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 | 1116 +++++++++++++++++++++-------------------------------------
1 files changed, 401 insertions(+), 715 deletions(-)
diff --git a/src/darknet.c b/src/darknet.c
index 64012e0..0f6af48 100644
--- a/src/darknet.c
+++ b/src/darknet.c
@@ -1,765 +1,451 @@
-#include "connected_layer.h"
-#include "convolutional_layer.h"
-#include "maxpool_layer.h"
-#include "network.h"
-#include "image.h"
-#include "parser.h"
-#include "data.h"
-#include "matrix.h"
-#include "utils.h"
-#include "blas.h"
-#include "matrix.h"
-#include "server.h"
-
#include <time.h>
#include <stdlib.h>
#include <stdio.h>
-#define _GNU_SOURCE
-#include <fenv.h>
+#include "parser.h"
+#include "utils.h"
+#include "cuda.h"
+#include "blas.h"
+#include "connected_layer.h"
-void test_load()
-{
- image dog = load_image("dog.jpg", 300, 400);
- show_image(dog, "Test Load");
- show_image_layers(dog, "Test Load");
-}
-
-void test_parser()
-{
- network net = parse_network_cfg("cfg/trained_imagenet.cfg");
- save_network(net, "cfg/trained_imagenet_smaller.cfg");
-}
-
-#define AMNT 3
-void draw_detection(image im, float *box, int side)
-{
- int j;
- int r, c;
- float amount[AMNT] = {0};
- for(r = 0; r < side*side; ++r){
- float val = box[r*5];
- for(j = 0; j < AMNT; ++j){
- if(val > amount[j]) {
- float swap = val;
- val = amount[j];
- amount[j] = swap;
- }
- }
- }
- float smallest = amount[AMNT-1];
-
- for(r = 0; r < side; ++r){
- for(c = 0; c < side; ++c){
- j = (r*side + c) * 5;
- printf("Prob: %f\n", box[j]);
- if(box[j] >= smallest){
- int d = im.w/side;
- int y = r*d+box[j+1]*d;
- int x = c*d+box[j+2]*d;
- int h = box[j+3]*256;
- int w = box[j+4]*256;
- //printf("%f %f %f %f\n", box[j+1], box[j+2], box[j+3], box[j+4]);
- //printf("%d %d %d %d\n", x, y, w, h);
- //printf("%d %d %d %d\n", x-w/2, y-h/2, x+w/2, y+h/2);
- draw_box(im, x-w/2, y-h/2, x+w/2, y+h/2);
- }
- }
- }
- show_image(im, "box");
- cvWaitKey(0);
-}
-
-
-void train_detection_net(char *cfgfile)
-{
- float avg_loss = 1;
- //network net = parse_network_cfg("/home/pjreddie/imagenet_backup/alexnet_1270.cfg");
- network net = parse_network_cfg(cfgfile);
- printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
- int imgs = 1024;
- srand(time(0));
- //srand(23410);
- int i = 0;
- list *plist = get_paths("/home/pjreddie/data/imagenet/horse.txt");
- char **paths = (char **)list_to_array(plist);
- printf("%d\n", plist->size);
- data train, buffer;
- pthread_t load_thread = load_data_detection_thread(imgs, paths, plist->size, 256, 256, 7, 7, 256, &buffer);
- clock_t time;
- while(1){
- i += 1;
- time=clock();
- pthread_join(load_thread, 0);
- train = buffer;
- load_thread = load_data_detection_thread(imgs, paths, plist->size, 256, 256, 7, 7, 256, &buffer);
- //data train = load_data_detection_random(imgs, paths, plist->size, 224, 224, 7, 7, 256);
-
-/*
- image im = float_to_image(224, 224, 3, train.X.vals[923]);
- draw_detection(im, train.y.vals[923], 7);
- */
-
- normalize_data_rows(train);
- printf("Loaded: %lf seconds\n", sec(clock()-time));
- time=clock();
- float loss = train_network(net, train);
- avg_loss = avg_loss*.9 + loss*.1;
- printf("%d: %f, %f avg, %lf seconds, %d images\n", i, loss, avg_loss, sec(clock()-time), i*imgs);
- if(i%100==0){
- char buff[256];
- sprintf(buff, "/home/pjreddie/imagenet_backup/detnet_%d.cfg", i);
