From 1edcf73a73d2007afc61289245763f5cf0c29e10 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Thu, 04 Dec 2014 07:20:29 +0000
Subject: [PATCH] Detection good, split up col images
---
src/cnn.c | 998 +++++++++++++++++++++++++++++++++-------------------------
1 files changed, 562 insertions(+), 436 deletions(-)
diff --git a/src/cnn.c b/src/cnn.c
index 2d09582..46248ed 100644
--- a/src/cnn.c
+++ b/src/cnn.c
@@ -18,30 +18,31 @@
void test_convolve()
{
- image dog = load_image("dog.jpg",300,400);
- printf("dog channels %d\n", dog.c);
- image kernel = make_random_image(3,3,dog.c);
- image edge = make_image(dog.h, dog.w, 1);
- int i;
- clock_t start = clock(), end;
- for(i = 0; i < 1000; ++i){
- convolve(dog, kernel, 1, 0, edge, 1);
- }
- end = clock();
- printf("Convolutions: %lf seconds\n", (float)(end-start)/CLOCKS_PER_SEC);
- show_image_layers(edge, "Test Convolve");
+ image dog = load_image("dog.jpg",300,400);
+ printf("dog channels %d\n", dog.c);
+ image kernel = make_random_image(3,3,dog.c);
+ image edge = make_image(dog.h, dog.w, 1);
+ int i;
+ clock_t start = clock(), end;
+ for(i = 0; i < 1000; ++i){
+ convolve(dog, kernel, 1, 0, edge, 1);
+ }
+ end = clock();
+ printf("Convolutions: %lf seconds\n", (float)(end-start)/CLOCKS_PER_SEC);
+ 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));
+ 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;
@@ -50,7 +51,7 @@
for(i = 0; i < in_size; ++i){
X[i] = dog.data[i%get_network_input_size(net)];
}
-// get_batch(test, net.batch, X, y);
+ // 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);
@@ -72,42 +73,44 @@
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));
+ /*
+ 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);
+ 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};
+ 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;
@@ -116,297 +119,418 @@
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,
- 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");
- */
+ 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);
- printf("dog channels %d\n", dog.c);
+ image dog = load_image("dog.jpg",300,400);
+ printf("dog channels %d\n", dog.c);
- int size = 11;
- int stride = 4;
- int n = 40;
- float *filters = make_random_image(size, size, dog.c*n).data;
+ int size = 11;
+ int stride = 4;
+ int n = 40;
+ float *filters = make_random_image(size, size, dog.c*n).data;
- int mw = ((dog.h-size)/stride+1)*((dog.w-size)/stride+1);
- int mh = (size*size*dog.c);
- float *matrix = calloc(mh*mw, sizeof(float));
+ int mw = ((dog.h-size)/stride+1)*((dog.w-size)/stride+1);
+ int mh = (size*size*dog.c);
+ float *matrix = calloc(mh*mw, sizeof(float));
- image edge = make_image((dog.h-size)/stride+1, (dog.w-size)/stride+1, n);
+ image edge = make_image((dog.h-size)/stride+1, (dog.w-size)/stride+1, n);
- 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);
- gemm(0,0,n,mw,mh,1,filters,mh,matrix,mw,1,edge.data,mw);
- }
- end = clock();
- printf("Convolutions: %lf seconds\n", (float)(end-start)/CLOCKS_PER_SEC);
- show_image_layers(edge, "Test Convolve");
- cvWaitKey(0);
+ 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);
+ gemm(0,0,n,mw,mh,1,filters,mh,matrix,mw,1,edge.data,mw);
+ }
+ end = clock();
+ printf("Convolutions: %lf seconds\n", (float)(end-start)/CLOCKS_PER_SEC);
+ show_image_layers(edge, "Test Convolve");
+ cvWaitKey(0);
}
void test_color()
{
- image dog = load_image("test_color.png", 300, 400);
- show_image_layers(dog, "Test Color");
+ image dog = load_image("test_color.png", 300, 400);
+ show_image_layers(dog, "Test Color");
}
void verify_convolutional_layer()
{
- srand(0);
- int i;
- int n = 1;
- int stride = 1;
- int size = 3;
- float eps = .00000001;
- image test = make_random_image(5,5, 1);
- convolutional_layer layer = *make_convolutional_layer(1,test.h,test.w,test.c, n, size, stride, 0, RELU,0,0,0);
