LEGO brick detection using the KV260 and YoloV3-tiny

GPU=0
CUDNN=0
CUDNN_HALF=0
OPENCV=1
AVX=0
OPENMP=0
LIBSO=0
ZED_CAMERA=0
ZED_CAMERA_v2_8=0

# set GPU=1 and CUDNN=1 to speedup on GPU
# set CUDNN_HALF=1 to further speedup 3 x times (Mixed-precision on Tensor Cores) GPU: Volta, Xavier, Turing and higher
# set AVX=1 and OPENMP=1 to speedup on CPU (if error occurs then set AVX=0)
# set ZED_CAMERA=1 to enable ZED SDK 3.0 and above
# set ZED_CAMERA_v2_8=1 to enable ZED SDK 2.X

USE_CPP=0
DEBUG=0

ARCH= -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_61,code=[sm_61,compute_61]

OS := $(shell uname)

# GeForce RTX 3070, 3080, 3090
# ARCH= -gencode arch=compute_86,code=[sm_86,compute_86]

# Kepler GeForce GTX 770, GTX 760, GT 740
# ARCH= -gencode arch=compute_30,code=sm_30

# Tesla A100 (GA100), DGX-A100, RTX 3080
# ARCH= -gencode arch=compute_80,code=[sm_80,compute_80]

# Tesla V100
# ARCH= -gencode arch=compute_70,code=[sm_70,compute_70]

# GeForce RTX 2080 Ti, RTX 2080, RTX 2070, Quadro RTX 8000, Quadro RTX 6000, Quadro RTX 5000, Tesla T4, XNOR Tensor Cores
# ARCH= -gencode arch=compute_75,code=[sm_75,compute_75]

# Jetson XAVIER
# ARCH= -gencode arch=compute_72,code=[sm_72,compute_72]

# GTX 1080, GTX 1070, GTX 1060, GTX 1050, GTX 1030, Titan Xp, Tesla P40, Tesla P4
# ARCH= -gencode arch=compute_61,code=sm_61 -gencode arch=compute_61,code=compute_61

# GP100/Tesla P100 - DGX-1
# ARCH= -gencode arch=compute_60,code=sm_60

# For Jetson TX1, Tegra X1, DRIVE CX, DRIVE PX - uncomment:
# ARCH= -gencode arch=compute_53,code=[sm_53,compute_53]

# For Jetson Tx2 or Drive-PX2 uncomment:
# ARCH= -gencode arch=compute_62,code=[sm_62,compute_62]

# For Tesla GA10x cards, RTX 3090, RTX 3080, RTX 3070, RTX A6000, RTX A40 uncomment:
# ARCH= -gencode arch=compute_86,code=[sm_86,compute_86]


VPATH=./src/
EXEC=darknet
OBJDIR=./obj/

ifeq ($(LIBSO), 1)
LIBNAMESO=libdarknet.so
APPNAMESO=uselib
endif

ifeq ($(USE_CPP), 1)
CC=g++
else
CC=gcc
endif

CPP=g++ -std=c++11
NVCC=nvcc
OPTS=-Ofast
LDFLAGS= -lm -pthread
COMMON= -Iinclude/ -I3rdparty/stb/include
CFLAGS=-Wall -Wfatal-errors -Wno-unused-result -Wno-unknown-pragmas -fPIC

ifeq ($(DEBUG), 1)
#OPTS= -O0 -g
#OPTS= -Og -g
COMMON+= -DDEBUG
CFLAGS+= -DDEBUG
else
ifeq ($(AVX), 1)
CFLAGS+= -ffp-contract=fast -mavx -mavx2 -msse3 -msse4.1 -msse4.2 -msse4a
endif
endif