- save_network(net, buff);
- }
- free_data(train);
- }
-}
-
-void validate_detection_net(char *cfgfile)
-{
- network net = parse_network_cfg(cfgfile);
- fprintf(stderr, "Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
- srand(time(0));
-
- list *plist = get_paths("/home/pjreddie/data/imagenet/detection.val");
- char **paths = (char **)list_to_array(plist);
-
- int m = plist->size;
- int i = 0;
- int splits = 50;
- int num = (i+1)*m/splits - i*m/splits;
-
- fprintf(stderr, "%d\n", m);
- data val, buffer;
- pthread_t load_thread = load_data_thread(paths, num, 0, 0, 245, 224, 224, &buffer);
- clock_t time;
- for(i = 1; i <= splits; ++i){
- time=clock();
- pthread_join(load_thread, 0);
- val = buffer;
- normalize_data_rows(val);
-
- num = (i+1)*m/splits - i*m/splits;
- char **part = paths+(i*m/splits);
- if(i != splits) load_thread = load_data_thread(part, num, 0, 0, 245, 224, 224, &buffer);
-
- fprintf(stderr, "Loaded: %lf seconds\n", sec(clock()-time));
- matrix pred = network_predict_data(net, val);
- int j, k;
- for(j = 0; j < pred.rows; ++j){
- for(k = 0; k < pred.cols; k += 5){
- if (pred.vals[j][k] > .005){
- int index = k/5;
- int r = index/7;
- int c = index%7;
- float y = (32.*(r + pred.vals[j][k+1]))/224.;
- float x = (32.*(c + pred.vals[j][k+2]))/224.;
- float h = (256.*(pred.vals[j][k+3]))/224.;
- float w = (256.*(pred.vals[j][k+4]))/224.;
- printf("%d %f %f %f %f %f\n", (i-1)*m/splits + j + 1, pred.vals[j][k], y, x, h, w);
- }
- }
- }
-
- time=clock();
- free_data(val);
- }
-}
-/*
-
-void train_imagenet_distributed(char *address)
-{
- float avg_loss = 1;
- srand(time(0));
- network net = parse_network_cfg("cfg/net.cfg");
- set_learning_network(&net, 0, 1, 0);
- printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
- int imgs = net.batch;
- int i = 0;
- char **labels = get_labels("/home/pjreddie/data/imagenet/cls.labels.list");
- list *plist = get_paths("/data/imagenet/cls.train.list");
- char **paths = (char **)list_to_array(plist);
- printf("%d\n", plist->size);
- clock_t time;
- data train, buffer;
- pthread_t load_thread = load_data_thread(paths, imgs, plist->size, labels, 1000, 224, 224, &buffer);
- while(1){
- i += 1;
-
- time=clock();
- client_update(net, address);
- printf("Updated: %lf seconds\n", sec(clock()-time));
-
- time=clock();
- pthread_join(load_thread, 0);
- train = buffer;
- normalize_data_rows(train);
- load_thread = load_data_thread(paths, imgs, plist->size, labels, 1000, 224, 224, &buffer);
- printf("Loaded: %lf seconds\n", sec(clock()-time));
- time=clock();
-
- float loss = train_network(net, train);
- avg_loss = avg_loss*.9 + loss*.1;
- printf("%d: %f, %f avg, %lf seconds, %d images\n", i, loss, avg_loss, sec(clock()-time), i*imgs);
- free_data(train);
- }
-}
-*/
-
-void train_imagenet(char *cfgfile)
-{
- float avg_loss = 1;
- srand(time(0));
- network net = parse_network_cfg(cfgfile);
- //test_learn_bias(*(convolutional_layer *)net.layers[1]);
- //set_learning_network(&net, net.learning_rate, 0, net.decay);
- printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
- int imgs = 1024;
- int i = net.seen/imgs;
- char **labels = get_labels("/home/pjreddie/data/imagenet/cls.labels.list");
- list *plist = get_paths("/data/imagenet/cls.train.list");
- char **paths = (char **)list_to_array(plist);