- image out = get_convolutional_image(layer);
- float **jacobian = calloc(test.h*test.w*test.c, sizeof(float));
+/*
+ srand(0);
+ int i;
+ int n = 1;
+ int stride = 1;
+ int size = 3;
+ float eps = .00000001;
+ image test = make_random_image(5,5, 1);
+ convolutional_layer layer = *make_convolutional_layer(1,test.h,test.w,test.c, n, size, stride, 0, RELU,0,0,0);
+ image out = get_convolutional_image(layer);
+ float **jacobian = calloc(test.h*test.w*test.c, sizeof(float));
- forward_convolutional_layer(layer, test.data);
- image base = copy_image(out);
+ forward_convolutional_layer(layer, test.data);
+ image base = copy_image(out);
- for(i = 0; i < test.h*test.w*test.c; ++i){
- test.data[i] += eps;
- forward_convolutional_layer(layer, test.data);
- image partial = copy_image(out);
- subtract_image(partial, base);
- scale_image(partial, 1/eps);
- jacobian[i] = partial.data;
- test.data[i] -= eps;
- }
- float **jacobian2 = calloc(out.h*out.w*out.c, sizeof(float));
- image in_delta = make_image(test.h, test.w, test.c);
- image out_delta = get_convolutional_delta(layer);
- for(i = 0; i < out.h*out.w*out.c; ++i){
- out_delta.data[i] = 1;
- backward_convolutional_layer(layer, in_delta.data);
- image partial = copy_image(in_delta);
- jacobian2[i] = partial.data;
- out_delta.data[i] = 0;
- }
- int j;
- float *j1 = calloc(test.h*test.w*test.c*out.h*out.w*out.c, sizeof(float));
- float *j2 = calloc(test.h*test.w*test.c*out.h*out.w*out.c, sizeof(float));
- for(i = 0; i < test.h*test.w*test.c; ++i){
- for(j =0 ; j < out.h*out.w*out.c; ++j){
- j1[i*out.h*out.w*out.c + j] = jacobian[i][j];
- j2[i*out.h*out.w*out.c + j] = jacobian2[j][i];
- printf("%f %f\n", jacobian[i][j], jacobian2[j][i]);
- }
- }
+ for(i = 0; i < test.h*test.w*test.c; ++i){
+ test.data[i] += eps;
+ forward_convolutional_layer(layer, test.data);
+ image partial = copy_image(out);
+ subtract_image(partial, base);
+ scale_image(partial, 1/eps);
+ jacobian[i] = partial.data;
+ test.data[i] -= eps;
+ }
+ float **jacobian2 = calloc(out.h*out.w*out.c, sizeof(float));
+ image in_delta = make_image(test.h, test.w, test.c);
+ image out_delta = get_convolutional_delta(layer);
+ for(i = 0; i < out.h*out.w*out.c; ++i){
+ out_delta.data[i] = 1;
+ backward_convolutional_layer(layer, in_delta.data);
+ image partial = copy_image(in_delta);
+ jacobian2[i] = partial.data;
+ out_delta.data[i] = 0;
+ }
+ int j;
+ float *j1 = calloc(test.h*test.w*test.c*out.h*out.w*out.c, sizeof(float));
+ float *j2 = calloc(test.h*test.w*test.c*out.h*out.w*out.c, sizeof(float));
+ for(i = 0; i < test.h*test.w*test.c; ++i){
+ for(j =0 ; j < out.h*out.w*out.c; ++j){
+ j1[i*out.h*out.w*out.c + j] = jacobian[i][j];
+ j2[i*out.h*out.w*out.c + j] = jacobian2[j][i];
+ printf("%f %f\n", jacobian[i][j], jacobian2[j][i]);
+ }
+ }
- image mj1 = float_to_image(test.w*test.h*test.c, out.w*out.h*out.c, 1, j1);
- image mj2 = float_to_image(test.w*test.h*test.c, out.w*out.h*out.c, 1, j2);
- printf("%f %f\n", avg_image_layer(mj1,0), avg_image_layer(mj2,0));
- show_image(mj1, "forward jacobian");
- show_image(mj2, "backward jacobian");
+ image mj1 = float_to_image(test.w*test.h*test.c, out.w*out.h*out.c, 1, j1);
+ image mj2 = float_to_image(test.w*test.h*test.c, out.w*out.h*out.c, 1, j2);
+ 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()
{
- image dog = load_image("dog.jpg", 300, 400);
- show_image(dog, "Test Load");
- show_image_layers(dog, "Test Load");
+ image dog = load_image("dog.jpg", 300, 400);
+ show_image(dog, "Test Load");
+ show_image_layers(dog, "Test Load");
}
void test_upsample()
{
- image dog = load_image("dog.jpg", 300, 400);
- int n = 3;
- image up = make_image(n*dog.h, n*dog.w, dog.c);
- upsample_image(dog, n, up);
- show_image(up, "Test Upsample");
- show_image_layers(up, "Test Upsample");
+ image dog = load_image("dog.jpg", 300, 400);
