From cc06817efa24f20811ef6b32143c6700a91c5f2a Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Fri, 11 Apr 2014 08:00:27 +0000
Subject: [PATCH] Attempt at visualizing ImageNet Features
---
src/tests.c | 799 ++++++++++++++++++++++++++++++++++++++++++++------------
1 files changed, 623 insertions(+), 176 deletions(-)
diff --git a/src/tests.c b/src/tests.c
index 0e639be..5d9136d 100644
--- a/src/tests.c
+++ b/src/tests.c
@@ -1,68 +1,136 @@
#include "connected_layer.h"
+//#include "old_conv.h"
#include "convolutional_layer.h"
#include "maxpool_layer.h"
#include "network.h"
#include "image.h"
#include "parser.h"
+#include "data.h"
+#include "matrix.h"
+#include "utils.h"
+#include "mini_blas.h"
#include <time.h>
#include <stdlib.h>
#include <stdio.h>
+#define _GNU_SOURCE
+#include <fenv.h>
+
void test_convolve()
{
- image dog = load_image("dog.jpg");
- //show_image_layers(dog, "Dog");
+ 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);
+ convolve(dog, kernel, 1, 0, edge, 1);
}
end = clock();
- printf("Convolutions: %lf seconds\n", (double)(end-start)/CLOCKS_PER_SEC);
+ printf("Convolutions: %lf seconds\n", (float)(end-start)/CLOCKS_PER_SEC);
show_image_layers(edge, "Test Convolve");
}
+void test_convolve_matrix()
+{
+ 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 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);
+
+
+ int i;
+ clock_t start = clock(), end;
+ for(i = 0; i < 1000; ++i){
+ im2col_cpu(dog.data, dog.c, dog.h, dog.w, size, stride, 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");
+ image dog = load_image("test_color.png", 300, 400);
show_image_layers(dog, "Test Color");
}
-void test_convolutional_layer()
+void verify_convolutional_layer()
{
srand(0);
- image dog = load_image("dog.jpg");
int i;
- int n = 3;
+ int n = 1;
int stride = 1;
int size = 3;
- convolutional_layer layer = *make_convolutional_layer(dog.h, dog.w, dog.c, n, size, stride);
- char buff[256];
- for(i = 0; i < n; ++i) {
- sprintf(buff, "Kernel %d", i);
- show_image(layer.kernels[i], buff);
- }
- run_convolutional_layer(dog, layer);
+ 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, RELU);
+ image out = get_convolutional_image(layer);
+ float **jacobian = calloc(test.h*test.w*test.c, sizeof(float));
- maxpool_layer mlayer = *make_maxpool_layer(layer.output.h, layer.output.w, layer.output.c, 2);
- run_maxpool_layer(layer.output,mlayer);
+ forward_convolutional_layer(layer, test.data);
+ image base = copy_image(out);
- show_image_layers(mlayer.output, "Test Maxpool Layer");
+ 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");
}
void test_load()
{
- image dog = load_image("dog.jpg");
+ 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");
+ 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);
@@ -73,13 +141,13 @@
void test_rotate()
{
int i;
- image dog = load_image("dog.jpg");
+ 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", (double)(end-start)/CLOCKS_PER_SEC);
+ printf("Rotations: %lf seconds\n", (float)(end-start)/CLOCKS_PER_SEC);
show_image(dog, "Test Rotate");
image random = make_random_image(3,3,3);
@@ -90,168 +158,546 @@
show_image(random, "Test Rotate Random");
}
-void test_network()
-{
- network net;
- net.n = 11;
- net.layers = calloc(net.n, sizeof(void *));
- net.types = calloc(net.n, sizeof(LAYER_TYPE));
- net.types[0] = CONVOLUTIONAL;
- net.types[1] = MAXPOOL;
- net.types[2] = CONVOLUTIONAL;
