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 | 432 +++++++++++++++++++++++++++++++++++++++++------------
1 files changed, 329 insertions(+), 103 deletions(-)
diff --git a/src/cnn.c b/src/cnn.c
index f866194..9e9e62b 100644
--- a/src/cnn.c
+++ b/src/cnn.c
@@ -32,6 +32,113 @@
show_image_layers(edge, "Test Convolve");
}
+#ifdef GPU
+
+void test_convolutional_layer()
+{
+ int i;
+ image dog = load_image("data/dog.jpg",224,224);
+ network net = parse_network_cfg("cfg/convolutional.cfg");
+// data test = load_cifar10_data("data/cifar10/test_batch.bin");
+// float *X = calloc(net.batch*test.X.cols, sizeof(float));
+// float *y = calloc(net.batch*test.y.cols, sizeof(float));
+ int in_size = get_network_input_size(net)*net.batch;
+ int del_size = get_network_output_size_layer(net, 0)*net.batch;
+ int size = get_network_output_size(net)*net.batch;
+ float *X = calloc(in_size, sizeof(float));
+ float *y = calloc(size, sizeof(float));
+ for(i = 0; i < in_size; ++i){
+ X[i] = dog.data[i%get_network_input_size(net)];
+ }
+// get_batch(test, net.batch, X, y);
+ clock_t start, end;
+ cl_mem input_cl = cl_make_array(X, in_size);
+ cl_mem truth_cl = cl_make_array(y, size);
+
+ forward_network_gpu(net, input_cl, truth_cl, 1);
+ start = clock();
+ forward_network_gpu(net, input_cl, truth_cl, 1);
+ end = clock();
+ float gpu_sec = (float)(end-start)/CLOCKS_PER_SEC;
+ printf("forward gpu: %f sec\n", gpu_sec);
+ start = clock();
+ backward_network_gpu(net, input_cl);
+ end = clock();
+ gpu_sec = (float)(end-start)/CLOCKS_PER_SEC;
+ printf("backward gpu: %f sec\n", gpu_sec);
+ //float gpu_cost = get_network_cost(net);
+ float *gpu_out = calloc(size, sizeof(float));
+ memcpy(gpu_out, get_network_output(net), size*sizeof(float));
+
+ float *gpu_del = calloc(del_size, sizeof(float));
+ memcpy(gpu_del, get_network_delta_layer(net, 0), del_size*sizeof(float));
+
+/*
+ start = clock();
+ forward_network(net, X, y, 1);
+ backward_network(net, X);
+ float cpu_cost = get_network_cost(net);
+ end = clock();
+ float cpu_sec = (float)(end-start)/CLOCKS_PER_SEC;
+ float *cpu_out = calloc(size, sizeof(float));
+ memcpy(cpu_out, get_network_output(net), size*sizeof(float));
+ float *cpu_del = calloc(del_size, sizeof(float));
+ memcpy(cpu_del, get_network_delta_layer(net, 0), del_size*sizeof(float));
+
+ float sum = 0;
+ float del_sum = 0;
+ for(i = 0; i < size; ++i) sum += pow(gpu_out[i] - cpu_out[i], 2);
+ for(i = 0; i < del_size; ++i) {
+ //printf("%f %f\n", cpu_del[i], gpu_del[i]);
+ del_sum += pow(cpu_del[i] - gpu_del[i], 2);
+ }
+ printf("GPU cost: %f, CPU cost: %f\n", gpu_cost, cpu_cost);
+ printf("gpu: %f sec, cpu: %f sec, diff: %f, delta diff: %f, size: %d\n", gpu_sec, cpu_sec, sum, del_sum, size);
+ */
+}
+
+void test_col2im()
+{
+ float col[] = {1,2,1,2,
+ 1,2,1,2,
+ 1,2,1,2,
+ 1,2,1,2,
+ 1,2,1,2,
+ 1,2,1,2,
+ 1,2,1,2,
+ 1,2,1,2,
+ 1,2,1,2};
+ float im[16] = {0};
+ int batch = 1;
+ int channels = 1;
+ int height=4;
+ int width=4;
+ int ksize = 3;
+ int stride = 1;
+ int pad = 0;
+ 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,
+ 9,10,11,12
+ };
+ float data_col[18] = {0};
+ im2col_cpu(data_im, batch,
+ channels, height, width,
+ ksize, stride, pad, data_col) ;
+ for(i = 0; i < 18; ++i)printf("%f,", data_col[i]);
+ printf("\n");
+ */
+}
+
+#endif
+
void test_convolve_matrix()
{
image dog = load_image("dog.jpg",300,400);
@@ -171,29 +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];
@@ -204,45 +306,145 @@
}
}
+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);
- 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()
{
- srand(222222);
+ network net = parse_network_cfg("cfg/cifar10_part5.cfg");
+ data test = load_cifar10_data("data/cifar10/test_batch.bin");
+ clock_t start = clock(), end;
+ float test_acc = network_accuracy(net, test);
+ end = clock();
+ printf("%f in %f Sec\n", test_acc, (float)(end-start)/CLOCKS_PER_SEC);
+ visualize_network(net);
+ cvWaitKey(0);
+}
+
+void train_cifar10()
+{
+ srand(555555);