+ int n = 3;
+ image up = make_image(n*dog.h, n*dog.w, dog.c);
+ upsample_image(dog, n, up);
+ show_image(up, "Test Upsample");
+ show_image_layers(up, "Test Upsample");
}
void test_rotate()
{
- int i;
- image dog = load_image("dog.jpg",300,400);
- clock_t start = clock(), end;
- for(i = 0; i < 1001; ++i){
- rotate_image(dog);
- }
- end = clock();
- printf("Rotations: %lf seconds\n", (float)(end-start)/CLOCKS_PER_SEC);
- show_image(dog, "Test Rotate");
+ int i;
+ image dog = load_image("dog.jpg",300,400);
+ clock_t start = clock(), end;
+ for(i = 0; i < 1001; ++i){
+ rotate_image(dog);
+ }
+ end = clock();
+ printf("Rotations: %lf seconds\n", (float)(end-start)/CLOCKS_PER_SEC);
+ show_image(dog, "Test Rotate");
- image random = make_random_image(3,3,3);
- show_image(random, "Test Rotate Random");
- rotate_image(random);
- show_image(random, "Test Rotate Random");
- rotate_image(random);
- show_image(random, "Test Rotate Random");
+ image random = make_random_image(3,3,3);
+ show_image(random, "Test Rotate Random");
+ rotate_image(random);
+ show_image(random, "Test Rotate Random");
+ rotate_image(random);
+ show_image(random, "Test Rotate Random");
}
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()
+void train_asirra()
{
- char *labels[] = {"cat","dog"};
- data train = load_data_image_pathfile_random("train_paths.txt", 101,labels, 2, 300, 400);
- free_data(train);
-}
-
-void train_assira()
-{
- 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"};
+ srand(2222222);
+ int i = 0;
+ char *labels[] = {"cat","dog"};
+
+ list *plist = get_paths("data/assira/train.list");
+ char **paths = (char **)list_to_array(plist);
+ int m = plist->size;
+ free_list(plist);
+
clock_t time;
- while(1){
- i += 1000;
+
+ while(1){
+ 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);
+ data train = load_data_random(imgs*net.batch, paths, m, labels, 2, 256, 256);
+ normalize_data_rows(train);
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];
- sprintf(buff, "cfg/assira_backup_%d.cfg", i);
- save_network(net, buff);
- }
- //lr *= .99;
- }
+ //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%10==0){
+ char buff[256];
+ sprintf(buff, "cfg/asirra_backup_%d.cfg", i);
+ save_network(net, buff);
+ }
+ //lr *= .99;
+ }
}
+void train_detection_net()
+{
+ float avg_loss = 1;
+ //network net = parse_network_cfg("/home/pjreddie/imagenet_backup/alexnet_1270.cfg");
+ network net = parse_network_cfg("cfg/detnet.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));
+ srand(23410);
+ int i = 0;
+ list *plist = get_paths("/home/pjreddie/data/imagenet/horse.txt");
+ 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_detection_random(imgs*net.batch, paths, plist->size, 256, 256, 8, 8, 256);
+ //translate_data_rows(train, -144);
+ /*
+ image im = float_to_image(256, 256, 3, train.X.vals[0]);
+ float *truth = train.y.vals[0];
+ int j;
+ int r, c;
+ for(r = 0; r < 8; ++r){
+ for(c = 0; c < 8; ++c){
+ j = (r*8 + c) * 5;
+ if(truth[j]){
+ int d = 256/8;
+ int y = r*d+truth[j+1]*d;
+ int x = c*d+truth[j+2]*d;
+ int h = truth[j+3]*256;
+ int w = truth[j+4]*256;
+ printf("%f %f %f %f\n", truth[j+1], truth[j+2], truth[j+3], truth[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);
+ */
+
+ 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/detnet_%d.cfg", i);
+ save_network(net, buff);
+ }
+ }
+}
+
+
void train_imagenet()
{
- network net = parse_network_cfg("cfg/imagenet_backup_710.cfg");
+ float avg_loss = 1;
+ //network net = parse_network_cfg("/home/pjreddie/imagenet_backup/alexnet_1270.cfg");
+ network net = parse_network_cfg("cfg/alexnet.part");
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
int imgs = 1000/net.batch+1;
- //imgs=1;
- srand(888888);
- int i = 0;
+ srand(time(0));
+ int i = 0;
char **labels = get_labels("/home/pjreddie/data/imagenet/cls.labels.list");
