From 73f7aacf35ec9b1d0f9de9ddf38af0889f213e99 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Tue, 20 Sep 2016 18:34:49 +0000
Subject: [PATCH] better multigpu
---
src/darknet.c | 78 +++++++++++++++++++++++++++++++++-----
1 files changed, 67 insertions(+), 11 deletions(-)
diff --git a/src/darknet.c b/src/darknet.c
index 49c9747..1b72329 100644
--- a/src/darknet.c
+++ b/src/darknet.c
@@ -12,7 +12,7 @@
#include "opencv2/highgui/highgui_c.h"
#endif
-extern void run_imagenet(int argc, char **argv);
+extern void run_voxel(int argc, char **argv);
extern void run_yolo(int argc, char **argv);
extern void run_detector(int argc, char **argv);
extern void run_coco(int argc, char **argv);
@@ -28,6 +28,7 @@
extern void run_cifar(int argc, char **argv);
extern void run_go(int argc, char **argv);
extern void run_art(int argc, char **argv);
+extern void run_super(int argc, char **argv);
void change_rate(char *filename, float scale, float add)
{
@@ -65,7 +66,7 @@
if(l.type == CONVOLUTIONAL){
int num = l.n*l.c*l.size*l.size;
axpy_cpu(l.n, 1, l.biases, 1, out.biases, 1);
- axpy_cpu(num, 1, l.filters, 1, out.filters, 1);
+ axpy_cpu(num, 1, l.weights, 1, out.weights, 1);
}
if(l.type == CONNECTED){
axpy_cpu(l.outputs, 1, l.biases, 1, out.biases, 1);
@@ -79,7 +80,7 @@
if(l.type == CONVOLUTIONAL){
int num = l.n*l.c*l.size*l.size;
scal_cpu(l.n, 1./n, l.biases, 1);
- scal_cpu(num, 1./n, l.filters, 1);
+ scal_cpu(num, 1./n, l.weights, 1);
}
if(l.type == CONNECTED){
scal_cpu(l.outputs, 1./n, l.biases, 1);
@@ -89,6 +90,23 @@
save_weights(sum, outfile);
}
+void speed(char *cfgfile, int tics)
+{
+ if (tics == 0) tics = 1000;
+ network net = parse_network_cfg(cfgfile);
+ set_batch_network(&net, 1);
+ int i;
+ time_t start = time(0);
+ image im = make_image(net.w, net.h, net.c);
+ for(i = 0; i < tics; ++i){
+ network_predict(net, im.data);
+ }
+ double t = difftime(time(0), start);
+ printf("\n%d evals, %f Seconds\n", tics, t);
+ printf("Speed: %f sec/eval\n", t/tics);
+ printf("Speed: %f Hz\n", tics/t);
+}
+
void operations(char *cfgfile)
{
gpu_index = -1;
@@ -141,7 +159,7 @@
for(i = 0; i < net.n; ++i){
layer l = net.layers[i];
if(l.type == CONVOLUTIONAL){
- rescale_filters(l, 2, -.5);
+ rescale_weights(l, 2, -.5);
break;
}
}
@@ -159,7 +177,7 @@
for(i = 0; i < net.n; ++i){
layer l = net.layers[i];
if(l.type == CONVOLUTIONAL){
- rgbgr_filters(l);
+ rgbgr_weights(l);
break;
}
}
@@ -236,6 +254,39 @@
save_weights(net, outfile);
}
+void statistics_net(char *cfgfile, char *weightfile)
+{
+ gpu_index = -1;
+ network net = parse_network_cfg(cfgfile);
+ if (weightfile) {
+ load_weights(&net, weightfile);
+ }
+ int i;
+ for (i = 0; i < net.n; ++i) {
+ layer l = net.layers[i];
+ if (l.type == CONNECTED && l.batch_normalize) {
+ printf("Connected Layer %d\n", i);
+ statistics_connected_layer(l);
+ }
+ if (l.type == GRU && l.batch_normalize) {
+ printf("GRU Layer %d\n", i);
+ printf("Input Z\n");
+ statistics_connected_layer(*l.input_z_layer);
+ printf("Input R\n");
+ statistics_connected_layer(*l.input_r_layer);
+ printf("Input H\n");
+ statistics_connected_layer(*l.input_h_layer);
+ printf("State Z\n");
+ statistics_connected_layer(*l.state_z_layer);
+ printf("State R\n");
+ statistics_connected_layer(*l.state_r_layer);
+ printf("State H\n");
+ statistics_connected_layer(*l.state_h_layer);
+ }
+ printf("\n");
+ }
+}
+
void denormalize_net(char *cfgfile, char *weightfile, char *outfile)
{
gpu_index = -1;
@@ -303,17 +354,18 @@
gpu_index = -1;
#else
if(gpu_index >= 0){
- cudaError_t status = cudaSetDevice(gpu_index);
- check_error(status);
+ cuda_set_device(gpu_index);
}
#endif
- if(0==strcmp(argv[1], "imagenet")){
- run_imagenet(argc, argv);
- } else if (0 == strcmp(argv[1], "average")){
+ if (0 == strcmp(argv[1], "average")){
average(argc, argv);
} else if (0 == strcmp(argv[1], "yolo")){
run_yolo(argc, argv);
+ } else if (0 == strcmp(argv[1], "voxel")){
+ run_voxel(argc, argv);
+ } else if (0 == strcmp(argv[1], "super")){
+ run_super(argc, argv);
} else if (0 == strcmp(argv[1], "detector")){
run_detector(argc, argv);
} else if (0 == strcmp(argv[1], "cifar")){
@@ -339,7 +391,7 @@
} else if (0 == strcmp(argv[1], "writing")){
run_writing(argc, argv);
} else if (0 == strcmp(argv[1], "3d")){
- composite_3d(argv[2], argv[3], argv[4]);
+ composite_3d(argv[2], argv[3], argv[4], (argc > 5) ? atof(argv[5]) : 0);
} else if (0 == strcmp(argv[1], "test")){
test_resize(argv[2]);
} else if (0 == strcmp(argv[1], "captcha")){
@@ -354,12 +406,16 @@
reset_normalize_net(argv[2], argv[3], argv[4]);
} else if (0 == strcmp(argv[1], "denormalize")){
denormalize_net(argv[2], argv[3], argv[4]);
+ } else if (0 == strcmp(argv[1], "statistics")){
+ statistics_net(argv[2], argv[3]);
} else if (0 == strcmp(argv[1], "normalize")){
normalize_net(argv[2], argv[3], argv[4]);
} else if (0 == strcmp(argv[1], "rescale")){
rescale_net(argv[2], argv[3], argv[4]);
} else if (0 == strcmp(argv[1], "ops")){
operations(argv[2]);
+ } else if (0 == strcmp(argv[1], "speed")){
+ speed(argv[2], (argc > 3) ? atoi(argv[3]) : 0);
} else if (0 == strcmp(argv[1], "partial")){
partial(argv[2], argv[3], argv[4], atoi(argv[5]));
} else if (0 == strcmp(argv[1], "average")){
--
Gitblit v1.10.0