CFLAGS+=$(OPTS)

ifneq (,$(findstring MSYS_NT,$(OS)))
LDFLAGS+=-lws2_32
endif

ifeq ($(OPENCV), 1)
COMMON+= -DOPENCV
CFLAGS+= -DOPENCV
LDFLAGS+= `pkg-config --libs opencv4 2> /dev/null || pkg-config --libs opencv`
COMMON+= `pkg-config --cflags opencv4 2> /dev/null || pkg-config --cflags opencv`
endif

ifeq ($(OPENMP), 1)
    ifeq ($(OS),Darwin) #MAC
	    CFLAGS+= -Xpreprocessor -fopenmp
	else
		CFLAGS+= -fopenmp
	endif
LDFLAGS+= -lgomp
endif

ifeq ($(GPU), 1)
COMMON+= -DGPU -I/usr/local/cuda/include/
CFLAGS+= -DGPU
ifeq ($(OS),Darwin) #MAC
LDFLAGS+= -L/usr/local/cuda/lib -lcuda -lcudart -lcublas -lcurand
else
LDFLAGS+= -L/usr/local/cuda/lib64 -lcuda -lcudart -lcublas -lcurand
endif
endif

ifeq ($(CUDNN), 1)
COMMON+= -DCUDNN
ifeq ($(OS),Darwin) #MAC
CFLAGS+= -DCUDNN -I/usr/local/cuda/include
LDFLAGS+= -L/usr/local/cuda/lib -lcudnn
else
CFLAGS+= -DCUDNN -I/usr/local/cudnn/include
LDFLAGS+= -L/usr/local/cudnn/lib64 -lcudnn
endif
endif

ifeq ($(CUDNN_HALF), 1)
COMMON+= -DCUDNN_HALF
CFLAGS+= -DCUDNN_HALF
ARCH+= -gencode arch=compute_70,code=[sm_70,compute_70]
endif

ifeq ($(ZED_CAMERA), 1)
CFLAGS+= -DZED_STEREO -I/usr/local/zed/include
ifeq ($(ZED_CAMERA_v2_8), 1)
LDFLAGS+= -L/usr/local/zed/lib -lsl_core -lsl_input -lsl_zed
#-lstdc++ -D_GLIBCXX_USE_CXX11_ABI=0
else
LDFLAGS+= -L/usr/local/zed/lib -lsl_zed
#-lstdc++ -D_GLIBCXX_USE_CXX11_ABI=0
endif
endif

OBJ=image_opencv.o http_stream.o gemm.o utils.o dark_cuda.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 captcha.o route_layer.o writing.o box.o nightmare.o normalization_layer.o avgpool_layer.o coco.o dice.o yolo.o detector.o layer.o compare.o classifier.o local_layer.o swag.o shortcut_layer.o representation_layer.o activation_layer.o rnn_layer.o gru_layer.o rnn.o rnn_vid.o crnn_layer.o demo.o tag.o cifar.o go.o batchnorm_layer.o art.o region_layer.o reorg_layer.o reorg_old_layer.o super.o voxel.o tree.o yolo_layer.o gaussian_yolo_layer.o upsample_layer.o lstm_layer.o conv_lstm_layer.o scale_channels_layer.o sam_layer.o
ifeq ($(GPU), 1)
LDFLAGS+= -lstdc++
OBJ+=convolutional_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 network_kernels.o avgpool_layer_kernels.o
endif

OBJS = $(addprefix $(OBJDIR), $(OBJ))
DEPS = $(wildcard src/*.h) Makefile include/darknet.h

all: $(OBJDIR) backup results setchmod $(EXEC) $(LIBNAMESO) $(APPNAMESO)

ifeq ($(LIBSO), 1)
CFLAGS+= -fPIC

$(LIBNAMESO): $(OBJDIR) $(OBJS) include/yolo_v2_class.hpp src/yolo_v2_class.cpp
	$(CPP) -shared -std=c++11 -fvisibility=hidden -DLIB_EXPORTS $(COMMON) $(CFLAGS) $(OBJS) src/yolo_v2_class.cpp -o $@ $(LDFLAGS)

$(APPNAMESO): $(LIBNAMESO) include/yolo_v2_class.hpp src/yolo_console_dll.cpp
	$(CPP) -std=c++11 $(COMMON) $(CFLAGS) -o $@ src/yolo_console_dll.cpp $(LDFLAGS) -L ./ -l:$(LIBNAMESO)
endif

$(EXEC): $(OBJS)
	$(CPP) -std=c++11 $(COMMON) $(CFLAGS) $^ -o $@ $(LDFLAGS)