- list *plist = get_paths("/home/pjreddie/data/imagenet/cls.cropped.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;
+ 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);
+ 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_sgd_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_%d.cfg", i);
- save_network(net, buff);
- }
- }
+#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/alexnet_%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");
+
+ list *plist = get_paths("/home/pjreddie/data/imagenet/cls.val.list");
+ char **paths = (char **)list_to_array(plist);
+ int m = plist->size;
+ free_list(plist);
+
+ clock_t time;
+ float avg_acc = 0;
+ int splits = 50;
+
+ for(i = 0; 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);
+
+ 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 draw_detection(image im, float *box)
+{
+ int j;
+ int r, c;
+ for(r = 0; r < 8; ++r){
+ for(c = 0; c < 8; ++c){
+ j = (r*8 + c) * 5;
+ printf("Prob: %f\n", box[j]);
+ if(box[j] > .05){
+ int d = 256/8;
+ 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 test_detection()
+{
+ network net = parse_network_cfg("cfg/detnet.test");
+ srand(2222222);
+ clock_t time;
+ char filename[256];
+ 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);
+ float *X = im.data;
+ time=clock();
+ float *predictions = network_predict(net, X);
+ printf("%s: Predicted in %f seconds.\n", filename, sec(clock()-time));
+ draw_detection(im, predictions);
+ free_image(im);
+ }
}
void test_imagenet()
{
- network net = parse_network_cfg("cfg/imagenet_test.cfg");
+ network net = parse_network_cfg("cfg/imagenet_test.cfg");
//imgs=1;
- srand(2222222);
- int i = 0;
+ 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);
+ while(1){
+ fgets(filename, 256, stdin);
+ strtok(filename, "\n");
image im = load_image_color(filename, 256, 256);
- normalize_image(im);
+ 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));
+ 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);
- }
+ free_image(im);
+ }
}
-void test_visualize()
+void test_visualize(char *filename)
{
- network net = parse_network_cfg("cfg/assira_backup_740000.cfg");
- srand(2222222);
- 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("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);
+ network net = parse_network_cfg(filename);
+ visualize_network(net);
+ cvWaitKey(0);
}
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);
@@ -490,35 +614,16 @@
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_gpu(net, train, iters);
+ 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()
@@ -625,7 +730,7 @@
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);
+ //im2col_cpu(test.data,1, c, h, w, size, stride, 0, matrix);
//image render = float_to_image(mh, mw, mc, matrix);
}
}
@@ -636,161 +741,204 @@
save_network(net, "cfg/voc_imagenet_rev.cfg");
}
-void tune_VOC()
+
+void visualize_cat()
{
- network net = parse_network_cfg("cfg/voc_start.cfg");
- srand(2222222);
- int i = 20;
- char *labels[] = {"aeroplane","bicycle","bird","boat","bottle","bus","car","cat","chair","cow","diningtable","dog","horse","motorbike","person","pottedplant","sheep","sofa","train","tvmonitor"};
- float lr = .000005;
- float momentum = .9;
- float decay = 0.0001;
- while(i++ < 1000 || 1){
- data train = load_data_image_pathfile_random("/home/pjreddie/VOC2012/trainval_paths.txt", 10, labels, 20, 256, 256);
-
- image im = float_to_image(256, 256, 3,train.X.vals[0]);
- show_image(im, "input");
- visualize_network(net);
- cvWaitKey(100);
-
- translate_data_rows(train, -144);
- clock_t start = clock(), end;
- float loss = train_network_sgd(net, train, 10);
- 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);
- free_data(train);
- /*
- if(i%10==0){
- char buff[256];
- sprintf(buff, "/home/pjreddie/voc_cfg/voc_ramp_%d.cfg", i);
