From 1b5afb45838e603fa6780762eb8cc59246dc2d81 Mon Sep 17 00:00:00 2001
From: IlyaOvodov <b@ovdv.ru>
Date: Tue, 08 May 2018 11:09:35 +0000
Subject: [PATCH] Output improvements for detector results: When printing detector results, output was done in random order, obfuscating results for interpreting. Now: 1. Text output includes coordinates of rects in (left,right,top,bottom in pixels) along with label and score 2. Text output is sorted by rect lefts to simplify finding appropriate rects on image 3. If several class probs are > thresh for some detection, the most probable is written first and coordinates for others are not repeated 4. Rects are imprinted in image in order by their best class prob, so most probable rects are always on top and not overlayed by less probable ones 5. Most probable label for rect is always written first Also: 6. Message about low GPU memory include required amount
---
src/darknet.c | 246 +++++++++++++++++++++++++++++++++++++++---------
1 files changed, 199 insertions(+), 47 deletions(-)
diff --git a/src/darknet.c b/src/darknet.c
index f2982ac..0f6af48 100644
--- a/src/darknet.c
+++ b/src/darknet.c
@@ -12,8 +12,11 @@
#include "opencv2/highgui/highgui_c.h"
#endif
-extern void run_imagenet(int argc, char **argv);
+extern void predict_classifier(char *datacfg, char *cfgfile, char *weightfile, char *filename, int top);
+extern void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh, int ext_output);
+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);
extern void run_writing(int argc, char **argv);
extern void run_captcha(int argc, char **argv);
@@ -26,20 +29,8 @@
extern void run_tag(int argc, char **argv);
extern void run_cifar(int argc, char **argv);
extern void run_go(int argc, char **argv);
-
-void change_rate(char *filename, float scale, float add)
-{
- // Ready for some weird shit??
- FILE *fp = fopen(filename, "r+b");
- if(!fp) file_error(filename);
- float rate = 0;
- fread(&rate, sizeof(float), 1, fp);
- printf("Scaling learning rate from %f to %f\n", rate, rate*scale+add);
- rate = rate*scale + add;
- fseek(fp, 0, SEEK_SET);
- fwrite(&rate, sizeof(float), 1, fp);
- fclose(fp);
-}
+extern void run_art(int argc, char **argv);
+extern void run_super(int argc, char **argv);
void average(int argc, char *argv[])
{
@@ -63,7 +54,12 @@
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.batch_normalize){
+ axpy_cpu(l.n, 1, l.scales, 1, out.scales, 1);
+ axpy_cpu(l.n, 1, l.rolling_mean, 1, out.rolling_mean, 1);
+ axpy_cpu(l.n, 1, l.rolling_variance, 1, out.rolling_variance, 1);
+ }
}
if(l.type == CONNECTED){
axpy_cpu(l.outputs, 1, l.biases, 1, out.biases, 1);
@@ -77,7 +73,12 @@
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.batch_normalize){
+ scal_cpu(l.n, 1./n, l.scales, 1);
+ scal_cpu(l.n, 1./n, l.rolling_mean, 1);
+ scal_cpu(l.n, 1./n, l.rolling_variance, 1);
+ }
}
if(l.type == CONNECTED){
scal_cpu(l.outputs, 1./n, l.biases, 1);
@@ -87,6 +88,66 @@
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;
+ network net = parse_network_cfg(cfgfile);
+ int i;
+ long ops = 0;
+ for(i = 0; i < net.n; ++i){
+ layer l = net.layers[i];
