From ace5aeb0f59fdceb99e607af9780added20da37c Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Fri, 24 Jan 2014 22:51:17 +0000
Subject: [PATCH] MNIST connected network showing off matrices

---
 src/tests.c |  292 ++++++++++++++++++++++++++++++++++-----------------------
 1 files changed, 174 insertions(+), 118 deletions(-)

diff --git a/src/tests.c b/src/tests.c
index 722de1a..c459a36 100644
--- a/src/tests.c
+++ b/src/tests.c
@@ -7,6 +7,7 @@
 #include "data.h"
 #include "matrix.h"
 #include "utils.h"
+#include "mini_blas.h"
 
 #include <time.h>
 #include <stdlib.h>
@@ -15,7 +16,6 @@
 void test_convolve()
 {
     image dog = load_image("dog.jpg");
-    //show_image_layers(dog, "Dog");
     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);
@@ -29,6 +29,35 @@
     show_image_layers(edge, "Test Convolve");
 }
 
+void test_convolve_matrix()
+{
+    image dog = load_image("dog.jpg");
+    printf("dog channels %d\n", dog.c);
+    
+    int size = 11;
+    int stride = 1;
+    int n = 40;
+    double *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);
+    double *matrix = calloc(mh*mw, sizeof(double));
+
+    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", (double)(end-start)/CLOCKS_PER_SEC);
+    show_image_layers(edge, "Test Convolve");
+    cvWaitKey(0);
+}
+
 void test_color()
 {
     image dog = load_image("test_color.png");
@@ -88,7 +117,7 @@
     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_layer2(layer, test.data, in_delta.data);
+        backward_convolutional_layer(layer, test.data, in_delta.data);
         image partial = copy_image(in_delta);
         jacobian2[i] = partial.data;
         out_delta.data[i] = 0;
@@ -156,7 +185,7 @@
     int count = 0;
         
     double avgerr = 0;
-    while(1){
+    while(++count < 100000000){
         double v = ((double)rand()/RAND_MAX);
         double truth = v*v;
         input[0] = v;
@@ -165,22 +194,18 @@
         double *delta = get_network_delta(net);
         double err = pow((out[0]-truth),2.);
         avgerr = .99 * avgerr + .01 * err;
-        //if(++count % 100000 == 0) printf("%f\n", avgerr);
-        if(++count % 1000000 == 0) printf("%f %f :%f AVG %f \n", truth, out[0], err, avgerr);
+        if(count % 1000000 == 0) printf("%f %f :%f AVG %f \n", truth, out[0], err, avgerr);
         delta[0] = truth - out[0];
-        learn_network(net, input);
-        update_network(net, .001);
+        backward_network(net, input, &truth);
+        update_network(net, .001,0,0);
     }
 }
 
 void test_data()
 {
     char *labels[] = {"cat","dog"};
-    batch train = random_batch("train_paths.txt", 101,labels, 2);
-    show_image(train.images[0], "Test Data Loading");
-    show_image(train.images[100], "Test Data Loading");
-    show_image(train.images[10], "Test Data Loading");
-    free_batch(train);
+    data train = load_data_image_pathfile_random("train_paths.txt", 101,labels, 2);
+    free_data(train);
 }
 
 void test_full()
@@ -189,90 +214,88 @@
     srand(0);
     int i = 0;
     char *labels[] = {"cat","dog"};
+    double lr = .00001;
+    double momentum = .9;
+    double decay = 0.01;
     while(i++ < 1000 || 1){
-        batch train = random_batch("train_paths.txt", 1000, labels, 2);
-        train_network_batch(net, train);
-        free_batch(train);
+        data train = load_data_image_pathfile_random("train_paths.txt", 1000, labels, 2);
+        train_network(net, train, lr, momentum, decay);
+        free_data(train);
         printf("Round %d\n", i);
     }
 }
 