- net.types[3] = MAXPOOL;
- net.types[4] = CONVOLUTIONAL;
- net.types[5] = CONVOLUTIONAL;
- net.types[6] = CONVOLUTIONAL;
- net.types[7] = MAXPOOL;
- net.types[8] = CONNECTED;
- net.types[9] = CONNECTED;
- net.types[10] = CONNECTED;
-
- image dog = load_image("test_hinton.jpg");
-
- int n = 48;
- int stride = 4;
- int size = 11;
- convolutional_layer cl = *make_convolutional_layer(dog.h, dog.w, dog.c, n, size, stride);
- maxpool_layer ml = *make_maxpool_layer(cl.output.h, cl.output.w, cl.output.c, 2);
-
- n = 128;
- size = 5;
- stride = 1;
- convolutional_layer cl2 = *make_convolutional_layer(ml.output.h, ml.output.w, ml.output.c, n, size, stride);
- maxpool_layer ml2 = *make_maxpool_layer(cl2.output.h, cl2.output.w, cl2.output.c, 2);
-
- n = 192;
- size = 3;
- convolutional_layer cl3 = *make_convolutional_layer(ml2.output.h, ml2.output.w, ml2.output.c, n, size, stride);
- convolutional_layer cl4 = *make_convolutional_layer(cl3.output.h, cl3.output.w, cl3.output.c, n, size, stride);
- n = 128;
- convolutional_layer cl5 = *make_convolutional_layer(cl4.output.h, cl4.output.w, cl4.output.c, n, size, stride);
- maxpool_layer ml3 = *make_maxpool_layer(cl5.output.h, cl5.output.w, cl5.output.c, 4);
- connected_layer nl = *make_connected_layer(ml3.output.h*ml3.output.w*ml3.output.c, 4096, RELU);
- connected_layer nl2 = *make_connected_layer(4096, 4096, RELU);
- connected_layer nl3 = *make_connected_layer(4096, 1000, RELU);
-
- net.layers[0] = &cl;
- net.layers[1] = &ml;
- net.layers[2] = &cl2;
- net.layers[3] = &ml2;
- net.layers[4] = &cl3;
- net.layers[5] = &cl4;
- net.layers[6] = &cl5;
- net.layers[7] = &ml3;
- net.layers[8] = &nl;
- net.layers[9] = &nl2;
- net.layers[10] = &nl3;
-
- int i;
- clock_t start = clock(), end;
- for(i = 0; i < 10; ++i){
- run_network(dog, net);
- rotate_image(dog);
- }
- end = clock();
- printf("Ran %lf second per iteration\n", (double)(end-start)/CLOCKS_PER_SEC/10);
-
- show_image_layers(get_network_image(net), "Test Network Layer");
-}
-
-void test_backpropagate()
-{
- int n = 3;
- int size = 4;
- int stride = 10;
- image dog = load_image("dog.jpg");
- show_image(dog, "Test Backpropagate Input");
- image dog_copy = copy_image(dog);
- convolutional_layer cl = *make_convolutional_layer(dog.h, dog.w, dog.c, n, size, stride);
- run_convolutional_layer(dog, cl);
- show_image(cl.output, "Test Backpropagate Output");
- int i;
- clock_t start = clock(), end;
- for(i = 0; i < 100; ++i){
- backpropagate_convolutional_layer(dog_copy, cl);
- }
- end = clock();
- printf("Backpropagate: %lf seconds\n", (double)(end-start)/CLOCKS_PER_SEC);
- start = clock();
- for(i = 0; i < 100; ++i){
- backpropagate_convolutional_layer_convolve(dog, cl);
- }
- end = clock();
- printf("Backpropagate Using Convolutions: %lf seconds\n", (double)(end-start)/CLOCKS_PER_SEC);
- show_image(dog_copy, "Test Backpropagate 1");
- show_image(dog, "Test Backpropagate 2");
- subtract_image(dog, dog_copy);
- show_image(dog, "Test Backpropagate Difference");
-}
-
-void test_ann()
-{
- network net;
- net.n = 3;
- net.layers = calloc(net.n, sizeof(void *));
- net.types = calloc(net.n, sizeof(LAYER_TYPE));
- net.types[0] = CONNECTED;
- net.types[1] = CONNECTED;
- net.types[2] = CONNECTED;
-
- connected_layer nl = *make_connected_layer(1, 20, RELU);
- connected_layer nl2 = *make_connected_layer(20, 20, RELU);
- connected_layer nl3 = *make_connected_layer(20, 1, RELU);