+ if(l.type == CONVOLUTIONAL){
+ ops += 2l * l.n * l.size*l.size*l.c * l.out_h*l.out_w;
+ } else if(l.type == CONNECTED){
+ ops += 2l * l.inputs * l.outputs;
+ }
+ }
+ printf("Floating Point Operations: %ld\n", ops);
+ printf("Floating Point Operations: %.2f Bn\n", (float)ops/1000000000.);
+}
+
+void oneoff(char *cfgfile, char *weightfile, char *outfile)
+{
+ gpu_index = -1;
+ network net = parse_network_cfg(cfgfile);
+ int oldn = net.layers[net.n - 2].n;
+ int c = net.layers[net.n - 2].c;
+ net.layers[net.n - 2].n = 9372;
+ net.layers[net.n - 2].biases += 5;
+ net.layers[net.n - 2].weights += 5*c;
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ net.layers[net.n - 2].biases -= 5;
+ net.layers[net.n - 2].weights -= 5*c;
+ net.layers[net.n - 2].n = oldn;
+ printf("%d\n", oldn);
+ layer l = net.layers[net.n - 2];
+ copy_cpu(l.n/3, l.biases, 1, l.biases + l.n/3, 1);
+ copy_cpu(l.n/3, l.biases, 1, l.biases + 2*l.n/3, 1);
+ copy_cpu(l.n/3*l.c, l.weights, 1, l.weights + l.n/3*l.c, 1);
+ copy_cpu(l.n/3*l.c, l.weights, 1, l.weights + 2*l.n/3*l.c, 1);
+ *net.seen = 0;
+ save_weights(net, outfile);
+}
+
void partial(char *cfgfile, char *weightfile, char *outfile, int max)
{
gpu_index = -1;
@@ -98,17 +159,6 @@
save_weights_upto(net, outfile, max);
}
-void stacked(char *cfgfile, char *weightfile, char *outfile)
-{
- gpu_index = -1;
- network net = parse_network_cfg(cfgfile);
- if(weightfile){
- load_weights(&net, weightfile);
- }
- net.seen = 0;
- save_weights_double(net, outfile);
-}
-
#include "convolutional_layer.h"
void rescale_net(char *cfgfile, char *weightfile, char *outfile)
{
@@ -121,7 +171,7 @@
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;
}
}
@@ -139,13 +189,54 @@
for(i = 0; i < net.n; ++i){
layer l = net.layers[i];
if(l.type == CONVOLUTIONAL){
- rgbgr_filters(l);
+ rgbgr_weights(l);
break;
}
}
save_weights(net, outfile);
}
+void reset_normalize_net(char *cfgfile, char *weightfile, char *outfile)
+{
+ 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 == CONVOLUTIONAL && l.batch_normalize) {
+ denormalize_convolutional_layer(l);
+ }
+ if (l.type == CONNECTED && l.batch_normalize) {
+ denormalize_connected_layer(l);
+ }
+ if (l.type == GRU && l.batch_normalize) {
+ denormalize_connected_layer(*l.input_z_layer);
+ denormalize_connected_layer(*l.input_r_layer);
+ denormalize_connected_layer(*l.input_h_layer);
+ denormalize_connected_layer(*l.state_z_layer);
+ denormalize_connected_layer(*l.state_r_layer);
+ denormalize_connected_layer(*l.state_h_layer);
+ }
+ }
+ save_weights(net, outfile);
+}
+
+layer normalize_layer(layer l, int n)
+{
+ int j;
+ l.batch_normalize=1;
+ l.scales = calloc(n, sizeof(float));
+ for(j = 0; j < n; ++j){
+ l.scales[j] = 1;
+ }
+ l.rolling_mean = calloc(n, sizeof(float));
+ l.rolling_variance = calloc(n, sizeof(float));
+ return l;
+}
+
void normalize_net(char *cfgfile, char *weightfile, char *outfile)
{
gpu_index = -1;
@@ -153,22 +244,61 @@
if(weightfile){
load_weights(&net, weightfile);
}
- int i, j;
+ int i;
for(i = 0; i < net.n; ++i){
layer l = net.layers[i];
- if(l.type == CONVOLUTIONAL){
+ if(l.type == CONVOLUTIONAL && !l.batch_normalize){
