YOLOv3如何保存检测视频
老板接的无人货柜项目，需要前端用一个多分类器，对fps要求高，于是就直接用了yolov3（darknet）来做为base model，关于如何训练自己的数据就不展示了，网上很多教程，讲的也很清楚，不难。如果有问题，可以留言一起讨论，下面说说用训练好的模型怎么检测视频，然后将检测结果保存到本地。
1、打开image.c，修改后的完整文件如下：其中 //************************guoqing_revised 之间的代码为新增代码
#include "image.h"
#include "utils.h"
#include "blas.h"
#include "cuda.h"
#include
#include
#define STB_IMAGE_IMPLEMENTATION
#include "stb_image.h"
#define STB_IMAGE_WRITE_IMPLEMENTATION
#include "stb_image_write.h"
int windows = 0;
float colors[6][3] = { {1,0,1}, {0,0,1},{0,1,1},{0,1,0},{1,1,0},{1,0,0} };
float get_color(int c, int x, int max)
{
float ratio = ((float)x/max)*5;
int i = floor(ratio);
int j = ceil(ratio);
ratio -= i;
float r = (1-ratio) * colors[i][c] + ratio*colors[j][c];
//printf("%f\n", r);
return r;
}
image mask_to_rgb(image mask)
{
int n = mask.c;
image im = make_image(mask.w, mask.h, 3);
int i, j;
for(j = 0; j < n; ++j){
int offset = j*123457 % n;
float red = get_color(2,offset,n);
float green = get_color(1,offset,n);
float blue = get_color(0,offset,n);
for(i = 0; i < im.w*im.h; ++i){
im.data[i + 0*im.w*im.h] += mask.data[j*im.h*im.w + i]*red;
im.data[i + 1*im.w*im.h] += mask.data[j*im.h*im.w + i]*green;
im.data[i + 2*im.w*im.h] += mask.data[j*im.h*im.w + i]*blue;
}
}
return im;
}
static float get_pixel(image m, int x, int y, int c)
{
assert(x < m.w && y < m.h && c < m.c);
return m.data[c*m.h*m.w + y*m.w + x];
}
static float get_pixel_extend(image m, int x, int y, int c)
{
if(x < 0 || x >= m.w || y < 0 || y >= m.h) return 0;
/*
if(x < 0) x = 0;
if(x >= m.w) x = m.w-1;
if(y < 0) y = 0;
if(y >= m.h) y = m.h-1;
*/
if(c < 0 || c >= m.c) return 0;
return get_pixel(m, x, y, c);
}
static void set_pixel(image m, int x, int y, int c, float val)
{
if (x < 0 || y < 0 || c < 0 || x >= m.w || y >= m.h || c >= m.c) return;
assert(x < m.w && y < m.h && c < m.c);
m.data[c*m.h*m.w + y*m.w + x] = val;
}
static void add_pixel(image m, int x, int y, int c, float val)
{
assert(x < m.w && y < m.h && c < m.c);
m.data[c*m.h*m.w + y*m.w + x] += val;
}
static float bilinear_interpolate(image im, float x, float y, int c)
{
int ix = (int) floorf(x);
int iy = (int) floorf(y);
float dx = x - ix;
float dy = y - iy;
float val = (1-dy) * (1-dx) * get_pixel_extend(im, ix, iy, c) +
dy * (1-dx) * get_pixel_extend(im, ix, iy+1, c) +
(1-dy) * dx * get_pixel_extend(im, ix+1, iy, c) +
dy * dx * get_pixel_extend(im, ix+1, iy+1, c);
return val;
}
void composite_image(image source, image dest, int dx, int dy)
{
int x,y,k;
for(k = 0; k < source.c; ++k){
for(y = 0; y < source.h; ++y){
for(x = 0; x < source.w; ++x){
float val = get_pixel(source, x, y, k);
float val2 = get_pixel_extend(dest, dx+x, dy+y, k);
set_pixel(dest, dx+x, dy+y, k, val * val2);
}
}
}
}
image border_image(image a, int border)
{
image b = make_image(a.w + 2*border, a.h + 2*border, a.c);
int x,y,k;
for(k = 0; k < b.c; ++k){
for(y = 0; y < b.h; ++y){
for(x = 0; x < b.w; ++x){
float val = get_pixel_extend(a, x - border, y - border, k);
if(x - border < 0 || x - border >= a.w || y - border < 0 || y - border >= a.h) val = 1;
set_pixel(b, x, y, k, val);
}
}
}
return b;
}
image tile_images(image a, image b, int dx)
{
if(a.w == 0) return copy_image(b);
image c = make_image(a.w + b.w + dx, (a.h > b.h) ? a.h : b.h, (a.c > b.c) ? a.c : b.c);
fill_cpu(c.w*c.h*c.c, 1, c.data, 1);
embed_image(a, c, 0, 0);
composite_image(b, c, a.w + dx, 0);
return c;
}
image get_label(image **characters, char *string, int size)
{
size = size/10;
if(size > 7) size = 7;
image label = make_empty_image(0,0,0);
while(*string){
image l = characters[size][(int)*string];
image n = tile_images(label, l, -size - 1 + (size+1)/2);
free_image(label);
label = n;
++string;
}
image b = border_image(label, label.h*.25);
free_image(label);
return b;
}
void draw_label(image a, int r, int c, image label, const float *rgb)
{
int w = label.w;
int h = label.h;
if (r - h >= 0) r = r - h;
int i, j, k;
for(j = 0; j < h && j + r < a.h; ++j){
for(i = 0; i < w && i + c < a.w; ++i){
for(k = 0; k < label.c; ++k){
float val = get_pixel(label, i, j, k);
set_pixel(a, i+c, j+r, k, rgb[k] * val);
}
}
}
}
void draw_box(image a, int x1, int y1, int x2, int y2, float r, float g, float b)
{
//normalize_image(a);
int i;
if(x1 < 0) x1 = 0;
if(x1 >= a.w) x1 = a.w-1;
if(x2 < 0) x2 = 0;
if(x2 >= a.w) x2 = a.w-1;
if(y1 < 0) y1 = 0;
if(y1 >= a.h) y1 = a.h-1;
if(y2 < 0) y2 = 0;
if(y2 >= a.h) y2 = a.h-1;
for(i = x1; i <= x2; ++i){