-
- net.layers[0] = &nl;
- net.layers[1] = &nl2;
- net.layers[2] = &nl3;
-
- image t = make_image(1,1,1);
- int count = 0;
-
- double avgerr = 0;
- while(1){
- double v = ((double)rand()/RAND_MAX);
- double truth = v*v;
- set_pixel(t,0,0,0,v);
- run_network(t, net);
- double *out = get_network_output(net);
- double err = pow((out[0]-truth),2.);
- avgerr = .99 * avgerr + .01 * err;
- //if(++count % 100000 == 0) printf("%f\n", avgerr);
- if(++count % 100000 == 0) printf("%f %f :%f AVG %f \n", truth, out[0], err, avgerr);
- out[0] = truth - out[0];
- learn_network(t, net);
- update_network(net, .001);
- }
-
-}
-
void test_parser()
{
- network net = parse_network_cfg("test.cfg");
- image t = make_image(1,1,1);
+ network net = parse_network_cfg("test_parser.cfg");
+ float input[1];
int count = 0;
- double avgerr = 0;
- while(1){
- double v = ((double)rand()/RAND_MAX);
- double truth = v*v;
- set_pixel(t,0,0,0,v);
- run_network(t, net);
- double *out = get_network_output(net);
- double err = pow((out[0]-truth),2.);
+ float avgerr = 0;
+ while(++count < 100000000){
+ float v = ((float)rand()/RAND_MAX);
+ float truth = v*v;
+ input[0] = v;
+ forward_network(net, input);
+ float *out = get_network_output(net);
+ float *delta = get_network_delta(net);
+ float err = pow((out[0]-truth),2.);
avgerr = .99 * avgerr + .01 * err;
- //if(++count % 100000 == 0) printf("%f\n", avgerr);
- if(++count % 100000 == 0) printf("%f %f :%f AVG %f \n", truth, out[0], err, avgerr);
- out[0] = truth - out[0];
- learn_network(t, net);
- update_network(net, .001);
+ if(count % 1000000 == 0) printf("%f %f :%f AVG %f \n", truth, out[0], err, avgerr);
+ delta[0] = truth - out[0];
+ backward_network(net, input, &truth);
+ update_network(net, .001,0,0);
}
}
-int main()
+void test_data()
{
- test_parser();
+ char *labels[] = {"cat","dog"};
+ data train = load_data_image_pathfile_random("train_paths.txt", 101,labels, 2, 300, 400);
+ free_data(train);
+}
+
+void train_full()
+{
+ network net = parse_network_cfg("cfg/imagenet.cfg");
+ srand(2222222);
+ int i = 0;
+ char *labels[] = {"cat","dog"};
+ float lr = .00001;
+ float momentum = .9;
+ float decay = 0.01;
+ 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.);
+ normalize_data_rows(train);
+ clock_t start = clock(), end;
+ float loss = train_network_sgd(net, train, 1000, lr, momentum, decay);
+ 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%10000==0){
+ char buff[256];
+ sprintf(buff, "cfg/assira_backup_%d.cfg", i);
+ save_network(net, buff);
+ }
+ //lr *= .99;
+ }
+}
+
+void test_visualize()
+{
+ network net = parse_network_cfg("cfg/imagenet.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("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);
+ int class = get_predicted_class_network(net);
+ fprintf(fp, "%d\n", class);
+ }
+ free_data(test);
+ }
+ fclose(fp);
+}
+
+void test_cifar10()
+{
+ data test = load_cifar10_data("images/cifar10/test_batch.bin");
+ scale_data_rows(test, 1./255);
+ network net = parse_network_cfg("cfg/cifar10.cfg");
+ int count = 0;
+ float lr = .000005;
+ float momentum = .99;
+ float decay = 0.001;
+ decay = 0;
+ int batch = 10000;
+ while(++count <= 10000){
+ char buff[256];
+ sprintf(buff, "images/cifar10/data_batch_%d.bin", rand()%5+1);
+ data train = load_cifar10_data(buff);
+ scale_data_rows(train, 1./255);
+ train_network_sgd(net, train, batch, lr, momentum, decay);