-double error_network(network net, matrix m, double *truth)
-{
-    int i;
-    int correct = 0;
-    for(i = 0; i < m.rows; ++i){
-        forward_network(net, m.vals[i]);
-        double *out = get_network_output(net);
-        double err = truth[i] - out[0];
-        if(fabs(err) < .5) ++correct;
-    }
-    return (double)correct/m.rows;
-}
-
-double **one_hot(double *a, int n, int k)
-{
-    int i;
-    double **t = calloc(n, sizeof(double*));
-    for(i = 0; i < n; ++i){
-        t[i] = calloc(k, sizeof(double));
-        int index = (int)a[i];
-        t[i][index] = 1;
-    }
-    return t;
-}
-
 void test_nist()
 {
-    network net = parse_network_cfg("nist.cfg");
-    matrix m = csv_to_matrix("images/nist_train.csv");
-    matrix ho = hold_out_matrix(&m, 3000);
-    double *truth_1d = pop_column(&m, 0);
-    double **truth = one_hot(truth_1d, m.rows, 10);
-    double *ho_truth_1d = pop_column(&ho, 0);
-    double **ho_truth = one_hot(ho_truth_1d, ho.rows, 10);
-    int i,j;
-    clock_t start = clock(), end;
+    srand(444444);
+    srand(888888);
+    network net = parse_network_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;
-    double lr = .0001;
-    while(++count <= 3000000){
-        //lr *= .99;
-        int index = 0;
-        int correct = 0;
-        for(i = 0; i < 1000; ++i){
-            index = rand()%m.rows;
-            normalize_array(m.vals[index], 28*28);
-            forward_network(net, m.vals[index]);
-            double *out = get_network_output(net);
-            double *delta = get_network_delta(net);
-            int max_i = 0;
-            double max = out[0];
-            for(j = 0; j < 10; ++j){
-                delta[j] = truth[index][j]-out[j];
-                if(out[j] > max){
-                    max = out[j];
-                    max_i = j;
-                }
-            }
-            if(truth[index][max_i]) ++correct;
-            learn_network(net, m.vals[index]);
-            update_network(net, lr);
+    double lr = .0005;
+    double momentum = .9;
+    double decay = 0.01;
+    clock_t start = clock(), end;
+    while(++count <= 1000){
+        double acc = train_network_sgd(net, train, 6400, lr, momentum, decay);
+        printf("%5d Training Loss: %lf, Params: %f %f %f, ",count*100, 1.-acc, lr, momentum, decay);
+        end = clock();
+        printf("Time: %lf seconds\n", (double)(end-start)/CLOCKS_PER_SEC);
+        start=end;
+        //visualize_network(net);
+        //cvWaitKey(100);
+        //lr /= 2; 
+        if(count%5 == 0 && 0){
+            double train_acc = network_accuracy(net, train);
+            fprintf(stderr, "\nTRAIN: %f\n", train_acc);
+            double test_acc = network_accuracy(net, test);
+            fprintf(stderr, "TEST: %f\n\n", test_acc);
+            printf("%d, %f, %f\n", count, train_acc, test_acc);
         }
-        print_network(net);
-        image input = double_to_image(28,28,1, m.vals[index]);
-        show_image(input, "Input");
-        image o = get_network_image(net);
-        show_image_collapsed(o, "Output");
-        visualize_network(net);
-        cvWaitKey(100);
-        //double test_acc = error_network(net, m, truth);
-        //double valid_acc = error_network(net, ho, ho_truth);
-        //printf("%f, %f\n", test_acc, valid_acc);
-        fprintf(stderr, "%5d: %f %f\n",count, (double)correct/1000, lr);
-        //if(valid_acc > .70) break;
     }
-    end = clock();
-    printf("Neural Net Learning: %lf seconds\n", (double)(end-start)/CLOCKS_PER_SEC);
+}
+
+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;
+        double lr = .0005;
+        double momentum = .9;
+        double decay = .01;
+        network net = parse_network_cfg("nist.cfg");
+        while(++count <= 15){
+            double 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);
+        double 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);
+    }
+    double acc = matrix_accuracy(test.y, prediction);
+    printf("Full Ensemble Accuracy: %lf\n", acc);
 }
 
 void test_kernel_update()
@@ -281,23 +304,23 @@
     double delta[] = {.1};
     double input[] = {.3, .5, .3, .5, .5, .5, .5, .0, .5};
     double kernel[] = {1,2,3,4,5,6,7,8,9};
-    convolutional_layer layer = *make_convolutional_layer(3, 3, 1, 1, 3, 1, IDENTITY);
+    convolutional_layer layer = *make_convolutional_layer(3, 3, 1, 1, 3, 1, LINEAR);
     layer.kernels[0].data = kernel;
     layer.delta = delta;
     learn_convolutional_layer(layer, input);
     print_image(layer.kernels[0]);
     print_image(get_convolutional_delta(layer));
     print_image(layer.kernel_updates[0]);
-    
+
 }
 