a.data[i + y1*a.w + 0*a.w*a.h] = r;
a.data[i + y2*a.w + 0*a.w*a.h] = r;
a.data[i + y1*a.w + 1*a.w*a.h] = g;
a.data[i + y2*a.w + 1*a.w*a.h] = g;
a.data[i + y1*a.w + 2*a.w*a.h] = b;
a.data[i + y2*a.w + 2*a.w*a.h] = b;
}
for(i = y1; i <= y2; ++i){
a.data[x1 + i*a.w + 0*a.w*a.h] = r;
a.data[x2 + i*a.w + 0*a.w*a.h] = r;
a.data[x1 + i*a.w + 1*a.w*a.h] = g;
a.data[x2 + i*a.w + 1*a.w*a.h] = g;
a.data[x1 + i*a.w + 2*a.w*a.h] = b;
a.data[x2 + i*a.w + 2*a.w*a.h] = b;
}
}
void draw_box_width(image a, int x1, int y1, int x2, int y2, int w, float r, float g, float b)
{
int i;
for(i = 0; i < w; ++i){
draw_box(a, x1+i, y1+i, x2-i, y2-i, r, g, b);
}
}
void draw_bbox(image a, box bbox, int w, float r, float g, float b)
{
int left = (bbox.x-bbox.w/2)*a.w;
int right = (bbox.x+bbox.w/2)*a.w;
int top = (bbox.y-bbox.h/2)*a.h;
int bot = (bbox.y+bbox.h/2)*a.h;
int i;
for(i = 0; i < w; ++i){
draw_box(a, left+i, top+i, right-i, bot-i, r, g, b);
}
}
image **load_alphabet()
{
int i, j;
const int nsize = 8;
image **alphabets = calloc(nsize, sizeof(image));
for(j = 0; j < nsize; ++j){
alphabets[j] = calloc(128, sizeof(image));
for(i = 32; i < 127; ++i){
char buff[256];
sprintf(buff, "data/labels/%d_%d.png", i, j);
alphabets[j][i] = load_image_color(buff, 0, 0);
}
}
return alphabets;
}
void draw_detections(image im, detection *dets, int num, float thresh, char **names, image **alphabet, int classes)
{
int i,j;
for(i = 0; i < num; ++i){
char labelstr[4096] = {0};
int class = -1;
for(j = 0; j < classes; ++j){
if (dets[i].prob[j] > thresh){
if (class < 0) {
strcat(labelstr, names[j]);
class = j;
} else {
strcat(labelstr, ", ");
strcat(labelstr, names[j]);
}
printf("%s: %.0f%%\n", names[j], dets[i].prob[j]*100);
}
}
if(class >= 0){
int width = im.h * .006;
/*
if(0){
width = pow(prob, 1./2.)*10+1;
alphabet = 0;
}
*/
//printf("%d %s: %.0f%%\n", i, names[class], prob*100);
int offset = class*123457 % classes;
float red = get_color(2,offset,classes);
float green = get_color(1,offset,classes);
float blue = get_color(0,offset,classes);
float rgb[3];
//width = prob*20+2;
rgb[0] = red;
rgb[1] = green;
rgb[2] = blue;
box b = dets[i].bbox;
//printf("%f %f %f %f\n", b.x, b.y, b.w, b.h);
int left = (b.x-b.w/2.)*im.w;
int right = (b.x+b.w/2.)*im.w;
int top = (b.y-b.h/2.)*im.h;
int bot = (b.y+b.h/2.)*im.h;
if(left < 0) left = 0;
if(right > im.w-1) right = im.w-1;
if(top < 0) top = 0;
if(bot > im.h-1) bot = im.h-1;
draw_box_width(im, left, top, right, bot, width, red, green, blue);
if (alphabet) {
image label = get_label(alphabet, labelstr, (im.h*.03));
draw_label(im, top + width, left, label, rgb);
free_image(label);
}
if (dets[i].mask){
image mask = float_to_image(14, 14, 1, dets[i].mask);
image resized_mask = resize_image(mask, b.w*im.w, b.h*im.h);
image tmask = threshold_image(resized_mask, .5);
embed_image(tmask, im, left, top);
free_image(mask);
free_image(resized_mask);
free_image(tmask);
}
}
}
}
void transpose_image(image im)
{
assert(im.w == im.h);
int n, m;
int c;
for(c = 0; c < im.c; ++c){
for(n = 0; n < im.w-1; ++n){
for(m = n + 1; m < im.w; ++m){
float swap = im.data[m + im.w*(n + im.h*c)];
im.data[m + im.w*(n + im.h*c)] = im.data[n + im.w*(m + im.h*c)];
im.data[n + im.w*(m + im.h*c)] = swap;
}
}
}
}
void rotate_image_cw(image im, int times)
{
assert(im.w == im.h);
times = (times + 400) % 4;
int i, x, y, c;
int n = im.w;
for(i = 0; i < times; ++i){
for(c = 0; c < im.c; ++c){
for(x = 0; x < n/2; ++x){
for(y = 0; y < (n-1)/2 + 1; ++y){
float temp = im.data[y + im.w*(x + im.h*c)];
im.data[y + im.w*(x + im.h*c)] = im.data[n-1-x + im.w*(y + im.h*c)];
im.data[n-1-x + im.w*(y + im.h*c)] = im.data[n-1-y + im.w*(n-1-x + im.h*c)];
im.data[n-1-y + im.w*(n-1-x + im.h*c)] = im.data[x + im.w*(n-1-y + im.h*c)];
im.data[x + im.w*(n-1-y + im.h*c)] = temp;
}
}
}
}
}
void flip_image(image a)
{
int i,j,k;
for(k = 0; k < a.c; ++k){
for(i = 0; i < a.h; ++i){
for(j = 0; j < a.w/2; ++j){
int index = j + a.w*(i + a.h*(k));
int flip = (a.w - j - 1) + a.w*(i + a.h*(k));
float swap = a.data[flip];
a.data[flip] = a.data[index];
a.data[index] = swap;
}
}
}
}
image image_distance(image a, image b)
{
int i,j;
image dist = make_image(a.w, a.h, 1);
for(i = 0; i < a.c; ++i){
for(j = 0; j < a.h*a.w; ++j){
dist.data[j] += pow(a.data[i*a.h*a.w+j]-b.data[i*a.h*a.w+j],2);
}
}
for(j = 0; j < a.h*a.w; ++j){
dist.data[j] = sqrt(dist.data[j]);
}
return dist;
}
void ghost_image(image source, image dest, int dx, int dy)
{
int x,y,k;