+ net.layers[i] = normalize_layer(l, l.n);
+ }
+ if (l.type == CONNECTED && !l.batch_normalize) {
+ net.layers[i] = normalize_layer(l, l.outputs);
+ }
+ if (l.type == GRU && l.batch_normalize) {
+ *l.input_z_layer = normalize_layer(*l.input_z_layer, l.input_z_layer->outputs);
+ *l.input_r_layer = normalize_layer(*l.input_r_layer, l.input_r_layer->outputs);
+ *l.input_h_layer = normalize_layer(*l.input_h_layer, l.input_h_layer->outputs);
+ *l.state_z_layer = normalize_layer(*l.state_z_layer, l.state_z_layer->outputs);
+ *l.state_r_layer = normalize_layer(*l.state_r_layer, l.state_r_layer->outputs);
+ *l.state_h_layer = normalize_layer(*l.state_h_layer, l.state_h_layer->outputs);
net.layers[i].batch_normalize=1;
- net.layers[i].scales = calloc(l.n, sizeof(float));
- for(j = 0; j < l.n; ++j){
- net.layers[i].scales[i] = 1;
- }
- net.layers[i].rolling_mean = calloc(l.n, sizeof(float));
- net.layers[i].rolling_variance = calloc(l.n, sizeof(float));
}
}
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;
@@ -236,17 +366,25 @@
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], "detect")){
+ float thresh = find_float_arg(argc, argv, "-thresh", .24);
+ int ext_output = find_arg(argc, argv, "-ext_output");
+ char *filename = (argc > 4) ? argv[4]: 0;
+ test_detector("cfg/coco.data", argv[2], argv[3], filename, thresh, ext_output);
} else if (0 == strcmp(argv[1], "cifar")){
run_cifar(argc, argv);
} else if (0 == strcmp(argv[1], "go")){
@@ -257,8 +395,12 @@
run_vid_rnn(argc, argv);
} else if (0 == strcmp(argv[1], "coco")){
run_coco(argc, argv);
+ } else if (0 == strcmp(argv[1], "classify")){
+ predict_classifier("cfg/imagenet1k.data", argv[2], argv[3], argv[4], 5);
} else if (0 == strcmp(argv[1], "classifier")){
run_classifier(argc, argv);
+ } else if (0 == strcmp(argv[1], "art")){
+ run_art(argc, argv);
} else if (0 == strcmp(argv[1], "tag")){
run_tag(argc, argv);
} else if (0 == strcmp(argv[1], "compare")){
@@ -267,26 +409,36 @@
run_dice(argc, argv);
} 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], (argc > 5) ? atof(argv[5]) : 0);
} else if (0 == strcmp(argv[1], "test")){
test_resize(argv[2]);
} else if (0 == strcmp(argv[1], "captcha")){
run_captcha(argc, argv);
} else if (0 == strcmp(argv[1], "nightmare")){
run_nightmare(argc, argv);
- } else if (0 == strcmp(argv[1], "change")){
- change_rate(argv[2], atof(argv[3]), (argc > 4) ? atof(argv[4]) : 0);
} else if (0 == strcmp(argv[1], "rgbgr")){
rgbgr_net(argv[2], argv[3], argv[4]);
+ } else if (0 == strcmp(argv[1], "reset")){
+ 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 && argv[3]) ? atoi(argv[3]) : 0);
+ } else if (0 == strcmp(argv[1], "oneoff")){
+ oneoff(argv[2], argv[3], argv[4]);
} else if (0 == strcmp(argv[1], "partial")){
partial(argv[2], argv[3], argv[4], atoi(argv[5]));
- } else if (0 == strcmp(argv[1], "stacked")){
- stacked(argv[2], argv[3], argv[4]);
+ } else if (0 == strcmp(argv[1], "average")){
+ average(argc, argv);
} else if (0 == strcmp(argv[1], "visualize")){
visualize(argv[2], (argc > 3) ? argv[3] : 0);
} else if (0 == strcmp(argv[1], "imtest")){
--
Gitblit v1.10.0