- printf("%d\n", plist->size);
- clock_t time;
- pthread_t load_thread;
- data train;
- data buffer;
- load_thread = load_data_thread(paths, imgs, plist->size, labels, 1000, 256, 256, &buffer);
- while(1){
- ++i;
- time=clock();
- pthread_join(load_thread, 0);
- train = buffer;
- load_thread = load_data_thread(paths, imgs, plist->size, labels, 1000, 256, 256, &buffer);
- printf("Loaded: %lf seconds\n", sec(clock()-time));
- time=clock();
- float loss = train_network(net, train);
- net.seen += imgs;
- avg_loss = avg_loss*.9 + loss*.1;
- printf("%d: %f, %f avg, %lf seconds, %d images\n", i, loss, avg_loss, sec(clock()-time), net.seen);
- free_data(train);
- if(i%100==0){
- char buff[256];
- sprintf(buff, "/home/pjreddie/imagenet_backup/vgg_%d.cfg", i);
- save_network(net, buff);
- }
- }
-}
-
-void validate_imagenet(char *filename)
-{
- int i = 0;
- network net = parse_network_cfg(filename);
- srand(time(0));
-
- char **labels = get_labels("/home/pjreddie/data/imagenet/cls.val.labels.list");
-
- list *plist = get_paths("/home/pjreddie/data/imagenet/cls.val.list");
- char **paths = (char **)list_to_array(plist);
- int m = plist->size;
- free_list(plist);
-
- clock_t time;
- float avg_acc = 0;
- float avg_top5 = 0;
- int splits = 50;
- int num = (i+1)*m/splits - i*m/splits;
-
- data val, buffer;
- pthread_t load_thread = load_data_thread(paths, num, 0, labels, 1000, 256, 256, &buffer);
- for(i = 1; i <= splits; ++i){
- time=clock();
-
- pthread_join(load_thread, 0);
- val = buffer;
- //normalize_data_rows(val);
-
- num = (i+1)*m/splits - i*m/splits;
- char **part = paths+(i*m/splits);
- if(i != splits) load_thread = load_data_thread(part, num, 0, labels, 1000, 256, 256, &buffer);
- printf("Loaded: %d images in %lf seconds\n", val.X.rows, sec(clock()-time));
-
- time=clock();
- float *acc = network_accuracies(net, val);
- avg_acc += acc[0];
- avg_top5 += acc[1];
- printf("%d: top1: %f, top5: %f, %lf seconds, %d images\n", i, avg_acc/i, avg_top5/i, sec(clock()-time), val.X.rows);
- free_data(val);
- }
-}
-
-void test_detection(char *cfgfile)
-{
- network net = parse_network_cfg(cfgfile);
- set_batch_network(&net, 1);
- srand(2222222);
- clock_t time;
- char filename[256];
- while(1){
- fgets(filename, 256, stdin);
- strtok(filename, "\n");
- image im = load_image_color(filename, 224, 224);
- z_normalize_image(im);
- printf("%d %d %d\n", im.h, im.w, im.c);
- float *X = im.data;
- time=clock();
- float *predictions = network_predict(net, X);
- printf("%s: Predicted in %f seconds.\n", filename, sec(clock()-time));
- draw_detection(im, predictions, 7);
- free_image(im);
- }
-}
-
-void test_init(char *cfgfile)
-{
- network net = parse_network_cfg(cfgfile);
- set_batch_network(&net, 1);
- srand(2222222);
- int i = 0;
- char *filename = "data/test.jpg";
-
- image im = load_image_color(filename, 256, 256);
- //z_normalize_image(im);
- translate_image(im, -128);
- scale_image(im, 1/128.);
- float *X = im.data;
- forward_network(net, X, 0, 1);
- for(i = 0; i < net.n; ++i){
- if(net.types[i] == CONVOLUTIONAL){
- convolutional_layer layer = *(convolutional_layer *)net.layers[i];
- image output = get_convolutional_image(layer);
- int size = output.h*output.w*output.c;
- float v = variance_array(layer.output, size);
- float m = mean_array(layer.output, size);