float max_dist = sqrt((-source.w/2. + .5)*(-source.w/2. + .5));
for(k = 0; k < source.c; ++k){
for(y = 0; y < source.h; ++y){
for(x = 0; x < source.w; ++x){
float dist = sqrt((x - source.w/2. + .5)*(x - source.w/2. + .5) + (y - source.h/2. + .5)*(y - source.h/2. + .5));
float alpha = (1 - dist/max_dist);
if(alpha < 0) alpha = 0;
float v1 = get_pixel(source, x,y,k);
float v2 = get_pixel(dest, dx+x,dy+y,k);
float val = alpha*v1 + (1-alpha)*v2;
set_pixel(dest, dx+x, dy+y, k, val);
}
}
}
}
void blocky_image(image im, int s)
{
int i,j,k;
for(k = 0; k < im.c; ++k){
for(j = 0; j < im.h; ++j){
for(i = 0; i < im.w; ++i){
im.data[i + im.w*(j + im.h*k)] = im.data[i/s*s + im.w*(j/s*s + im.h*k)];
}
}
}
}
void censor_image(image im, int dx, int dy, int w, int h)
{
int i,j,k;
int s = 32;
if(dx < 0) dx = 0;
if(dy < 0) dy = 0;
for(k = 0; k < im.c; ++k){
for(j = dy; j < dy + h && j < im.h; ++j){
for(i = dx; i < dx + w && i < im.w; ++i){
im.data[i + im.w*(j + im.h*k)] = im.data[i/s*s + im.w*(j/s*s + im.h*k)];
//im.data[i + j*im.w + k*im.w*im.h] = 0;
}
}
}
}
void embed_image(image source, image dest, int dx, int dy)
{
int x,y,k;
for(k = 0; k < source.c; ++k){
for(y = 0; y < source.h; ++y){
for(x = 0; x < source.w; ++x){
float val = get_pixel(source, x,y,k);
set_pixel(dest, dx+x, dy+y, k, val);
}
}
}
}
image collapse_image_layers(image source, int border)
{
int h = source.h;
h = (h+border)*source.c - border;
image dest = make_image(source.w, h, 1);
int i;
for(i = 0; i < source.c; ++i){
image layer = get_image_layer(source, i);
int h_offset = i*(source.h+border);
embed_image(layer, dest, 0, h_offset);
free_image(layer);
}
return dest;
}
void constrain_image(image im)
{
int i;
for(i = 0; i < im.w*im.h*im.c; ++i){
if(im.data[i] < 0) im.data[i] = 0;
if(im.data[i] > 1) im.data[i] = 1;
}
}
void normalize_image(image p)
{
int i;
float min = 9999999;
float max = -999999;
for(i = 0; i < p.h*p.w*p.c; ++i){
float v = p.data[i];
if(v < min) min = v;
if(v > max) max = v;
}
if(max - min < .000000001){
min = 0;
max = 1;
}
for(i = 0; i < p.c*p.w*p.h; ++i){
p.data[i] = (p.data[i] - min)/(max-min);
}
}
void normalize_image2(image p)
{
float *min = calloc(p.c, sizeof(float));
float *max = calloc(p.c, sizeof(float));
int i,j;
for(i = 0; i < p.c; ++i) min[i] = max[i] = p.data[i*p.h*p.w];
for(j = 0; j < p.c; ++j){
for(i = 0; i < p.h*p.w; ++i){
float v = p.data[i+j*p.h*p.w];
if(v < min[j]) min[j] = v;
if(v > max[j]) max[j] = v;
}
}
for(i = 0; i < p.c; ++i){
if(max[i] - min[i] < .000000001){
min[i] = 0;
max[i] = 1;
}
}
for(j = 0; j < p.c; ++j){
for(i = 0; i < p.w*p.h; ++i){
p.data[i+j*p.h*p.w] = (p.data[i+j*p.h*p.w] - min[j])/(max[j]-min[j]);
}
}
free(min);
free(max);
}
void copy_image_into(image src, image dest)
{
memcpy(dest.data, src.data, src.h*src.w*src.c*sizeof(float));
}
image copy_image(image p)
{
image copy = p;
copy.data = calloc(p.h*p.w*p.c, sizeof(float));
memcpy(copy.data, p.data, p.h*p.w*p.c*sizeof(float));
return copy;
}
void rgbgr_image(image im)
{
int i;
for(i = 0; i < im.w*im.h; ++i){
float swap = im.data[i];
im.data[i] = im.data[i+im.w*im.h*2];
im.data[i+im.w*im.h*2] = swap;
}
}
int show_image(image p, const char *name, int ms)
{
#ifdef OPENCV
int c = show_image_cv(p, name, ms);
return c;
#else
fprintf(stderr, "Not compiled with OpenCV, saving to %s.png instead\n", name);
save_image(p, name);
return -1;
#endif
}
void save_image_options(image im, const char *name, IMTYPE f, int quality)
{
char buff[256];
//sprintf(buff, "%s (%d)", name, windows);
if(f == PNG) sprintf(buff, "%s.png", name);
else if (f == BMP) sprintf(buff, "%s.bmp", name);
else if (f == TGA) sprintf(buff, "%s.tga", name);
else if (f == JPG) sprintf(buff, "%s.jpg", name);
else sprintf(buff, "%s.png", name);
unsigned char *data = calloc(im.w*im.h*im.c, sizeof(char));
int i,k;
for(k = 0; k < im.c; ++k){
for(i = 0; i < im.w*im.h; ++i){
data[i*im.c+k] = (unsigned char) (255*im.data[i + k*im.w*im.h]);
}
}
int success = 0;
if(f == PNG) success = stbi_write_png(buff, im.w, im.h, im.c, data, im.w*im.c);
else if (f == BMP) success = stbi_write_bmp(buff, im.w, im.h, im.c, data);
else if (f == TGA) success = stbi_write_tga(buff, im.w, im.h, im.c, data);
else if (f == JPG) success = stbi_write_jpg(buff, im.w, im.h, im.c, data, quality);
free(data);
if(!success) fprintf(stderr, "Failed to write image %s\n", buff);
}
//************************guoqing_revised
#ifdef NUMPY
image ndarray_to_image(unsigned char* src, long* shape, long* strides)
{