network net = parse_network_cfg("cfg/cifar10.cfg");
- //data test = load_cifar10_data("data/cifar10/test_batch.bin");
+ data test = load_cifar10_data("data/cifar10/test_batch.bin");
int count = 0;
int iters = 10000/net.batch;
data train = load_all_cifar10();
@@ -251,11 +453,19 @@
float loss = train_network_sgd(net, train, iters);
end = clock();
//visualize_network(net);
- //cvWaitKey(1000);
+ //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);
- 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);
+ if(count%10 == 0){
+ 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/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);
+ }
}
free_data(train);
}
@@ -281,10 +491,10 @@
void test_nist_single()
{
srand(222222);
- network net = parse_network_cfg("cfg/nist.cfg");
+ network net = parse_network_cfg("cfg/nist_single.cfg");
data train = load_categorical_data_csv("data/mnist/mnist_tiny.csv", 0, 10);
normalize_data_rows(train);
- float loss = train_network_sgd(net, train, 5);
+ float loss = train_network_sgd(net, train, 1);
printf("Loss: %f, LR: %f, Momentum: %f, Decay: %f\n", loss, net.learning_rate, net.momentum, net.decay);
}
@@ -292,25 +502,43 @@
void test_nist()
{
srand(222222);
+ network net = parse_network_cfg("cfg/nist_final.cfg");
+ data test = load_categorical_data_csv("data/mnist/mnist_test.csv",0,10);
+ translate_data_rows(test, -144);
+ clock_t start = clock(), end;
+ float test_acc = network_accuracy_multi(net, test,16);
+ end = clock();
+ printf("Accuracy: %f, Time: %lf seconds\n", test_acc,(float)(end-start)/CLOCKS_PER_SEC);
+}
+
+void train_nist()
+{
+ 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);
- scale_data_rows(train, 1./128);
- translate_data_rows(test, -144);
- scale_data_rows(test, 1./128);
+ 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;
- while(++count <= 100){
+ 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);
- //save_network(net, "cfg/nist_basic_trained.cfg");
+ /*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();
@@ -373,7 +601,7 @@
int index = rand()%m.rows;
//image p = float_to_image(1690,1,1,m.vals[index]);
//normalize_image(p);
- forward_network(net, m.vals[index], 1);
+ forward_network(net, m.vals[index], 0, 1);
float *out = get_network_output(net);
float *delta = get_network_delta(net);
//printf("%f\n", out[0]);
@@ -394,7 +622,7 @@
matrix test = csv_to_matrix("test.csv");
truth = pop_column(&test, 0);
for(i = 0; i < test.rows; ++i){
- forward_network(net, test.vals[i], 0);
+ forward_network(net, test.vals[i],0, 0);
float *out = get_network_output(net);
if(fabs(out[0]) < .5) fprintf(fp, "0\n");
else fprintf(fp, "1\n");
@@ -494,7 +722,7 @@
//normalize_array(im.data, im.h*im.w*im.c);
translate_image(im, -144);
resize_network(net, im.h, im.w, im.c);
- forward_network(net, im.data, 0);
+ forward_network(net, im.data, 0, 0);
image out = get_network_image(net);
free_image(im);
cvReleaseImage(&sized);
@@ -546,7 +774,7 @@
resize_network(net, im.h, im.w, im.c);
//scale_image(im, 1./255);
translate_image(im, -144);
- forward_network(net, im.data, 0);
+ forward_network(net, im.data, 0, 0);
image out = get_network_image(net);
int dh = (im.h - h)/(out.h-1);
@@ -608,7 +836,7 @@
image im = load_image(image_path, 0, 0);
printf("Processing %dx%d image\n", im.h, im.w);
resize_network(net, im.h, im.w, im.c);
- forward_network(net, im.data, 0);
+ forward_network(net, im.data, 0, 0);
image out = get_network_image(net);
int dh = (im.h - h)/h;
@@ -641,7 +869,7 @@
image im = load_image("data/cat.png", 0, 0);
printf("Processing %dx%d image\n", im.h, im.w);
resize_network(net, im.h, im.w, im.c);
- forward_network(net, im.data, 0);
+ forward_network(net, im.data, 0, 0);
visualize_network(net);
cvWaitKey(0);
@@ -754,53 +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();
- //test_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();
+ //train_imagenet_small();
+ //test_imagenet();
+ //train_nist();
//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