$(OBJDIR)%.o: %.c $(DEPS)
	$(CC) $(COMMON) $(CFLAGS) -c $< -o $@

$(OBJDIR)%.o: %.cpp $(DEPS)
	$(CPP) -std=c++11 $(COMMON) $(CFLAGS) -c $< -o $@

$(OBJDIR)%.o: %.cu $(DEPS)
	$(NVCC) $(ARCH) $(COMMON) --compiler-options "$(CFLAGS)" -c $< -o $@

$(OBJDIR):
	mkdir -p $(OBJDIR)
backup:
	mkdir -p backup
results:
	mkdir -p results
setchmod:
	chmod +x *.sh

.PHONY: clean

clean:
	rm -rf $(OBJS) $(EXEC) $(LIBNAMESO) $(APPNAMESO)

#ifndef _GNU_SOURCE
#define _GNU_SOURCE
#endif
#include "image.h"
#include "utils.h"
#include "blas.h"
#include "dark_cuda.h"
#include <stdio.h>
#ifndef _USE_MATH_DEFINES
#define _USE_MATH_DEFINES
#endif
#include <math.h>

#ifndef STB_IMAGE_IMPLEMENTATION
#define STB_IMAGE_IMPLEMENTATION
#include "stb_image.h"
#endif
#ifndef STB_IMAGE_WRITE_IMPLEMENTATION
#define STB_IMAGE_WRITE_IMPLEMENTATION
#include "stb_image_write.h"
#endif

extern int check_mistakes;
//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;
}

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;
}

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)
{
    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;
}

image get_label_v3(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*.05);
    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_weighted_label(image a, int r, int c, image label, const float *rgb, const float alpha)
{
    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 val1 = get_pixel(label, i, j, k);
                float val2 = get_pixel(a, i + c, j + r, k);
                float val_dst = val1 * rgb[k] * alpha + val2 * (1 - alpha);
                set_pixel(a, i + c, j + r, k, val_dst);
            }
        }
    }
}

void draw_box_bw(image a, int x1, int y1, int x2, int y2, float brightness)
{
    //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] = brightness;
        a.data[i + y2*a.w + 0 * a.w*a.h] = brightness;
    }
    for (i = y1; i <= y2; ++i) {
        a.data[x1 + i*a.w + 0 * a.w*a.h] = brightness;
        a.data[x2 + i*a.w + 0 * a.w*a.h] = brightness;
    }
}

void draw_box_width_bw(image a, int x1, int y1, int x2, int y2, int w, float brightness)
{
    int i;
    for (i = 0; i < w; ++i) {
        float alternate_color = (w % 2) ? (brightness) : (1.0 - brightness);
        draw_box_bw(a, x1 + i, y1 + i, x2 - i, y2 - i, alternate_color);
    }
}

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 = (image**)xcalloc(nsize, sizeof(image*));
    for(j = 0; j < nsize; ++j){
        alphabets[j] = (image*)xcalloc(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;
}



// Creates array of detections with prob > thresh and fills best_class for them
detection_with_class* get_actual_detections(detection *dets, int dets_num, float thresh, int* selected_detections_num, char **names)
{
    int selected_num = 0;
    detection_with_class* result_arr = (detection_with_class*)xcalloc(dets_num, sizeof(detection_with_class));
    int i;
    for (i = 0; i < dets_num; ++i) {
        int best_class = -1;
        float best_class_prob = thresh;
        int j;
        for (j = 0; j < dets[i].classes; ++j) {
            int show = strncmp(names[j], "dont_show", 9);
            if (dets[i].prob[j] > best_class_prob && show) {
                best_class = j;
                best_class_prob = dets[i].prob[j];
            }
        }
        if (best_class >= 0) {
            result_arr[selected_num].det = dets[i];
            result_arr[selected_num].best_class = best_class;
            ++selected_num;
        }
    }
    if (selected_detections_num)
        *selected_detections_num = selected_num;
    return result_arr;
}