- printf("%d: Convolutional, mean: %f, variance %f\n", i, m, v);
- }
- else if(net.types[i] == CONNECTED){
- connected_layer layer = *(connected_layer *)net.layers[i];
- int size = layer.outputs;
- float v = variance_array(layer.output, size);
- float m = mean_array(layer.output, size);
- printf("%d: Connected, mean: %f, variance %f\n", i, m, v);
- }
- }
- free_image(im);
-}
-void test_dog(char *cfgfile)
-{
- image im = load_image_color("data/dog.jpg", 224, 224);
- translate_image(im, -128);
- print_image(im);
- float *X = im.data;
- network net = parse_network_cfg(cfgfile);
- set_batch_network(&net, 1);
- float *predictions = network_predict(net, X);
- image crop = get_network_image_layer(net, 0);
- //show_image(crop, "cropped");
- // print_image(crop);
- //show_image(im, "orig");
- float * inter = get_network_output(net);
- pm(1000, 1, inter);
- //cvWaitKey(0);
-}
-
-void test_imagenet(char *cfgfile)
-{
- network net = parse_network_cfg(cfgfile);
- set_batch_network(&net, 1);
- //imgs=1;
- srand(2222222);
- int i = 0;
- char **names = get_labels("cfg/shortnames.txt");
- clock_t time;
- char filename[256];
- int indexes[10];
- while(1){
- fgets(filename, 256, stdin);
- strtok(filename, "\n");
- image im = load_image_color(filename, 256, 256);
- translate_image(im, -128);
- //scale_image(im, 1/128.);
- printf("%d %d %d\n", im.h, im.w, im.c);
- float *X = im.data;
- time=clock();
- float *predictions = network_predict(net, X);
- top_predictions(net, 10, indexes);
- printf("%s: Predicted in %f seconds.\n", filename, sec(clock()-time));
- for(i = 0; i < 10; ++i){
- int index = indexes[i];
- printf("%s: %f\n", names[index], predictions[index]);
- }
- free_image(im);
- }
-}
-
-void test_visualize(char *filename)
-{
- network net = parse_network_cfg(filename);
- visualize_network(net);
- cvWaitKey(0);
-}
-
-void test_cifar10(char *cfgfile)
-{
- network net = parse_network_cfg(cfgfile);
- data test = load_cifar10_data("data/cifar10/test_batch.bin");
- clock_t start = clock(), end;
- float test_acc = network_accuracy_multi(net, test, 10);
- end = clock();
- printf("%f in %f Sec\n", test_acc, sec(end-start));
- //visualize_network(net);
- //cvWaitKey(0);
-}
-
-void train_cifar10(char *cfgfile)
-{
- srand(555555);
- srand(time(0));
- network net = parse_network_cfg(cfgfile);
- data test = load_cifar10_data("data/cifar10/test_batch.bin");
- int count = 0;
- int iters = 50000/net.batch;
- data train = load_all_cifar10();
- while(++count <= 10000){
- clock_t time = clock();
- float loss = train_network_sgd(net, train, iters);
-
- if(count%10 == 0){
- float test_acc = network_accuracy(net, test);
- printf("%d: Loss: %f, Test Acc: %f, Time: %lf seconds\n", count, loss, test_acc,sec(clock()-time));
- char buff[256];
- sprintf(buff, "/home/pjreddie/imagenet_backup/cifar10_%d.cfg", count);
- save_network(net, buff);
- }else{
- printf("%d: Loss: %f, Time: %lf seconds\n", count, loss, sec(clock()-time));
- }
-
- }
- free_data(train);
-}
-
-void compare_nist(char *p1,char *p2)
-{
- srand(222222);
- network n1 = parse_network_cfg(p1);
- network n2 = parse_network_cfg(p2);
- data test = load_categorical_data_csv("data/mnist/mnist_test.csv",0,10);
- normalize_data_rows(test);
- compare_networks(n1, n2, test);
-}
-
-void test_nist(char *path)
-{
- srand(222222);
- network net = parse_network_cfg(path);
