From 796e464d43274415603e6f27a4bb81b6c1ef8cf3 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Fri, 24 Jan 2014 22:49:02 +0000
Subject: [PATCH] Connected layers use matrices

---
 src/tests.c |  164 ++++++++++++++++++++++++++++++++++++++++++++++++------
 1 files changed, 145 insertions(+), 19 deletions(-)

diff --git a/src/tests.c b/src/tests.c
index d7d9389..ce131e7 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>
@@ -28,6 +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");
@@ -184,9 +214,12 @@
     srand(0);
     int i = 0;
     char *labels[] = {"cat","dog"};
+    double lr = .00001;
+    double momentum = .9;
+    double decay = 0.01;
     while(i++ < 1000 || 1){
         data train = load_data_image_pathfile_random("train_paths.txt", 1000, labels, 2);
-        train_network(net, train, .0005, 0, 0);
+        train_network(net, train, lr, momentum, decay);
         free_data(train);
         printf("Round %d\n", i);
     }
@@ -195,28 +228,74 @@
 void test_nist()
 {
     srand(444444);
-    network net = parse_network_cfg("nist.cfg");
+    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);
+    //randomize_data(train);
     int count = 0;
     double lr = .0005;
-    while(++count <= 1){
-        double acc = train_network_sgd(net, train, lr, .9, .001);
-        printf("Training Accuracy: %lf", acc);
-        lr /= 2; 
+    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);
+        }
     }
+}
+
+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;
     /*
-    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);
-    */
-    //end = clock();
-    //printf("Neural Net Learning: %lf seconds\n", (double)(end-start)/CLOCKS_PER_SEC);
+       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()
@@ -283,16 +362,63 @@
 void test_split()
 {
     data train = load_categorical_data_csv("mnist/mnist_train.csv", 0, 10);
-    data *split = cv_split_data(train, 0, 13);
+    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;
+        }
+    }
+    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_split();
-   // test_nist();
+    //test_split();
+    //test_ensemble();
+    //test_nist();
     //test_full();
     //test_random_preprocess();
     //test_random_classify();
@@ -307,6 +433,6 @@
     //test_convolutional_layer();
     //verify_convolutional_layer();
     //test_color();
-    cvWaitKey(0);
+    //cvWaitKey(0);
     return 0;
 }

--
Gitblit v1.10.0