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 |  374 +++++++++++++++++++++++++++++++++++++++++++++++------
 1 files changed, 331 insertions(+), 43 deletions(-)

diff --git a/src/tests.c b/src/tests.c
index 09ec7b2..5d9136d 100644
--- a/src/tests.c
+++ b/src/tests.c
@@ -77,7 +77,7 @@
     int size = 3;
     float eps = .00000001;
     image test = make_random_image(5,5, 1);
-    convolutional_layer layer = *make_convolutional_layer(test.h,test.w,test.c, n, size, stride, RELU);
+    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));
     
@@ -188,70 +188,151 @@
     free_data(train);
 }
 
-void test_full()
+void train_full()
 {
-    network net = parse_network_cfg("full.cfg");
+    network net = parse_network_cfg("cfg/imagenet.cfg");
     srand(2222222);
-    int i = 800;
+    int i = 0;
     char *labels[] = {"cat","dog"};
     float lr = .00001;
     float momentum = .9;
     float decay = 0.01;
-    while(i++ < 1000 || 1){
-        visualize_network(net);
-        cvWaitKey(100);
-        data train = load_data_image_pathfile_random("train_paths.txt", 1000, labels, 2, 256, 256);
-        image im = float_to_image(256, 256, 3,train.X.vals[0]);
-        show_image(im, "input");
-        cvWaitKey(100);
+    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, 100, lr, momentum, decay);
+        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%100==0){
+        if(i%10000==0){
             char buff[256];
-            sprintf(buff, "backup_%d.cfg", i);
-            //save_network(net, buff);
+            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("nist.cfg");
+    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 = .0005;
+    float lr = .00005;
     float momentum = .9;
-    float decay = 0.001;
-    clock_t start = clock(), end;
-    while(++count <= 100){
-        //visualize_network(net);
-        float loss = train_network_sgd(net, train, 1000, lr, momentum, decay);
-        printf("%5d Training Loss: %lf, Params: %f %f %f, ",count*100, loss, lr, momentum, decay);
-        end = clock();
-        printf("Time: %lf seconds\n", (float)(end-start)/CLOCKS_PER_SEC);
-        start=end;
-        //cvWaitKey(100);
-        //lr /= 2; 
-        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;
+    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;
         }
+         */
     }
 }
 
@@ -366,20 +447,21 @@
 
 void train_VOC()
 {
-    network net = parse_network_cfg("cfg/voc_backup_ramp_80.cfg");
+    network net = parse_network_cfg("cfg/voc_start.cfg");
     srand(2222222);
-    int i = 0;
+    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){
-        visualize_network(net);
-        cvWaitKey(100);
-        data train = load_data_image_pathfile_random("images/VOC2012/train_paths.txt", 1000, labels, 20, 300, 400);
+        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);
@@ -388,25 +470,231 @@
         free_data(train);
         if(i%10==0){
             char buff[256];
-            sprintf(buff, "cfg/voc_backup_ramp_%d.cfg", i);
+            sprintf(buff, "cfg/voc_clean_ramp_%d.cfg", i);
             save_network(net, buff);
         }
         //lr *= .99;
     }
 }
 
-int main()
+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(&copy);
+            //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();
+    //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();

--
Gitblit v1.10.0