int h = shape[0];
int w = shape[1];
int c = shape[2];
int step_h = strides[0];
int step_w = strides[1];
int step_c = strides[2];
image im = make_image(w, h, c);
int i, j, k;
int index1, index2 = 0;
for(i = 0; i < h; ++i){
for(k=0;k h){
h = (h * max) / w;
w = max;
} else {
w = (w * max) / h;
h = max;
}
if(w == im.w && h == im.h) return im;
image resized = resize_image(im, w, h);
return resized;
}
image resize_min(image im, int min)
{
int w = im.w;
int h = im.h;
if(w < h){
h = (h * min) / w;
w = min;
} else {
w = (w * min) / h;
h = min;
}
if(w == im.w && h == im.h) return im;
image resized = resize_image(im, w, h);
return resized;
}
image random_crop_image(image im, int w, int h)
{
int dx = rand_int(0, im.w - w);
int dy = rand_int(0, im.h - h);
image crop = crop_image(im, dx, dy, w, h);
return crop;
}
augment_args random_augment_args(image im, float angle, float aspect, int low, int high, int w, int h)
{
augment_args a = {0};
aspect = rand_scale(aspect);
int r = rand_int(low, high);
int min = (im.h < im.w*aspect) ? im.h : im.w*aspect;
float scale = (float)r / min;
float rad = rand_uniform(-angle, angle) * TWO_PI / 360.;
float dx = (im.w*scale/aspect - w) / 2.;
float dy = (im.h*scale - w) / 2.;
//if(dx < 0) dx = 0;
//if(dy < 0) dy = 0;
dx = rand_uniform(-dx, dx);
dy = rand_uniform(-dy, dy);
a.rad = rad;
a.scale = scale;
a.w = w;
a.h = h;
a.dx = dx;
a.dy = dy;
a.aspect = aspect;
return a;
}
image random_augment_image(image im, float angle, float aspect, int low, int high, int w, int h)
{
augment_args a = random_augment_args(im, angle, aspect, low, high, w, h);
image crop = rotate_crop_image(im, a.rad, a.scale, a.w, a.h, a.dx, a.dy, a.aspect);
return crop;
}
float three_way_max(float a, float b, float c)
{
return (a > b) ? ( (a > c) ? a : c) : ( (b > c) ? b : c) ;
}
float three_way_min(float a, float b, float c)
{
return (a < b) ? ( (a < c) ? a : c) : ( (b < c) ? b : c) ;
}
void yuv_to_rgb(image im)
{
assert(im.c == 3);
int i, j;
float r, g, b;
float y, u, v;
for(j = 0; j < im.h; ++j){
for(i = 0; i < im.w; ++i){
y = get_pixel(im, i , j, 0);
u = get_pixel(im, i , j, 1);
v = get_pixel(im, i , j, 2);
r = y + 1.13983*v;
g = y + -.39465*u + -.58060*v;
b = y + 2.03211*u;
set_pixel(im, i, j, 0, r);
set_pixel(im, i, j, 1, g);
set_pixel(im, i, j, 2, b);
}
}
}
void rgb_to_yuv(image im)
{
assert(im.c == 3);
int i, j;
float r, g, b;
float y, u, v;
for(j = 0; j < im.h; ++j){
for(i = 0; i < im.w; ++i){
r = get_pixel(im, i , j, 0);
g = get_pixel(im, i , j, 1);
b = get_pixel(im, i , j, 2);
y = .299*r + .587*g + .114*b;
u = -.14713*r + -.28886*g + .436*b;
v = .615*r + -.51499*g + -.10001*b;
set_pixel(im, i, j, 0, y);
set_pixel(im, i, j, 1, u);
set_pixel(im, i, j, 2, v);
}
}
}
// http://www.cs.rit.edu/~ncs/color/t_convert.html
void rgb_to_hsv(image im)
{
assert(im.c == 3);
int i, j;
float r, g, b;
float h, s, v;
for(j = 0; j < im.h; ++j){
for(i = 0; i < im.w; ++i){
r = get_pixel(im, i , j, 0);
g = get_pixel(im, i , j, 1);
b = get_pixel(im, i , j, 2);
float max = three_way_max(r,g,b);
float min = three_way_min(r,g,b);
float delta = max - min;
v = max;
if(max == 0){
s = 0;
h = 0;
}else{
s = delta/max;
if(r == max){
h = (g - b) / delta;
} else if (g == max) {
h = 2 + (b - r) / delta;
} else {
h = 4 + (r - g) / delta;
}
if (h < 0) h += 6;
h = h/6.;
}
set_pixel(im, i, j, 0, h);
set_pixel(im, i, j, 1, s);
set_pixel(im, i, j, 2, v);
}
}
}
void hsv_to_rgb(image im)
{
assert(im.c == 3);
int i, j;
float r, g, b;
float h, s, v;
float f, p, q, t;
for(j = 0; j < im.h; ++j){
for(i = 0; i < im.w; ++i){
h = 6 * get_pixel(im, i , j, 0);
s = get_pixel(im, i , j, 1);
v = get_pixel(im, i , j, 2);
if (s == 0) {
r = g = b = v;
} else {
int index = floor(h);
f = h - index;
p = v*(1-s);
q = v*(1-s*f);
t = v*(1-s*(1-f));
if(index == 0){
r = v; g = t; b = p;
} else if(index == 1){
r = q; g = v; b = p;
} else if(index == 2){
r = p; g = v; b = t;
} else if(index == 3){
r = p; g = q; b = v;
} else if(index == 4){
r = t; g = p; b = v;
} else {
r = v; g = p; b = q;
}
}
set_pixel(im, i, j, 0, r);
set_pixel(im, i, j, 1, g);
set_pixel(im, i, j, 2, b);
}
}
}
void grayscale_image_3c(image im)
{
assert(im.c == 3);
int i, j, k;
float scale[] = {0.299, 0.587, 0.114};
for(j = 0; j < im.h; ++j){
for(i = 0; i < im.w; ++i){
float val = 0;
for(k = 0; k < 3; ++k){
val += scale[k]*get_pixel(im, i, j, k);
}
im.data[0*im.h*im.w + im.w*j + i] = val;
im.data[1*im.h*im.w + im.w*j + i] = val;
im.data[2*im.h*im.w + im.w*j + i] = val;