+ //printf("%5f %5f\n",(double)count*batch/train.X.rows, loss);
+
+ float test_acc = network_accuracy(net, test);
+ printf("%5f %5f\n",(double)count*batch/train.X.rows/5, 1-test_acc);
+ free_data(train);
+ }
+
+}
+
+void test_vince()
+{
+ network net = parse_network_cfg("cfg/vince.cfg");
+ data train = load_categorical_data_csv("images/vince.txt", 144, 2);
+ normalize_data_rows(train);
+
+ int count = 0;
+ float lr = .00005;
+ float momentum = .9;
+ float decay = 0.0001;
+ decay = 0;
+ int batch = 10000;
+ while(++count <= 10000){
+ float loss = train_network_sgd(net, train, batch, lr, momentum, decay);
+ printf("%5f %5f\n",(double)count*batch/train.X.rows, loss);
+ }
+}
+
+void test_nist()
+{
+ srand(444444);
+ srand(888888);
+ network net = parse_network_cfg("cfg/nist_basic.cfg");
+ data train = load_categorical_data_csv("mnist/mnist_train.csv", 0, 10);
+ data test = load_categorical_data_csv("mnist/mnist_test.csv",0,10);
+ normalize_data_rows(train);
+ normalize_data_rows(test);
+ //randomize_data(train);
+ int count = 0;
+ float lr = .00005;
+ float momentum = .9;
+ float decay = 0.0001;
+ decay = 0;
+ //clock_t start = clock(), end;
+ int batch = 10000;
+ while(++count <= 10000){
+ float loss = train_network_sgd(net, train, batch, lr, momentum, decay);
+ printf("%5f %5f\n",(double)count*batch/train.X.rows, loss);
+ //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;
+ /*
+ if(count%5 == 0){
+ float train_acc = network_accuracy(net, train);
+ fprintf(stderr, "\nTRAIN: %f\n", train_acc);
+ float test_acc = network_accuracy(net, test);
+ fprintf(stderr, "TEST: %f\n\n", test_acc);
+ printf("%d, %f, %f\n", count, train_acc, test_acc);
+ //lr *= .5;
+ }
+ */
+ }
+}
+
+void test_ensemble()
+{
+ int i;
+ srand(888888);
+ data d = load_categorical_data_csv("mnist/mnist_train.csv", 0, 10);
+ normalize_data_rows(d);
+ data test = load_categorical_data_csv("mnist/mnist_test.csv", 0,10);
+ normalize_data_rows(test);
+ data train = d;
+ // data *split = split_data(d, 1, 10);
+ // data train = split[0];
+ // data test = split[1];
+ matrix prediction = make_matrix(test.y.rows, test.y.cols);
+ int n = 30;
+ for(i = 0; i < n; ++i){
+ int count = 0;
+ float lr = .0005;
+ float momentum = .9;
+ float decay = .01;
+ network net = parse_network_cfg("nist.cfg");
+ while(++count <= 15){
+ float acc = train_network_sgd(net, train, train.X.rows, lr, momentum, decay);
+ printf("Training Accuracy: %lf Learning Rate: %f Momentum: %f Decay: %f\n", acc, lr, momentum, decay );
+ lr /= 2;
+ }
+ matrix partial = network_predict_data(net, test);
+ float acc = matrix_accuracy(test.y, partial);
+ printf("Model Accuracy: %lf\n", acc);
+ matrix_add_matrix(partial, prediction);
+ acc = matrix_accuracy(test.y, prediction);
+ printf("Current Ensemble Accuracy: %lf\n", acc);
+ free_matrix(partial);
+ }
+ float acc = matrix_accuracy(test.y, prediction);
+ printf("Full Ensemble Accuracy: %lf\n", acc);
+}
+
+void test_random_classify()
+{
+ network net = parse_network_cfg("connected.cfg");
+ matrix m = csv_to_matrix("train.csv");
+ //matrix ho = hold_out_matrix(&m, 2500);
+ float *truth = pop_column(&m, 0);
+ //float *ho_truth = pop_column(&ho, 0);
+ int i;
+ clock_t start = clock(), end;
+ int count = 0;
+ while(++count <= 300){
+ for(i = 0; i < m.rows; ++i){
+ 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]);
