
- cvWaitKey(0);
+ float avg_loss = 1;
+ //network net = parse_network_cfg("/home/pjreddie/imagenet_backup/alexnet_1270.cfg");
+ network net = parse_network_cfg("cfg/imagenet.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));
+ 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);
+ //translate_data_rows(train, -144);
+ 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);
+ 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);
+ save_network(net, buff);
+ }
+ }
+}
+
+void validate_imagenet(char *filename)
+{
+ int i;
+ network net = parse_network_cfg(filename);
+ srand(time(0));
+
+ char **labels = get_labels("/home/pjreddie/data/imagenet/cls.val.labels.list");
+ char *path = "/home/pjreddie/data/imagenet/cls.val.list";
+
+ clock_t time;
+ float avg_acc = 0;
+ int splits = 50;
+ for(i = 0; i < splits; ++i){
+ time=clock();
+ data val = load_data_image_pathfile_part(path, i, splits, labels, 1000, 256, 256);
+ normalize_data_rows(val);
+ 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);
+ #endif
+ free_data(val);
+ }
+}
+
+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){
+ fgets(filename, 256, stdin);
+ image im = load_image_color(filename, 256, 256);
+ 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));
+ for(i = 0; i < 10; ++i){
+ int index = indexes[i];
+ printf("%s: %f\n", names[index], predictions[index]);
+ }
+ free_image(im);
+ }
+}
+
+void test_visualize(char *filename)
+{
+ network net = parse_network_cfg(filename);
+ 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);
@@ -358,7 +480,7 @@
data train = load_all_cifar10();
while(++count <= 10000){
clock_t start = clock(), end;
- float loss = train_network_sgd_gpu(net, train, iters);
+ float loss = train_network_sgd(net, train, iters);
end = clock();
//visualize_network(net);
//cvWaitKey(5000);
@@ -369,7 +491,7 @@
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);
@@ -426,35 +548,16 @@
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);
- //scale_data_rows(train, 1./128);
translate_data_rows(test, -144);
- //scale_data_rows(test, 1./128);
- //randomize_data(train);
int count = 0;
- //clock_t start = clock(), end;
- int iters = 10000/net.batch;
+ int iters = 50000/net.batch;
while(++count <= 2000){
clock_t start = clock(), end;
float loss = train_network_sgd(net, train, iters);
end = clock();
float test_acc = network_accuracy(net, test);
- //float test_acc = 0;
- 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);
- /*printf("%f %f %f %f %f\n", mean_array(get_network_output_layer(net,0), 100),
- mean_array(get_network_output_layer(net,1), 100),
- mean_array(get_network_output_layer(net,2), 100),
- mean_array(get_network_output_layer(net,3), 100),
- mean_array(get_network_output_layer(net,4), 100));
- */
- //save_network(net, "cfg/nist_final2.cfg");
-
- //printf("%5d Training Loss: %lf, Params: %f %f %f, ",count*1000, loss, lr, momentum, decay);
- //end = clock();
- //printf("Time: %lf seconds\n", (float)(end-start)/CLOCKS_PER_SEC);
- //start=end;
- //lr *= .5;
+ printf("%d: Loss: %f, Test Acc: %f, Time: %lf seconds\n", count, loss, test_acc,(float)(end-start)/CLOCKS_PER_SEC);
}
- //save_network(net, "cfg/nist_basic_trained.cfg");
}
void test_ensemble()
@@ -890,57 +993,56 @@
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 = 1000/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);
+ }
+ #ifdef GPU
+ 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);
+ }
+ #endif
+}
+
int main(int argc, char *argv[])
{
- //train_assira();
- //test_distribution();
- //feenableexcept(FE_DIVBYZERO | FE_INVALID | FE_OVERFLOW);
-
- //test_blas();
- //test_visualize();
- //test_gpu_blas();
- //test_blas();
- //test_convolve_matrix();
- // test_im2row();
- //test_split();
- //test_ensemble();
- //test_nist_single();
- //test_nist();
- 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();
+ 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], "asirra")) train_asirra();
+ else if(0==strcmp(argv[1], "nist")) train_nist();
+ else if(0==strcmp(argv[1], "train_small")) train_imagenet_small();
+ else if(0==strcmp(argv[1], "test_correct")) test_gpu_net();
+ 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]);
+ #ifdef GPU
+ else if(0==strcmp(argv[1], "test_gpu")) test_gpu_blas();
+ #endif
+ 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