}
}
}
image grayscale_image(image im)
{
assert(im.c == 3);
int i, j, k;
image gray = make_image(im.w, im.h, 1);
float scale[] = {0.299, 0.587, 0.114};
for(k = 0; k < im.c; ++k){
for(j = 0; j < im.h; ++j){
for(i = 0; i < im.w; ++i){
gray.data[i+im.w*j] += scale[k]*get_pixel(im, i, j, k);
}
}
}
return gray;
}
image threshold_image(image im, float thresh)
{
int i;
image t = make_image(im.w, im.h, im.c);
for(i = 0; i < im.w*im.h*im.c; ++i){
t.data[i] = im.data[i]>thresh ? 1 : 0;
}
return t;
}
image blend_image(image fore, image back, float alpha)
{
assert(fore.w == back.w && fore.h == back.h && fore.c == back.c);
image blend = make_image(fore.w, fore.h, fore.c);
int i, j, k;
for(k = 0; k < fore.c; ++k){
for(j = 0; j < fore.h; ++j){
for(i = 0; i < fore.w; ++i){
float val = alpha * get_pixel(fore, i, j, k) +
(1 - alpha)* get_pixel(back, i, j, k);
set_pixel(blend, i, j, k, val);
}
}
}
return blend;
}
void scale_image_channel(image im, int c, float v)
{
int i, j;
for(j = 0; j < im.h; ++j){
for(i = 0; i < im.w; ++i){
float pix = get_pixel(im, i, j, c);
pix = pix*v;
set_pixel(im, i, j, c, pix);
}
}
}
void translate_image_channel(image im, int c, float v)
{
int i, j;
for(j = 0; j < im.h; ++j){
for(i = 0; i < im.w; ++i){
float pix = get_pixel(im, i, j, c);
pix = pix+v;
set_pixel(im, i, j, c, pix);
}
}
}
image binarize_image(image im)
{
image c = copy_image(im);
int i;
for(i = 0; i < im.w * im.h * im.c; ++i){
if(c.data[i] > .5) c.data[i] = 1;
else c.data[i] = 0;
}
return c;
}
void saturate_image(image im, float sat)
{
rgb_to_hsv(im);
scale_image_channel(im, 1, sat);
hsv_to_rgb(im);
constrain_image(im);
}
void hue_image(image im, float hue)
{
rgb_to_hsv(im);
int i;
for(i = 0; i < im.w*im.h; ++i){
im.data[i] = im.data[i] + hue;
if (im.data[i] > 1) im.data[i] -= 1;
if (im.data[i] < 0) im.data[i] += 1;
}
hsv_to_rgb(im);
constrain_image(im);
}
void exposure_image(image im, float sat)
{
rgb_to_hsv(im);
scale_image_channel(im, 2, sat);
hsv_to_rgb(im);
constrain_image(im);
}
void distort_image(image im, float hue, float sat, float val)
{
rgb_to_hsv(im);
scale_image_channel(im, 1, sat);
scale_image_channel(im, 2, val);
int i;
for(i = 0; i < im.w*im.h; ++i){
im.data[i] = im.data[i] + hue;
if (im.data[i] > 1) im.data[i] -= 1;
if (im.data[i] < 0) im.data[i] += 1;
}
hsv_to_rgb(im);
constrain_image(im);
}
void random_distort_image(image im, float hue, float saturation, float exposure)
{
float dhue = rand_uniform(-hue, hue);
float dsat = rand_scale(saturation);
float dexp = rand_scale(exposure);
distort_image(im, dhue, dsat, dexp);
}
void saturate_exposure_image(image im, float sat, float exposure)
{
rgb_to_hsv(im);
scale_image_channel(im, 1, sat);
scale_image_channel(im, 2, exposure);
hsv_to_rgb(im);
constrain_image(im);
}
image resize_image(image im, int w, int h)
{
image resized = make_image(w, h, im.c);
image part = make_image(w, im.h, im.c);
int r, c, k;
float w_scale = (float)(im.w - 1) / (w - 1);
float h_scale = (float)(im.h - 1) / (h - 1);
for(k = 0; k < im.c; ++k){
for(r = 0; r < im.h; ++r){
for(c = 0; c < w; ++c){
float val = 0;
if(c == w-1 || im.w == 1){
val = get_pixel(im, im.w-1, r, k);
} else {
float sx = c*w_scale;
int ix = (int) sx;
float dx = sx - ix;
val = (1 - dx) * get_pixel(im, ix, r, k) + dx * get_pixel(im, ix+1, r, k);
}
set_pixel(part, c, r, k, val);
}
}
}
for(k = 0; k < im.c; ++k){
for(r = 0; r < h; ++r){
float sy = r*h_scale;
int iy = (int) sy;
float dy = sy - iy;
for(c = 0; c < w; ++c){
float val = (1-dy) * get_pixel(part, c, iy, k);
set_pixel(resized, c, r, k, val);
}
if(r == h-1 || im.h == 1) continue;
for(c = 0; c < w; ++c){
float val = dy * get_pixel(part, c, iy+1, k);
add_pixel(resized, c, r, k, val);
}
}
}
free_image(part);
return resized;
}
void test_resize(char *filename)
{
image im = load_image(filename, 0,0, 3);
float mag = mag_array(im.data, im.w*im.h*im.c);
printf("L2 Norm: %f\n", mag);
image gray = grayscale_image(im);
image c1 = copy_image(im);
image c2 = copy_image(im);
image c3 = copy_image(im);
image c4 = copy_image(im);
distort_image(c1, .1, 1.5, 1.5);
distort_image(c2, -.1, .66666, .66666);
distort_image(c3, .1, 1.5, .66666);
distort_image(c4, .1, .66666, 1.5);
show_image(im, "Original", 1);
show_image(gray, "Gray", 1);
show_image(c1, "C1", 1);
show_image(c2, "C2", 1);
show_image(c3, "C3", 1);
show_image(c4, "C4", 1);
#ifdef OPENCV
while(1){
image aug = random_augment_image(im, 0, .75, 320, 448, 320, 320);
show_image(aug, "aug", 1);