+ float *out = get_network_output(net);
+ float *delta = get_network_delta(net);
+ //printf("%f\n", out[0]);
+ delta[0] = truth[index] - out[0];
+ // printf("%f\n", delta[0]);
+ //printf("%f %f\n", truth[index], out[0]);
+ //backward_network(net, m.vals[index], );
+ update_network(net, .00001, 0,0);
+ }
+ //float test_acc = error_network(net, m, truth);
+ //float valid_acc = error_network(net, ho, ho_truth);
+ //printf("%f, %f\n", test_acc, valid_acc);
+ //fprintf(stderr, "%5d: %f Valid: %f\n",count, test_acc, valid_acc);
+ //if(valid_acc > .70) break;
+ }
+ end = clock();
+ FILE *fp = fopen("submission/out.txt", "w");
+ 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]);
+ float *out = get_network_output(net);
+ if(fabs(out[0]) < .5) fprintf(fp, "0\n");
+ else fprintf(fp, "1\n");
+ }
+ fclose(fp);
+ printf("Neural Net Learning: %lf seconds\n", (float)(end-start)/CLOCKS_PER_SEC);
+}
+
+void test_split()
+{
+ data train = load_categorical_data_csv("mnist/mnist_train.csv", 0, 10);
+ data *split = split_data(train, 0, 13);
+ 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, c, h, w, size, stride, matrix);
+ //image render = float_to_image(mh, mw, mc, matrix);
+ }
+}
+
+void train_VOC()
+{
+ 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 = .00001;
+ float momentum = .9;
+ float decay = 0.01;
+ while(i++ < 1000 || 1){
+ data train = load_data_image_pathfile_random("images/VOC2012/val_paths.txt", 1000, labels, 20, 300, 400);
+
+ image im = float_to_image(300, 400, 3,train.X.vals[0]);
+ show_image(im, "input");
+ visualize_network(net);
+ cvWaitKey(100);
+
+ normalize_data_rows(train);
+ clock_t start = clock(), end;
+ float loss = train_network_sgd(net, train, 1000, lr, momentum, decay);
+ 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, "cfg/voc_clean_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);
+ resize_network(net, im.h, im.w, im.c);
+ forward_network(net, im.data);
+ image out = get_network_image_layer(net, 6);
+ free_image(im);
+ cvReleaseImage(&sized);
+ return copy_image(out);
+}
+
+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_features(char *filename)
+{
+ int i,j,k;
+ 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));
+ for(i = 0; i < num; ++i) vizs[i] = make_image(h, w, 3);
+ while(n){
+ char *image_path = (char *)n->val;
+ 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);
+ image out = get_network_image(net);
+
+ int dh = (im.h - h)/h;
+ int dw = (im.w - w)/w;
+ for(i = 0; i < out.h; ++i){
+ for(j = 0; j < out.w; ++j){
+ image sub = get_sub_image(im, dh*i, dw*j, h, w);
+ for(k = 0; k < out.c; ++k){
+ float val = get_pixel(out, i, j, k);
+ //printf("%f, ", val);
+ image sub_c = copy_image(sub);
+ scale_image(sub_c, val);
+ add_into_image(sub_c, vizs[k], 0, 0);
+ free_image(sub_c);
+ }
+ free_image(sub);
+ }
+ }
+ //printf("\n");
+ show_images(vizs, 10, "IMAGENET Visualization");
+ cvWaitKey(1000);
+ n = n->next;
+ }
+ cvWaitKey(0);
+}
+
+void features_VOC_image(char *image_file, char *image_dir, char *out_dir)
+{
+ int i,j;
+ network net = parse_network_cfg("cfg/voc_imagenet.cfg");
+ char image_path[1024];
+ sprintf(image_path, "%s/%s",image_dir, image_file);
+ char out_path[1024];
+ sprintf(out_path, "%s/%s.txt",out_dir, image_file);
+ printf("%s\n", image_file);
+ FILE *fp = fopen(out_path, "w");
+ if(fp == 0) file_error(out_path);
+
+ IplImage* src = 0;