- data test = load_categorical_data_csv("data/mnist/mnist_test.csv",0,10);
- normalize_data_rows(test);
- clock_t start = clock(), end;
- float test_acc = network_accuracy(net, test);
- end = clock();
- printf("Accuracy: %f, Time: %lf seconds\n", test_acc,(float)(end-start)/CLOCKS_PER_SEC);
-}
-
-void train_nist(char *cfgfile)
-{
- srand(222222);
- // srand(time(0));
- data train = load_categorical_data_csv("data/mnist/mnist_train.csv", 0, 10);
- data test = load_categorical_data_csv("data/mnist/mnist_test.csv",0,10);
- network net = parse_network_cfg(cfgfile);
- int count = 0;
- int iters = 6000/net.batch + 1;
- while(++count <= 100){
- clock_t start = clock(), end;
- normalize_data_rows(train);
- normalize_data_rows(test);
- float loss = train_network_sgd(net, train, iters);
- float test_acc = 0;
- if(count%1 == 0) test_acc = network_accuracy(net, test);
- end = clock();
- printf("%d: Loss: %f, Test Acc: %f, Time: %lf seconds\n", count, loss, test_acc,(float)(end-start)/CLOCKS_PER_SEC);
- }
- free_data(train);
- free_data(test);
- char buff[256];
- sprintf(buff, "%s.trained", cfgfile);
- save_network(net, buff);
-}
-
-/*
- void train_nist_distributed(char *address)
- {
- srand(time(0));
- network net = parse_network_cfg("cfg/nist.client");
- data train = load_categorical_data_csv("data/mnist/mnist_train.csv", 0, 10);
-//data test = load_categorical_data_csv("data/mnist/mnist_test.csv",0,10);
-normalize_data_rows(train);
-//normalize_data_rows(test);
-int count = 0;
-int iters = 50000/net.batch;
-iters = 1000/net.batch + 1;
-while(++count <= 2000){
-clock_t start = clock(), end;
-float loss = train_network_sgd(net, train, iters);
-client_update(net, address);
-end = clock();
-//float test_acc = network_accuracy_gpu(net, test);
-//float test_acc = 0;
-printf("%d: Loss: %f, Time: %lf seconds\n", count, loss, (float)(end-start)/CLOCKS_PER_SEC);
-}
-}
- */
-
-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;
- // 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;
- float lr = .0005;
- float momentum = .9;
- float decay = .01;
- network net = parse_network_cfg("nist.cfg");
- while(++count <= 15){
- float acc = train_network_sgd(net, train, train.X.rows);
- 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);
- float acc = matrix_topk_accuracy(test.y, partial,1);
- printf("Model Accuracy: %lf\n", acc);
- matrix_add_matrix(partial, prediction);
- acc = matrix_topk_accuracy(test.y, prediction,1);
- printf("Current Ensemble Accuracy: %lf\n", acc);
- free_matrix(partial);
- }
- float acc = matrix_topk_accuracy(test.y, prediction,1);
- printf("Full Ensemble Accuracy: %lf\n", acc);
-}
-
-void visualize_cat()
-{
- network net = parse_network_cfg("cfg/voc_imagenet.cfg");
- image im = load_image_color("data/cat.png", 0, 0);
- printf("Processing %dx%d image\n", im.h, im.w);
- resize_network(net, im.h, im.w, im.c);
- forward_network(net, im.data, 0, 0);
-
- visualize_network(net);
- cvWaitKey(0);
-}
-
-#ifdef GPU
-void test_convolutional_layer()
-{
- network net = parse_network_cfg("cfg/nist_conv.cfg");
- int size = get_network_input_size(net);
- float *in = calloc(size, sizeof(float));
- int i;
- for(i = 0; i < size; ++i) in[i] = rand_normal();
- float *in_gpu = cuda_make_array(in, size);
- convolutional_layer layer = *(convolutional_layer *)net.layers[0];