free_image(aug);
float exposure = 1.15;
float saturation = 1.15;
float hue = .05;
image c = copy_image(im);
float dexp = rand_scale(exposure);
float dsat = rand_scale(saturation);
float dhue = rand_uniform(-hue, hue);
distort_image(c, dhue, dsat, dexp);
show_image(c, "rand", 1);
printf("%f %f %f\n", dhue, dsat, dexp);
free_image(c);
}
#endif
}
image load_image_stb(char *filename, int channels)
{
int w, h, c;
unsigned char *data = stbi_load(filename, &w, &h, &c, channels);
if (!data) {
fprintf(stderr, "Cannot load image \"%s\"\nSTB Reason: %s\n", filename, stbi_failure_reason());
exit(0);
}
if(channels) c = channels;
int i,j,k;
image im = make_image(w, h, c);
for(k = 0; k < c; ++k){
for(j = 0; j < h; ++j){
for(i = 0; i < w; ++i){
int dst_index = i + w*j + w*h*k;
int src_index = k + c*i + c*w*j;
im.data[dst_index] = (float)data[src_index]/255.;
}
}
}
free(data);
return im;
}
image load_image(char *filename, int w, int h, int c)
{
#ifdef OPENCV
image out = load_image_cv(filename, c);
#else
image out = load_image_stb(filename, c);
#endif
if((h && w) && (h != out.h || w != out.w)){
image resized = resize_image(out, w, h);
free_image(out);
out = resized;
}
return out;
}
image load_image_color(char *filename, int w, int h)
{
return load_image(filename, w, h, 3);
}
image get_image_layer(image m, int l)
{
image out = make_image(m.w, m.h, 1);
int i;
for(i = 0; i < m.h*m.w; ++i){
out.data[i] = m.data[i+l*m.h*m.w];
}
return out;
}
void print_image(image m)
{
int i, j, k;
for(i =0 ; i < m.c; ++i){
for(j =0 ; j < m.h; ++j){
for(k = 0; k < m.w; ++k){
printf("%.2lf, ", m.data[i*m.h*m.w + j*m.w + k]);
if(k > 30) break;
}
printf("\n");
if(j > 30) break;
}
printf("\n");
}
printf("\n");
}
image collapse_images_vert(image *ims, int n)
{
int color = 1;
int border = 1;
int h,w,c;
w = ims[0].w;
h = (ims[0].h + border) * n - border;
c = ims[0].c;
if(c != 3 || !color){
w = (w+border)*c - border;
c = 1;
}
image filters = make_image(w, h, c);
int i,j;
for(i = 0; i < n; ++i){
int h_offset = i*(ims[0].h+border);
image copy = copy_image(ims[i]);
//normalize_image(copy);
if(c == 3 && color){
embed_image(copy, filters, 0, h_offset);
}
else{
for(j = 0; j < copy.c; ++j){
int w_offset = j*(ims[0].w+border);
image layer = get_image_layer(copy, j);
embed_image(layer, filters, w_offset, h_offset);
free_image(layer);
}
}
free_image(copy);
}
return filters;
}
image collapse_images_horz(image *ims, int n)
{
int color = 1;
int border = 1;
int h,w,c;
int size = ims[0].h;
h = size;
w = (ims[0].w + border) * n - border;
c = ims[0].c;
if(c != 3 || !color){
h = (h+border)*c - border;
c = 1;
}
image filters = make_image(w, h, c);
int i,j;
for(i = 0; i < n; ++i){
int w_offset = i*(size+border);
image copy = copy_image(ims[i]);
//normalize_image(copy);
if(c == 3 && color){
embed_image(copy, filters, w_offset, 0);
}
else{
for(j = 0; j < copy.c; ++j){
int h_offset = j*(size+border);
image layer = get_image_layer(copy, j);
embed_image(layer, filters, w_offset, h_offset);
free_image(layer);
}
}
free_image(copy);
}
return filters;
}
//guoqing_add
/*void save_video(image p, CvVideoWriter* mVideoWriter)
{
image copy = copy_image(p);
if(p.c == 3) rgbgr_image(copy);
int x,y,k;
IplImage *disp = cvCreateImage(cvSize(p.w,p.h), IPL_DEPTH_8U, p.c);
int step = disp->widthStep;
for(y = 0; y < p.h; ++y){
for(x = 0; x < p.w; ++x){
for(k= 0; k < p.c; ++k){
disp->imageData[y*step + x*p.c + k] = (unsigned char)(get_pixel(copy,x,y,k)*255);
}
}
}
cvWriteFrame(mVideoWriter,disp);
cvReleaseImage(&disp);
free_image(copy);
}*/
void show_image_normalized(image im, const char *name)
{
image c = copy_image(im);
normalize_image(c);
show_image(c, name, 1);
free_image(c);
}
void show_images(image *ims, int n, char *window)
{
image m = collapse_images_vert(ims, n);
/*
int w = 448;
int h = ((float)m.h/m.w) * 448;
if(h > 896){
h = 896;
w = ((float)m.w/m.h) * 896;
}
image sized = resize_image(m, w, h);
*/
normalize_image(m);
save_image(m, window);
show_image(m, window, 1);
free_image(m);
}
void free_image(image m)
{
if(m.data){
free(m.data);
}
}
2.打开image.h
修改如下：其中//********************guoqing_revised之间的代码为新增代码
3.由于修改了.c 文件，所以需要修改对应的makefile文件，然后重新编译
完整代码如下，其中 #*********************guoqing_revised部分为新增代码
GPU=1
CUDNN=1
OPENCV=1
OPENMP=0
NUMPY=1
DEBUG=0
ARCH= -gencode arch=compute_30,code=sm_30 \
-gencode arch=compute_35,code=sm_35 \
-gencode arch=compute_50,code=[sm_50,compute_50] \
-gencode arch=compute_52,code=[sm_52,compute_52]