+ if( (src = cvLoadImage(image_path,-1)) == 0 ) file_error(image_path);
+ int w = src->width;
+ int h = src->height;
+ int sbin = 8;
+ int interval = 4;
+ double scale = pow(2., 1./interval);
+ int m = (w<h)?w:h;
+ int max_scale = 1+floor((double)log((double)m/(5.*sbin))/log(scale));
+ if(max_scale < interval) error("max_scale must be >= interval");
+ image *ims = calloc(max_scale+interval, sizeof(image));
+
+ for(i = 0; i < interval; ++i){
+ double factor = 1./pow(scale, i);
+ double ih = round(h*factor);
+ double iw = round(w*factor);
+ int ex_h = round(ih/4.) - 2;
+ int ex_w = round(iw/4.) - 2;
+ ims[i] = features_output_size(net, src, ex_h, ex_w);
+
+ ih = round(h*factor);
+ iw = round(w*factor);
+ ex_h = round(ih/8.) - 2;
+ ex_w = round(iw/8.) - 2;
+ ims[i+interval] = features_output_size(net, src, ex_h, ex_w);
+ for(j = i+interval; j < max_scale; j += interval){
+ factor /= 2.;
+ ih = round(h*factor);
+ iw = round(w*factor);
+ ex_h = round(ih/8.) - 2;
+ ex_w = round(iw/8.) - 2;
+ ims[j+interval] = features_output_size(net, src, ex_h, ex_w);
+ }
+ }
+ for(i = 0; i < max_scale+interval; ++i){
+ image out = ims[i];
+ fprintf(fp, "%d, %d, %d\n",out.c, out.h, out.w);
+ for(j = 0; j < out.c*out.h*out.w; ++j){
+ if(j != 0)fprintf(fp, ",");
+ fprintf(fp, "%g", out.data[j]);
+ }
+ fprintf(fp, "\n");
+ free_image(out);
+ }
+ free(ims);
+ fclose(fp);
+ cvReleaseImage(&src);
+}
+
+void test_distribution()
+{
+ IplImage* img = 0;
+ if( (img = cvLoadImage("im_small.jpg",-1)) == 0 ) file_error("im_small.jpg");
+ network net = parse_network_cfg("cfg/voc_features.cfg");
+ int h = img->height/8-2;
+ int w = img->width/8-2;
+ image out = features_output_size(net, img, h, w);
+ int c = out.c;
+ out.c = 1;
+ show_image(out, "output");
+ out.c = c;
+ image input = ipl_to_image(img);
+ show_image(input, "input");
+ CvScalar s;
+ int i,j;
+ image affects = make_image(input.h, input.w, 1);
+ int count = 0;
+ for(i = 0; i<img->height; i += 1){
+ for(j = 0; j < img->width; j += 1){
+ IplImage *copy = cvCloneImage(img);
+ s=cvGet2D(copy,i,j); // get the (i,j) pixel value
+ printf("%d/%d\n", count++, img->height*img->width);
+ s.val[0]=0;
+ s.val[1]=0;
+ s.val[2]=0;
+ cvSet2D(copy,i,j,s); // set the (i,j) pixel value
+ image mod = features_output_size(net, copy, h, w);
+ image dist = image_distance(out, mod);
+ show_image(affects, "affects");
+ cvWaitKey(1);
+ cvReleaseImage(©);
+ //affects.data[i*affects.w + j] += dist.data[3*dist.w+5];
+ affects.data[i*affects.w + j] += dist.data[1*dist.w+1];
+ free_image(mod);
+ free_image(dist);
+ }
+ }
+ show_image(affects, "Origins");
+ cvWaitKey(0);
+ cvWaitKey(0);
+}
+
+
+int main(int argc, char *argv[])
+{
+ //train_full();
+ //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();
+ //test_cifar10();
+ //test_vince();
+ //test_full();
+ //train_VOC();
+ //features_VOC_image(argv[1], argv[2], argv[3]);
+ //features_VOC_image_size(argv[1], atoi(argv[2]), atoi(argv[3]));
+ //visualize_imagenet_features("data/assira/train.list");
+ visualize_imagenet_features("data/VOC2011.list");
+ fprintf(stderr, "Success!\n");
+ //test_random_preprocess();
+ //test_random_classify();
+ //test_parser();
//test_backpropagate();
//test_ann();
//test_convolve();
@@ -260,7 +706,8 @@
//test_load();
//test_network();
//test_convolutional_layer();
+ //verify_convolutional_layer();
//test_color();
- cvWaitKey(0);
+ //cvWaitKey(0);
return 0;
}
--
Gitblit v1.10.0