Skip to content

Commit

Permalink
Go
Browse files Browse the repository at this point in the history
  • Loading branch information
@pjreddie
pjreddie committed Mar 14, 2016
1 parent 16d06ec commit d1965bd
Show file tree
Hide file tree
Showing 21 changed files with 1,455 additions and 710 deletions.
10 changes: 5 additions & 5 deletions Makefile
View file
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
GPU=1
OPENCV=1
GPU=0
OPENCV=0
DEBUG=0

ARCH= --gpu-architecture=compute_20 --gpu-code=compute_20
ARCH= --gpu-architecture=compute_20 --gpu-code=compute_20

VPATH=./src/
EXEC=darknet
Expand Down Expand Up @@ -34,9 +34,9 @@ CFLAGS+= -DGPU
LDFLAGS+= -L/usr/local/cuda/lib64 -lcuda -lcudart -lcublas -lcurand
endif

OBJ=gemm.o utils.o cuda.o deconvolutional_layer.o convolutional_layer.o list.o image.o activations.o im2col.o col2im.o blas.o crop_layer.o dropout_layer.o maxpool_layer.o softmax_layer.o data.o matrix.o network.o connected_layer.o cost_layer.o parser.o option_list.o darknet.o detection_layer.o imagenet.o captcha.o route_layer.o writing.o box.o nightmare.o normalization_layer.o avgpool_layer.o coco.o dice.o yolo.o layer.o compare.o classifier.o local_layer.o swag.o shortcut_layer.o activation_layer.o rnn_layer.o rnn.o rnn_vid.o crnn_layer.o coco_demo.o tag.o cifar.o
OBJ=gemm.o utils.o cuda.o deconvolutional_layer.o convolutional_layer.o list.o image.o activations.o im2col.o col2im.o blas.o crop_layer.o dropout_layer.o maxpool_layer.o softmax_layer.o data.o matrix.o network.o connected_layer.o cost_layer.o parser.o option_list.o darknet.o detection_layer.o imagenet.o captcha.o route_layer.o writing.o box.o nightmare.o normalization_layer.o avgpool_layer.o coco.o dice.o yolo.o layer.o compare.o classifier.o local_layer.o swag.o shortcut_layer.o activation_layer.o rnn_layer.o rnn.o rnn_vid.o crnn_layer.o coco_demo.o tag.o cifar.o yolo_demo.o go.o
ifeq ($(GPU), 1)
OBJ+=convolutional_kernels.o deconvolutional_kernels.o activation_kernels.o im2col_kernels.o col2im_kernels.o blas_kernels.o crop_layer_kernels.o dropout_layer_kernels.o maxpool_layer_kernels.o softmax_layer_kernels.o network_kernels.o avgpool_layer_kernels.o yolo_kernels.o
OBJ+=convolutional_kernels.o deconvolutional_kernels.o activation_kernels.o im2col_kernels.o col2im_kernels.o blas_kernels.o crop_layer_kernels.o dropout_layer_kernels.o maxpool_layer_kernels.o softmax_layer_kernels.o network_kernels.o avgpool_layer_kernels.o
endif

OBJS = $(addprefix $(OBJDIR), $(OBJ))
Expand Down
67 changes: 67 additions & 0 deletions cfg/go.test.cfg
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,67 @@
[net]
batch=1
subdivisions=1
height=19
width=19
channels=1
momentum=0.9
decay=0.0005

learning_rate=0.1
max_batches = 0
policy=steps
steps=50000, 90000
scales=.1, .1

[convolutional]
filters=256
size=3
stride=1
pad=1
activation=leaky
batch_normalize=1

[convolutional]
filters=256
size=3
stride=1
pad=1
activation=leaky
batch_normalize=1

[convolutional]
filters=256
size=3
stride=1
pad=1
activation=leaky
batch_normalize=1

[convolutional]
filters=256
size=3
stride=1
pad=1
activation=leaky
batch_normalize=1