- int out_size = convolutional_out_height(layer)*convolutional_out_width(layer)*layer.batch;
- cuda_compare(layer.output_gpu, layer.output, out_size, "nothing");
- cuda_compare(layer.biases_gpu, layer.biases, layer.n, "biases");
- cuda_compare(layer.filters_gpu, layer.filters, layer.n*layer.size*layer.size*layer.c, "filters");
- bias_output(layer);
- bias_output_gpu(layer);
- cuda_compare(layer.output_gpu, layer.output, out_size, "biased output");
-}
+#ifdef OPENCV
+#include "opencv2/highgui/highgui_c.h"
#endif
-void test_correct_nist()
+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);
+extern void run_nightmare(int argc, char **argv);
+extern void run_dice(int argc, char **argv);
+extern void run_compare(int argc, char **argv);
+extern void run_classifier(int argc, char **argv);
+extern void run_char_rnn(int argc, char **argv);
+extern void run_vid_rnn(int argc, char **argv);
+extern void run_tag(int argc, char **argv);
+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 average(int argc, char *argv[])
{
- network net = parse_network_cfg("cfg/nist_conv.cfg");
- srand(222222);
- net = parse_network_cfg("cfg/nist_conv.cfg");
- data train = load_categorical_data_csv("data/mnist/mnist_train.csv", 0, 10);
- data test = load_categorical_data_csv("data/mnist/mnist_test.csv",0,10);
- normalize_data_rows(train);
- normalize_data_rows(test);
- int count = 0;
- int iters = 1000/net.batch;
-
- while(++count <= 5){
- clock_t start = clock(), end;
- float loss = train_network_sgd(net, train, iters);
- end = clock();
- float test_acc = network_accuracy(net, test);
- printf("%d: Loss: %f, Test Acc: %f, Time: %lf seconds, LR: %f, Momentum: %f, Decay: %f\n", count, loss, test_acc,(float)(end-start)/CLOCKS_PER_SEC, net.learning_rate, net.momentum, net.decay);
- }
- save_network(net, "cfg/nist_gpu.cfg");
-
+ char *cfgfile = argv[2];
+ char *outfile = argv[3];
gpu_index = -1;
- count = 0;
- srand(222222);
- net = parse_network_cfg("cfg/nist_conv.cfg");
- while(++count <= 5){
- clock_t start = clock(), end;
- float loss = train_network_sgd(net, train, iters);
- end = clock();
- float test_acc = network_accuracy(net, test);
- printf("%d: Loss: %f, Test Acc: %f, Time: %lf seconds, LR: %f, Momentum: %f, Decay: %f\n", count, loss, test_acc,(float)(end-start)/CLOCKS_PER_SEC, net.learning_rate, net.momentum, net.decay);
+ network net = parse_network_cfg(cfgfile);
+ network sum = parse_network_cfg(cfgfile);
+
+ char *weightfile = argv[4];
+ load_weights(&sum, weightfile);
+
+ int i, j;
+ int n = argc - 5;
+ for(i = 0; i < n; ++i){
+ weightfile = argv[i+5];
+ load_weights(&net, weightfile);
+ for(j = 0; j < net.n; ++j){
+ layer l = net.layers[j];
+ layer out = sum.layers[j];
+ 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.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);
+ axpy_cpu(l.outputs*l.inputs, 1, l.weights, 1, out.weights, 1);
+ }
+ }
}
- save_network(net, "cfg/nist_cpu.cfg");
+ n = n+1;
+ for(j = 0; j < net.n; ++j){
+ layer l = sum.layers[j];
+ 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.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);
+ scal_cpu(l.outputs*l.inputs, 1./n, l.weights, 1);
+ }
+ }
+ save_weights(sum, outfile);
}
-void test_correct_alexnet()
+void speed(char *cfgfile, int tics)
{
- char **labels = get_labels("/home/pjreddie/data/imagenet/cls.labels.list");