 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);
+    //matrix ho = hold_out_matrix(&m, 2500);
     double *truth = pop_column(&m, 0);
-    double *ho_truth = pop_column(&ho, 0);
+    //double *ho_truth = pop_column(&ho, 0);
     int i;
     clock_t start = clock(), end;
     int count = 0;
@@ -311,15 +334,15 @@
             double *delta = get_network_delta(net);
             //printf("%f\n", out[0]);
             delta[0] = truth[index] - out[0];
-           // printf("%f\n", delta[0]);
+            // printf("%f\n", delta[0]);
             //printf("%f %f\n", truth[index], out[0]);
-            learn_network(net, m.vals[index]);
-            update_network(net, .00001);
+            //backward_network(net, m.vals[index], );
+            update_network(net, .00001, 0,0);
         }
-        double test_acc = error_network(net, m, truth);
-        double 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);
+        //double test_acc = error_network(net, m, truth);
+        //double 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();
@@ -336,34 +359,67 @@
     printf("Neural Net Learning: %lf seconds\n", (double)(end-start)/CLOCKS_PER_SEC);
 }
 
-void test_random_preprocess()
+void test_split()
 {
-    FILE *file = fopen("train.csv", "w");
-    char *labels[] = {"cat","dog"};
-    int i,j,k;
-    srand(0);
-    network net = parse_network_cfg("convolutional.cfg");
-    for(i = 0; i < 100; ++i){
-        printf("%d\n", i);
-        batch part = get_batch("train_paths.txt", i, 100, labels, 2);
-        for(j = 0; j < part.n; ++j){
-            forward_network(net, part.images[j].data);
-            double *out = get_network_output(net);
-            fprintf(file, "%f", part.truth[j][0]);
-            for(k = 0; k < get_network_output_size(net); ++k){
-                fprintf(file, ",%f", out[k]);
-            }
-            fprintf(file, "\n");
+    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);
+}
+
+double *random_matrix(int rows, int cols)
+{
+    int i, j;
+    double *m = calloc(rows*cols, sizeof(double));
+    for(i = 0; i < rows; ++i){
+        for(j = 0; j < cols; ++j){
+            m[i*cols+j] = (double)rand()/RAND_MAX;
         }
-        free_batch(part);
+    }
+    return m;
+}
+
+void test_blas()
+{
+    int m = 6025, n = 20, k = 11*11*3;
+    double *a = random_matrix(m,k);
+    double *b = random_matrix(k,n);
+    double *c = random_matrix(m,n);
+    int i;
+    for(i = 0; i<1000; ++i){
+        gemm(0,0,m,n,k,1,a,k,b,n,1,c,n);
+    }
+}
+
+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;
+    double *matrix = calloc(msize, sizeof(double));
+    int i;
+    for(i = 0; i < 1000; ++i){
+    im2col_cpu(test.data,  c,  h,  w,  size,  stride, matrix);
+    image render = double_to_image(mh, mw, mc, matrix);
     }
 }
 
 int main()
 {
+    //test_blas();
+ //test_convolve_matrix();
+//    test_im2row();
     //test_kernel_update();
-    //test_nist();
-    test_full();
+    //test_split();
+    //test_ensemble();
+    test_nist();
+    //test_full();
     //test_random_preprocess();
     //test_random_classify();
     //test_parser();
@@ -377,6 +433,6 @@
     //test_convolutional_layer();
     //verify_convolutional_layer();
     //test_color();
-    cvWaitKey(0);
+    //cvWaitKey(0);
     return 0;
 }

--
Gitblit v1.10.0