mirror/darknet
1
0
Fork 0
mirror of https://github.com/pjreddie/darknet.git synced 2023-08-10 21:13:14 +03:00
Code Issues Projects Releases Wiki Activity

CSE546 submission

Browse Source
This commit is contained in:
Joseph Redmon 2013-12-10 10:30:42 -08:00
parent 8c3694bc91
commit ad9dbfe164
4 changed files with 31 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
nist.cfg
View File

@ -2,7 +2,7 @@
width=28
height=28
channels=1
filters=6
filters=5
size=5
stride=1
activation=ramp
@ -11,7 +11,7 @@ activation=ramp
stride=2
[conv]
filters=16
filters=50
size=5
stride=1
activation=ramp
@ -19,17 +19,8 @@ activation=ramp
[maxpool]
stride=2
[conv]
filters=120
size=3
stride=1
activation=ramp
[maxpool]
stride=2
[conn]
output = 80
output = 100
activation=ramp
[conn]

2
src/convolutional_layer.c
View File

@ -39,7 +39,7 @@ convolutional_layer *make_convolutional_layer(int h, int w, int c, int n, int si
layer->w = w;
layer->c = c;
layer->n = n;
layer->edge = 1;
layer->edge = 0;
layer->stride = stride;
layer->kernels = calloc(n, sizeof(image));
layer->kernel_updates = calloc(n, sizeof(image));

2
src/network.c
View File

@ -63,7 +63,7 @@ void update_network(network net, double step, double momentum, double decay)
}
else if(net.types[i] == CONNECTED){
connected_layer layer = *(connected_layer *)net.layers[i];
update_connected_layer(layer, step, momentum, decay);
update_connected_layer(layer, step, momentum, 0);
}
}
}

46
src/tests.c
View File

@ -195,26 +195,31 @@ void test_full()
void test_nist()
{
srand(444444);
srand(888888);
network net = parse_network_cfg("nist.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, 10000, lr, .9, .001);
printf("Training Accuracy: %lf\n", acc);
lr /= 2;
double momentum = .9;
double decay = 0.01;
while(++count <= 1000){
double acc = train_network_sgd(net, train, 1000, lr, momentum, decay);
printf("Training Accuracy: %lf, Params: %f %f %f\n", acc, lr, momentum, decay);
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);
}
}
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);
}
void test_ensemble()
@ -223,24 +228,25 @@ void test_ensemble()
srand(888888);
data d = load_categorical_data_csv("mnist/mnist_train.csv", 0, 10);
normalize_data_rows(d);
randomize_data(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];
*/
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 <= 5){
double acc = train_network_sgd(net, train, train.X.rows, lr, .9, .001);
printf("Training Accuracy: %lf\n", acc);
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);