- list *plist = get_paths("/data/imagenet/cls.train.list");
- char **paths = (char **)list_to_array(plist);
- printf("%d\n", plist->size);
- clock_t time;
- int count = 0;
- network net;
-
- srand(222222);
- net = parse_network_cfg("cfg/net.cfg");
- int imgs = net.batch;
-
- count = 0;
- while(++count <= 5){
- time=clock();
- data train = load_data(paths, imgs, plist->size, labels, 1000, 256, 256);
- normalize_data_rows(train);
- printf("Loaded: %lf seconds\n", sec(clock()-time));
- time=clock();
- float loss = train_network(net, train);
- printf("%d: %f, %lf seconds, %d images\n", count, loss, sec(clock()-time), imgs*net.batch);
- free_data(train);
+ 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;
- count = 0;
- srand(222222);
- net = parse_network_cfg("cfg/net.cfg");
- printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
- while(++count <= 5){
- time=clock();
- data train = load_data(paths, imgs, plist->size, labels, 1000, 256,256);
- normalize_data_rows(train);
- printf("Loaded: %lf seconds\n", sec(clock()-time));
- time=clock();
- float loss = train_network(net, train);
- printf("%d: %f, %lf seconds, %d images\n", count, loss, sec(clock()-time), imgs*net.batch);
- free_data(train);
+ 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 run_server()
- {
- srand(time(0));
- network net = parse_network_cfg("cfg/net.cfg");
- set_batch_network(&net, 1);
- server_update(net);
- }
-
- void test_client()
- {
- network net = parse_network_cfg("cfg/alexnet.client");
- clock_t time=clock();
- client_update(net, "localhost");
- printf("1\n");
- client_update(net, "localhost");
- printf("2\n");
- client_update(net, "localhost");
- printf("3\n");
- printf("Transfered: %lf seconds\n", sec(clock()-time));
- }
- */
-
-void del_arg(int argc, char **argv, int index)
+void oneoff(char *cfgfile, char *weightfile, char *outfile)
{
- int i;
- for(i = index; i < argc-1; ++i) argv[i] = argv[i+1];
-}
-
-int find_arg(int argc, char* argv[], char *arg)
-{
- int i;
- for(i = 0; i < argc; ++i) if(0==strcmp(argv[i], arg)) {
- del_arg(argc, argv, i);
- return 1;
+ 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);
}
- return 0;
+ 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);
}
-int find_int_arg(int argc, char **argv, char *arg, int def)
+void partial(char *cfgfile, char *weightfile, char *outfile, int max)
{
+ gpu_index = -1;
+ network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights_upto(&net, weightfile, max);
+ }
+ *net.seen = 0;
+ save_weights_upto(net, outfile, max);
+}
+
+#include "convolutional_layer.h"
+void rescale_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 < argc-1; ++i){
- if(0==strcmp(argv[i], arg)){
- def = atoi(argv[i+1]);
- del_arg(argc, argv, i);
- del_arg(argc, argv, i);
+ for(i = 0; i < net.n; ++i){
+ layer l = net.layers[i];
+ if(l.type == CONVOLUTIONAL){
+ rescale_weights(l, 2, -.5);
break;
}
}
- return def;
+ save_weights(net, outfile);
+}
+
+void rgbgr_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){
+ 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;
+ 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){
+ 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;
+ }
+ }
+ 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;
+ 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);