[convolutional]
filters=256
size=3
stride=1
pad=1
activation=leaky
batch_normalize=1

[convolutional]
filters=1
size=1
stride=1
pad=1
activation=leaky

[softmax]

[cost]
type=sse

4 changes: 2 additions & 2 deletions src/blas.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@ void mean_cpu(float *x, int batch, int filters, int spatial, float *mean)

void variance_cpu(float *x, float *mean, int batch, int filters, int spatial, float *variance)
{
float scale = 1./(batch * spatial);
float scale = 1./(batch * spatial - 1);
int i,j,k;
for(i = 0; i < filters; ++i){
variance[i] = 0;
Expand All @@ -67,7 +67,7 @@ void normalize_cpu(float *x, float *mean, float *variance, int batch, int filter
for(f = 0; f < filters; ++f){
for(i = 0; i < spatial; ++i){
int index = b*filters*spatial + f*spatial + i;
x[index] = (x[index] - mean[f])/(sqrt(variance[f]) + .00001f);
x[index] = (x[index] - mean[f])/(sqrt(variance[f]) + .000001f);
}
}
}
Expand Down
16 changes: 8 additions & 8 deletions src/blas_kernels.cu
View file
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ __global__ void normalize_kernel(int N, float *x, float *mean, float *variance,
if (index >= N) return;
int f = (index/spatial)%filters;

x[index] = (x[index] - mean[f])/(sqrt(variance[f]) + .00001f);
x[index] = (x[index] - mean[f])/(sqrt(variance[f]) + .000001f);
}

__global__ void normalize_delta_kernel(int N, float *x, float *mean, float *variance, float *mean_delta, float *variance_delta, int batch, int filters, int spatial, float *delta)
Expand All @@ -24,7 +24,7 @@ __global__ void normalize_delta_kernel(int N, float *x, float *mean, float *vari
if (index >= N) return;
int f = (index/spatial)%filters;

delta[index] = delta[index] * 1./(sqrt(variance[f]) + .00001f) + variance_delta[f] * 2. * (x[index] - mean[f]) / (spatial * batch) + mean_delta[f]/(spatial*batch);
delta[index] = delta[index] * 1./(sqrt(variance[f]) + .000001f) + variance_delta[f] * 2. * (x[index] - mean[f]) / (spatial * batch) + mean_delta[f]/(spatial*batch);
}

extern "C" void normalize_delta_gpu(float *x, float *mean, float *variance, float *mean_delta, float *variance_delta, int batch, int filters, int spatial, float *delta)
Expand All @@ -46,7 +46,7 @@ __global__ void variance_delta_kernel(float *x, float *delta, float *mean, floa
variance_delta[i] += delta[index]*(x[index] - mean[i]);
}
}
variance_delta[i] *= -.5 * pow(variance[i] + .00001f, (float)(-3./2.));
variance_delta[i] *= -.5 * pow(variance[i] + .000001f, (float)(-3./2.));
}

__global__ void accumulate_kernel(float *x, int n, int groups, float *sum)
Expand Down Expand Up @@ -83,7 +83,7 @@ __global__ void fast_mean_delta_kernel(float *delta, float *variance, int batch,
for(i = 0; i < threads; ++i){
mean_delta[filter] += local[i];
}
mean_delta[filter] *= (-1./sqrt(variance[filter] + .00001f));
mean_delta[filter] *= (-1./sqrt(variance[filter] + .000001f));
}
}

Expand Down Expand Up @@ -111,7 +111,7 @@ __global__ void fast_variance_delta_kernel(float *x, float *delta, float *mean,
for(i = 0; i < threads; ++i){
variance_delta[filter] += local[i];
}
variance_delta[filter] *= -.5 * pow(variance[filter] + .00001f, (float)(-3./2.));
variance_delta[filter] *= -.5 * pow(variance[filter] + .000001f, (float)(-3./2.));
}
}