# -gencode arch=compute_20,code=[sm_20,sm_21] \ This one is deprecated?
# This is what I use, uncomment if you know your arch and want to specify
# ARCH= -gencode arch=compute_52,code=compute_52
VPATH=./src/:./examples
SLIB=libdarknet.so
ALIB=libdarknet.a
EXEC=darknet
OBJDIR=./obj/
CC=gcc
CPP=g++
NVCC=nvcc
AR=ar
ARFLAGS=rcs
OPTS=-Ofast
LDFLAGS= -lm -pthread
COMMON= -Iinclude/ -Isrc/
CFLAGS=-Wall -Wno-unused-result -Wno-unknown-pragmas -Wfatal-errors -fPIC
ifeq ($(OPENMP), 1)
CFLAGS+= -fopenmp
endif
ifeq ($(DEBUG), 1)
OPTS=-O0 -g
endif
CFLAGS+=$(OPTS)
ifeq ($(OPENCV), 1)
COMMON+= -DOPENCV
CFLAGS+= -DOPENCV
LDFLAGS+= `pkg-config --libs opencv` -lstdc++
COMMON+= `pkg-config --cflags opencv`
endif
#*****************guoqing_revised
ifeq ($(NUMPY), 1)
COMMON+= -DNUMPY -I/usr/include/python2.7/ -I/usr/lib/python2.7/dist-packages/numpy/core/include/numpy/
CFLAGS+= -DNUMPY
endif
#*****************guoqing_revised
ifeq ($(GPU), 1)
COMMON+= -DGPU -I/usr/local/cuda/include/
CFLAGS+= -DGPU
LDFLAGS+= -L/usr/local/cuda/lib64 -lcuda -lcudart -lcublas -lcurand
endif
ifeq ($(CUDNN), 1)
COMMON+= -DCUDNN
CFLAGS+= -DCUDNN
LDFLAGS+= -lcudnn
endif
OBJ=gemm.o utils.o cuda.o deconvolutional_layer.o convolutional_layer.o list.o image.o activations.o im2col.o col2im.o blas.o crop_layer.o dropout_layer.o maxpool_layer.o softmax_layer.o data.o matrix.o network.o connected_layer.o cost_layer.o parser.o option_list.o detection_layer.o route_layer.o upsample_layer.o box.o normalization_layer.o avgpool_layer.o layer.o local_layer.o shortcut_layer.o logistic_layer.o activation_layer.o rnn_layer.o gru_layer.o crnn_layer.o demo.o batchnorm_layer.o region_layer.o reorg_layer.o tree.o lstm_layer.o l2norm_layer.o yolo_layer.o iseg_layer.o image_opencv.o
EXECOBJA=captcha.o lsd.o super.o art.o tag.o cifar.o go.o rnn.o segmenter.o regressor.o classifier.o coco.o yolo.o detector.o nightmare.o instance-segmenter.o darknet.o
ifeq ($(GPU), 1)
LDFLAGS+= -lstdc++
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 avgpool_layer_kernels.o
endif
EXECOBJ = $(addprefix $(OBJDIR), $(EXECOBJA))
OBJS = $(addprefix $(OBJDIR), $(OBJ))
DEPS = $(wildcard src/*.h) Makefile include/darknet.h
all: obj backup results $(SLIB) $(ALIB) $(EXEC)
#all: obj results $(SLIB) $(ALIB) $(EXEC)
$(EXEC): $(EXECOBJ) $(ALIB)
$(CC) $(COMMON) $(CFLAGS) $^ -o $@ $(LDFLAGS) $(ALIB)
$(ALIB): $(OBJS)
$(AR) $(ARFLAGS) $@ $^
$(SLIB): $(OBJS)
$(CC) $(CFLAGS) -shared $^ -o $@ $(LDFLAGS)
$(OBJDIR)%.o: %.cpp $(DEPS)
$(CPP) $(COMMON) $(CFLAGS) -c $< -o $@
$(OBJDIR)%.o: %.c $(DEPS)
$(CC) $(COMMON) $(CFLAGS) -c $< -o $@
$(OBJDIR)%.o: %.cu $(DEPS)
$(NVCC) $(ARCH) $(COMMON) --compiler-options "$(CFLAGS)" -c $< -o $@
obj:
mkdir -p obj
backup:
mkdir -p backup
results:
mkdir -p results
.PHONY: clean
clean:
rm -rf $(OBJS) $(SLIB) $(ALIB) $(EXEC) $(EXECOBJ) $(OBJDIR)/*
4.最后make clean ，然后make将编译产生的libdarknet.so文件(如下图)拷贝到python目录下即可
5、darknet的python目录下有一个darknet.py文件如下：
修改后的完整文件如下图，其中#************************guoqing_revised 之间的为添加的代码
from ctypes import *
import math
import random
#************************guoqing_revised
import cv2
#************************guoqing_revised
def sample(probs):
s = sum(probs)
probs = [a/s for a in probs]
r = random.uniform(0, 1)
for i in range(len(probs)):
r = r - probs[i]
if r <= 0:
return i
return len(probs)-1
def c_array(ctype, values):
arr = (ctype*len(values))()
arr[:] = values
return arr
class BOX(Structure):
_fields_ = [("x", c_float),
("y", c_float),
("w", c_float),
("h", c_float)]
class DETECTION(Structure):
_fields_ = [("bbox", BOX),
("classes", c_int),
("prob", POINTER(c_float)),
("mask", POINTER(c_float)),
("objectness", c_float),
("sort_class", c_int)]
class IMAGE(Structure):
_fields_ = [("w", c_int),
("h", c_int),
("c", c_int),
("data", POINTER(c_float))]
class METADATA(Structure):
_fields_ = [("classes", c_int),
("names", POINTER(c_char_p))]
#lib = CDLL("/home/pjreddie/documents/darknet/libdarknet.so", RTLD_GLOBAL)
lib = CDLL("libdarknet.so", RTLD_GLOBAL)
lib.network_width.argtypes = [c_void_p]
lib.network_width.restype = c_int
lib.network_height.argtypes = [c_void_p]
lib.network_height.restype = c_int
predict = lib.network_predict
predict.argtypes = [c_void_p, POINTER(c_float)]
predict.restype = POINTER(c_float)
set_gpu = lib.cuda_set_device
set_gpu.argtypes = [c_int]