+ net.layers[i].batch_normalize=0;
+ }
+ if (l.type == CONNECTED && l.batch_normalize) {
+ denormalize_connected_layer(l);
+ net.layers[i].batch_normalize=0;
+ }
+ 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);
+ l.input_z_layer->batch_normalize = 0;
+ l.input_r_layer->batch_normalize = 0;
+ l.input_h_layer->batch_normalize = 0;
+ l.state_z_layer->batch_normalize = 0;
+ l.state_r_layer->batch_normalize = 0;
+ l.state_h_layer->batch_normalize = 0;
+ net.layers[i].batch_normalize=0;
+ }
+ }
+ save_weights(net, outfile);
+}
+
+void visualize(char *cfgfile, char *weightfile)
+{
+ network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ visualize_network(net);
+#ifdef OPENCV
+ cvWaitKey(0);
+#endif
}
int main(int argc, char **argv)
{
+ //test_resize("data/bad.jpg");
+ //test_box();
//test_convolutional_layer();
if(argc < 2){
fprintf(stderr, "usage: %s <function>\n", argv[0]);
return 0;
}
gpu_index = find_int_arg(argc, argv, "-i", 0);
- if(find_arg(argc, argv, "-nogpu")) gpu_index = -1;
+ if(find_arg(argc, argv, "-nogpu")) {
+ gpu_index = -1;
+ }
#ifndef GPU
gpu_index = -1;
#else
if(gpu_index >= 0){
- cudaSetDevice(gpu_index);
+ cuda_set_device(gpu_index);
}
#endif
- if(0==strcmp(argv[1], "test_correct")) test_correct_alexnet();
- else if(0==strcmp(argv[1], "test_correct_nist")) test_correct_nist();
- //else if(0==strcmp(argv[1], "server")) run_server();
-
-#ifdef GPU
- else if(0==strcmp(argv[1], "test_gpu")) test_gpu_blas();
-#endif
-
- else if(argc < 3){
- fprintf(stderr, "usage: %s <function> <filename>\n", argv[0]);
- return 0;
+ 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")){
+ run_go(argc, argv);
+ } else if (0 == strcmp(argv[1], "rnn")){
+ run_char_rnn(argc, argv);
+ } else if (0 == strcmp(argv[1], "vid")){
+ 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")){
+ run_compare(argc, argv);
+ } else if (0 == strcmp(argv[1], "dice")){
+ 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], "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], "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")){
+ test_resize(argv[2]);
+ } else {
+ fprintf(stderr, "Not an option: %s\n", argv[1]);
}
- else if(0==strcmp(argv[1], "detection")) train_detection_net(argv[2]);
- else if(0==strcmp(argv[1], "test")) test_imagenet(argv[2]);
- else if(0==strcmp(argv[1], "dog")) test_dog(argv[2]);
- else if(0==strcmp(argv[1], "ctrain")) train_cifar10(argv[2]);
- else if(0==strcmp(argv[1], "nist")) train_nist(argv[2]);
- else if(0==strcmp(argv[1], "ctest")) test_cifar10(argv[2]);
- else if(0==strcmp(argv[1], "train")) train_imagenet(argv[2]);
- //else if(0==strcmp(argv[1], "client")) train_imagenet_distributed(argv[2]);
- else if(0==strcmp(argv[1], "detect")) test_detection(argv[2]);
- else if(0==strcmp(argv[1], "init")) test_init(argv[2]);
- else if(0==strcmp(argv[1], "visualize")) test_visualize(argv[2]);
- else if(0==strcmp(argv[1], "valid")) validate_imagenet(argv[2]);
- else if(0==strcmp(argv[1], "testnist")) test_nist(argv[2]);
- else if(0==strcmp(argv[1], "validetect")) validate_detection_net(argv[2]);
- else if(argc < 4){
- fprintf(stderr, "usage: %s <function> <filename> <filename>\n", argv[0]);
- return 0;
- }
- else if(0==strcmp(argv[1], "compare")) compare_nist(argv[2], argv[3]);
- fprintf(stderr, "Success!\n");
return 0;
}
--
Gitblit v1.10.0