Expand All @@ -128,7 +128,7 @@ __global__ void mean_delta_kernel(float *delta, float *variance, int batch, int
mean_delta[i] += delta[index];
}
}
mean_delta[i] *= (-1./sqrt(variance[i] + .00001f));
mean_delta[i] *= (-1./sqrt(variance[i] + .000001f));
}

extern "C" void mean_delta_gpu(float *delta, float *variance, int batch, int filters, int spatial, float *mean_delta)
Expand Down Expand Up @@ -167,7 +167,7 @@ __global__ void mean_kernel(float *x, int batch, int filters, int spatial, floa

__global__ void variance_kernel(float *x, float *mean, int batch, int filters, int spatial, float *variance)
{
float scale = 1./(batch * spatial);
float scale = 1./(batch * spatial - 1);
int j,k;
int i = (blockIdx.x + blockIdx.y*gridDim.x) * blockDim.x + threadIdx.x;
if (i >= filters) return;
Expand Down Expand Up @@ -288,7 +288,7 @@ __global__ void fast_variance_kernel(float *x, float *mean, int batch, int filt
for(i = 0; i < threads; ++i){
variance[filter] += local[i];
}
variance[filter] /= spatial * batch;
variance[filter] /= (spatial * batch - 1);
}
}

Expand Down
163 changes: 162 additions & 1 deletion src/cifar.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@ void train_cifar(char *cfgfile, char *weightfile)

float loss = train_network_sgd(net, train, 1);
if(avg_loss == -1) avg_loss = loss;
avg_loss = avg_loss*.9 + loss*.1;
avg_loss = avg_loss*.95 + loss*.05;
printf("%d, %.3f: %f, %f avg, %f rate, %lf seconds, %d images\n", get_current_batch(net), (float)(*net.seen)/N, loss, avg_loss, get_current_rate(net), sec(clock()-time), *net.seen);
if(*net.seen/N > epoch){
epoch = *net.seen/N;
Expand All @@ -57,6 +57,95 @@ void train_cifar(char *cfgfile, char *weightfile)
free_data(train);
}

void train_cifar_distill(char *cfgfile, char *weightfile)
{
data_seed = time(0);
srand(time(0));
float avg_loss = -1;
char *base = basecfg(cfgfile);
printf("%s\n", base);
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);

char *backup_directory = "/home/pjreddie/backup/";
int classes = 10;
int N = 50000;

char **labels = get_labels("data/cifar/labels.txt");
int epoch = (*net.seen)/N;

data train = load_all_cifar10();
matrix soft = csv_to_matrix("results/ensemble.csv");

float weight = .9;
scale_matrix(soft, weight);
scale_matrix(train.y, 1. - weight);
matrix_add_matrix(soft, train.y);

while(get_current_batch(net) < net.max_batches || net.max_batches == 0){
clock_t time=clock();

float loss = train_network_sgd(net, train, 1);
if(avg_loss == -1) avg_loss = loss;
avg_loss = avg_loss*.95 + loss*.05;
printf("%d, %.3f: %f, %f avg, %f rate, %lf seconds, %d images\n", get_current_batch(net), (float)(*net.seen)/N, loss, avg_loss, get_current_rate(net), sec(clock()-time), *net.seen);
if(*net.seen/N > epoch){
epoch = *net.seen/N;
char buff[256];
sprintf(buff, "%s/%s_%d.weights",backup_directory,base, epoch);
save_weights(net, buff);
}
if(get_current_batch(net)%100 == 0){
char buff[256];
sprintf(buff, "%s/%s.backup",backup_directory,base);
save_weights(net, buff);
}
}
char buff[256];
sprintf(buff, "%s/%s.weights", backup_directory, base);
save_weights(net, buff);

free_network(net);
free_ptrs((void**)labels, classes);
free(base);
free_data(train);
}

void test_cifar_multi(char *filename, char *weightfile)
{
network net = parse_network_cfg(filename);
if(weightfile){
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
srand(time(0));