- save_network(net, buff);
- }
- */
- //lr *= .99;
- }
-}
-
-int voc_size(int x)
-{
- x = x-1+3;
- x = x-1+3;
- x = x-1+3;
- x = (x-1)*2+1;
- x = x-1+5;
- x = (x-1)*2+1;
- x = (x-1)*4+11;
- return x;
-}
-
-image features_output_size(network net, IplImage *src, int outh, int outw)
-{
- int h = voc_size(outh);
- int w = voc_size(outw);
- fprintf(stderr, "%d %d\n", h, w);
-
- IplImage *sized = cvCreateImage(cvSize(w,h), src->depth, src->nChannels);
- cvResize(src, sized, CV_INTER_LINEAR);
- image im = ipl_to_image(sized);
- //normalize_array(im.data, im.h*im.w*im.c);
- translate_image(im, -144);
+ network net = parse_network_cfg("cfg/voc_imagenet.cfg");
+ 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, 0);
- image out = get_network_image(net);
- free_image(im);
- cvReleaseImage(&sized);
- return copy_image(out);
+
+ visualize_network(net);
+ cvWaitKey(0);
}
-void features_VOC_image_size(char *image_path, int h, int w)
-{
- int j;
- network net = parse_network_cfg("cfg/voc_imagenet.cfg");
- fprintf(stderr, "%s\n", image_path);
- IplImage* src = 0;
- if( (src = cvLoadImage(image_path,-1)) == 0 ) file_error(image_path);
- image out = features_output_size(net, src, h, w);
- for(j = 0; j < out.c*out.h*out.w; ++j){
- if(j != 0) printf(",");
- printf("%g", out.data[j]);
- }
- printf("\n");
- free_image(out);
- cvReleaseImage(&src);
-}
-void visualize_imagenet_topk(char *filename)
+void test_gpu_net()
{
- 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));
- }
-
+ 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;
- 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;
-
- 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);
- }
+ 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);
}
- //cvWaitKey(0);
+#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
+}
+
+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;
+
+ srand(222222);
+ network net = parse_network_cfg("cfg/alexnet.test");
+ printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
+ int imgs = 1000/net.batch+1;
+ imgs = 1;
+
+ while(++count <= 5){
+ 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();
+ 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);
+ }
+#ifdef GPU
+ count = 0;
+ srand(222222);
+ net = parse_network_cfg("cfg/alexnet.test");
+ while(++count <= 5){
+ 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();
+ 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
+}
+
+void test_server()
+{
+ network net = parse_network_cfg("cfg/alexnet.test");
+ server_update(net);
+}
+void test_client()
+{
+ network net = parse_network_cfg("cfg/alexnet.test");
+ client_update(net);
+}
+
+int main(int argc, char *argv[])
+{
+ 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], "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_correct_alexnet();
+ else if(0==strcmp(argv[1], "test")) test_imagenet();
+ else if(0==strcmp(argv[1], "server")) test_server();
+ else if(0==strcmp(argv[1], "client")) test_client();
+ else if(0==strcmp(argv[1], "detect")) test_detection();
+ 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
+ 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));
+ }
+
+ 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;
+
+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)
@@ -834,19 +982,6 @@
}
cvWaitKey(0);
}
-
-void visualize_cat()
-{
- network net = parse_network_cfg("cfg/voc_imagenet.cfg");
- 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, 0);
-
- visualize_network(net);
- cvWaitKey(0);
-}
-
void features_VOC_image(char *image_file, char *image_dir, char *out_dir, int flip, int interval)
{
int i,j;
@@ -953,13 +1088,4 @@
cvWaitKey(0);
cvWaitKey(0);
}
-
-
-int main(int argc, char *argv[])
-{
- test_gpu_blas();
- //train_imagenet();
- //train_nist();
- fprintf(stderr, "Success!\n");
- return 0;
-}
+*/
--
Gitblit v1.10.0