make_image = lib.make_image
make_image.argtypes = [c_int, c_int, c_int]
make_image.restype = IMAGE
get_network_boxes = lib.get_network_boxes
get_network_boxes.argtypes = [c_void_p, c_int, c_int, c_float, c_float, POINTER(c_int), c_int, POINTER(c_int)]
get_network_boxes.restype = POINTER(DETECTION)
make_network_boxes = lib.make_network_boxes
make_network_boxes.argtypes = [c_void_p]
make_network_boxes.restype = POINTER(DETECTION)
free_detections = lib.free_detections
free_detections.argtypes = [POINTER(DETECTION), c_int]
free_ptrs = lib.free_ptrs
free_ptrs.argtypes = [POINTER(c_void_p), c_int]
network_predict = lib.network_predict
network_predict.argtypes = [c_void_p, POINTER(c_float)]
reset_rnn = lib.reset_rnn
reset_rnn.argtypes = [c_void_p]
load_net = lib.load_network
load_net.argtypes = [c_char_p, c_char_p, c_int]
load_net.restype = c_void_p
do_nms_obj = lib.do_nms_obj
do_nms_obj.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]
do_nms_sort = lib.do_nms_sort
do_nms_sort.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]
free_image = lib.free_image
free_image.argtypes = [IMAGE]
letterbox_image = lib.letterbox_image
letterbox_image.argtypes = [IMAGE, c_int, c_int]
letterbox_image.restype = IMAGE
load_meta = lib.get_metadata
lib.get_metadata.argtypes = [c_char_p]
lib.get_metadata.restype = METADATA
load_image = lib.load_image_color
load_image.argtypes = [c_char_p, c_int, c_int]
load_image.restype = IMAGE
rgbgr_image = lib.rgbgr_image
rgbgr_image.argtypes = [IMAGE]
predict_image = lib.network_predict_image
predict_image.argtypes = [c_void_p, IMAGE]
predict_image.restype = POINTER(c_float)
def classify(net, meta, im):
out = predict_image(net, im)
res = []
for i in range(meta.classes):
res.append((meta.names[i], out[i]))
res = sorted(res, key=lambda x: -x[1])
return res
#def detect(net, meta, image, thresh=.5, hier_thresh=.5, nms=.45):
def detect(net, meta, im, thresh=.35, hier_thresh=.5, nms=.45):
#im = load_image(image, 0, 0)
num = c_int(0)
pnum = pointer(num)
predict_image(net, im)
dets = get_network_boxes(net, im.w, im.h, thresh, hier_thresh, None, 0, pnum)
num = pnum[0]
if (nms): do_nms_obj(dets, num, meta.classes, nms);
res = []
for j in range(num):
for i in range(meta.classes):
if dets[j].prob[i] > 0:
b = dets[j].bbox
res.append((meta.names[i], dets[j].prob[i], (b.x, b.y, b.w, b.h)))
res = sorted(res, key=lambda x: -x[1])
free_image(im)
free_detections(dets, num)
return res
#************************guoqing_revised
def nparray_to_image(img):
data = img.ctypes.data_as(POINTER(c_ubyte))
image = ndarray_image(data,img.ctypes.shape,img.ctypes.strides)
return image
ndarray_image = lib.ndarray_to_image
ndarray_image.argtypes = [POINTER(c_ubyte), POINTER(c_long), POINTER(c_long)]
ndarray_image.restype = IMAGE
#************************guoqing_revised
if __name__ == "__main__":
#net = load_net("cfg/densenet201.cfg", "/home/pjreddie/trained/densenet201.weights", 0)
#im = load_image("data/wolf.jpg", 0, 0)
#meta = load_meta("cfg/imagenet1k.data")
#r = classify(net, meta, im)
#print r[:10]
#guoqing annotation
#net = load_net("cfg/tiny-yolo.cfg", "tiny-yolo.weights", 0)
#meta = load_meta("cfg/coco.data")
#r = detect(net, meta, "data/dog.jpg")
#print r
#************************guoqing_revised
net = load_net("../cfg/yolov3-voc.cfg","../backup/yolov3-voc_20000.weights",0)
meta = load_meta("../cfg/voc.data")
vid = cv2.VideoCapture("../two_express.mp4")
fourcc =cv2.VideoWriter_fourcc('M','P','4','2')
videoWriter = cv2.VideoWriter('../output.avi',fourcc,25,(544,960))
while True:
return_value,arr = vid.read()
if not return_value:
break
im = nparray_to_image(arr)
boxes = detect(net,meta,im)
for i in range(len(boxes)):
score = boxes[i][1]
label = boxes[i][0]
xmin = boxes[i][2][0] - boxes[i][2][2]/2
ymin=boxes[i][2][1]-boxes[i][2][3]/2
xmax=boxes[i][2][0]+boxes[i][2][2]/2
ymax=boxes[i][2][1]+boxes[i][2][3]/2
cv2.rectangle(arr,(int(xmin),int(ymin)),(int(xmax),int(ymax)),(0,255,0),2)
cv2.putText(arr,str(label),(int(xmin),int(ymin)),fontFace = cv2.FONT_HERSHEY_SIMPLEX, fontScale=0.8, color=(0,255,255),thickness=2)
cv2.imshow("Canvas", arr)
videoWriter.write(arr)
cv2.waitKey(1)
cv2.destroyAllWindows()
#************************guoqing_revised
6.在python目录下,执行python darknet.py指令，测试看结果
python darknet.py可以看到载darknet目录下生成了检测视频 output.avi，能正常打开，表示成功
有问题欢迎讨论交流