float avg_acc = 0;
data test = load_cifar10_data("data/cifar/cifar-10-batches-bin/test_batch.bin");

int i;
for(i = 0; i < test.X.rows; ++i){
image im = float_to_image(32, 32, 3, test.X.vals[i]);

float pred[10] = {0};

float *p = network_predict(net, im.data);
axpy_cpu(10, 1, p, 1, pred, 1);
flip_image(im);
p = network_predict(net, im.data);
axpy_cpu(10, 1, p, 1, pred, 1);

int index = max_index(pred, 10);
int class = max_index(test.y.vals[i], 10);
if(index == class) avg_acc += 1;
free_image(im);
printf("%4d: %.2f%%\n", i, 100.*avg_acc/(i+1));
}
}

void test_cifar(char *filename, char *weightfile)
{
network net = parse_network_cfg(filename);
Expand All @@ -79,6 +168,73 @@ void test_cifar(char *filename, char *weightfile)
free_data(test);
}

void test_cifar_csv(char *filename, char *weightfile)
{
network net = parse_network_cfg(filename);
if(weightfile){
load_weights(&net, weightfile);
}
srand(time(0));

data test = load_cifar10_data("data/cifar/cifar-10-batches-bin/test_batch.bin");

matrix pred = network_predict_data(net, test);

int i;
for(i = 0; i < test.X.rows; ++i){
image im = float_to_image(32, 32, 3, test.X.vals[i]);
flip_image(im);
}
matrix pred2 = network_predict_data(net, test);
scale_matrix(pred, .5);
scale_matrix(pred2, .5);
matrix_add_matrix(pred2, pred);

matrix_to_csv(pred);
fprintf(stderr, "Accuracy: %f\n", matrix_topk_accuracy(test.y, pred, 1));
free_data(test);
}

void test_cifar_csvtrain(char *filename, char *weightfile)
{
network net = parse_network_cfg(filename);
if(weightfile){
load_weights(&net, weightfile);
}
srand(time(0));

data test = load_all_cifar10();

matrix pred = network_predict_data(net, test);

int i;
for(i = 0; i < test.X.rows; ++i){
image im = float_to_image(32, 32, 3, test.X.vals[i]);
flip_image(im);
}
matrix pred2 = network_predict_data(net, test);
scale_matrix(pred, .5);
scale_matrix(pred2, .5);
matrix_add_matrix(pred2, pred);

matrix_to_csv(pred);
fprintf(stderr, "Accuracy: %f\n", matrix_topk_accuracy(test.y, pred, 1));
free_data(test);
}

void eval_cifar_csv()
{
data test = load_cifar10_data("data/cifar/cifar-10-batches-bin/test_batch.bin");

matrix pred = csv_to_matrix("results/combined.csv");
fprintf(stderr, "%d %d\n", pred.rows, pred.cols);

fprintf(stderr, "Accuracy: %f\n", matrix_topk_accuracy(test.y, pred, 1));
free_data(test);
free_matrix(pred);
}


void run_cifar(int argc, char **argv)
{
if(argc < 4){
Expand All @@ -89,7 +245,12 @@ void run_cifar(int argc, char **argv)
char *cfg = argv[3];
char *weights = (argc > 4) ? argv[4] : 0;
if(0==strcmp(argv[2], "train")) train_cifar(cfg, weights);
else if(0==strcmp(argv[2], "distill")) train_cifar_distill(cfg, weights);
else if(0==strcmp(argv[2], "test")) test_cifar(cfg, weights);
else if(0==strcmp(argv[2], "multi")) test_cifar_multi(cfg, weights);
else if(0==strcmp(argv[2], "csv")) test_cifar_csv(cfg, weights);
else if(0==strcmp(argv[2], "csvtrain")) test_cifar_csvtrain(cfg, weights);
else if(0==strcmp(argv[2], "eval")) eval_cifar_csv();
}


Loading

0 comments on commit d1965bd

Please sign in to comment.