// compare to sort detection** by bbox.x
int compare_by_lefts(const void *a_ptr, const void *b_ptr) {
    const detection_with_class* a = (detection_with_class*)a_ptr;
    const detection_with_class* b = (detection_with_class*)b_ptr;
    const float delta = (a->det.bbox.x - a->det.bbox.w/2) - (b->det.bbox.x - b->det.bbox.w/2);
    return delta < 0 ? -1 : delta > 0 ? 1 : 0;
}

// compare to sort detection** by best_class probability
int compare_by_probs(const void *a_ptr, const void *b_ptr) {
    const detection_with_class* a = (detection_with_class*)a_ptr;
    const detection_with_class* b = (detection_with_class*)b_ptr;
    float delta = a->det.prob[a->best_class] - b->det.prob[b->best_class];
    return delta < 0 ? -1 : delta > 0 ? 1 : 0;
}

void draw_detections_v3(image im, detection *dets, int num, float thresh, char **names, image **alphabet, int classes, int ext_output)
{
    static int frame_id = 0;
    frame_id++;

    int selected_detections_num;
    detection_with_class* selected_detections = get_actual_detections(dets, num, thresh, &selected_detections_num, names);

    // text output
    qsort(selected_detections, selected_detections_num, sizeof(*selected_detections), compare_by_lefts);
    int i;
    for (i = 0; i < selected_detections_num; ++i) {
        const int best_class = selected_detections[i].best_class;
        printf("extract:%s: %.0f%%", names[best_class],    selected_detections[i].det.prob[best_class] * 100);
        if (ext_output)
            printf("\t(left_x: %4.0f:   top_y: %4.0f:   width: %4.0f:   height: %4.0f:)\n",
                round((selected_detections[i].det.bbox.x - selected_detections[i].det.bbox.w / 2)*im.w),
                round((selected_detections[i].det.bbox.y - selected_detections[i].det.bbox.h / 2)*im.h),
                round(selected_detections[i].det.bbox.w*im.w), round(selected_detections[i].det.bbox.h*im.h));
        else
            printf("\n");
        int j;
        for (j = 0; j < classes; ++j) {
            if (selected_detections[i].det.prob[j] > thresh && j != best_class) {
                printf("extract:%s: %.0f%%", names[j], selected_detections[i].det.prob[j] * 100);

                if (ext_output)
                    printf("\t(left_x: %4.0f:   top_y: %4.0f:   width: %4.0f:   height: %4.0f:)\n",
                        round((selected_detections[i].det.bbox.x - selected_detections[i].det.bbox.w / 2)*im.w),
                        round((selected_detections[i].det.bbox.y - selected_detections[i].det.bbox.h / 2)*im.h),
                        round(selected_detections[i].det.bbox.w*im.w), round(selected_detections[i].det.bbox.h*im.h));
                else
                    printf("\n");
            }
        }
    }

    // image output
    qsort(selected_detections, selected_detections_num, sizeof(*selected_detections), compare_by_probs);
    for (i = 0; i < selected_detections_num; ++i) {
            int width = im.h * .002;
            if (width < 1)
                width = 1;

            /*
            if(0){
            width = pow(prob, 1./2.)*10+1;
            alphabet = 0;
            }
            */

            //printf("%d %s: %.0f%%\n", i, names[selected_detections[i].best_class], prob*100);
            int offset = selected_detections[i].best_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 = selected_detections[i].det.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;

            //int b_x_center = (left + right) / 2;
            //int b_y_center = (top + bot) / 2;
            //int b_width = right - left;
            //int b_height = bot - top;
            //sprintf(labelstr, "%d x %d - w: %d, h: %d", b_x_center, b_y_center, b_width, b_height);

            // you should create directory: result_img
            //static int copied_frame_id = -1;
            //static image copy_img;
            //if (copied_frame_id != frame_id) {
            //    copied_frame_id = frame_id;
            //    if (copy_img.data) free_image(copy_img);
            //    copy_img = copy_image(im);
            //}
            //image cropped_im = crop_image(copy_img, left, top, right - left, bot - top);
            //static int img_id = 0;
            //img_id++;
            //char image_name[1024];
            //int best_class_id = selected_detections[i].best_class;
            //sprintf(image_name, "result_img/img_%d_%d_%d_%s.jpg", frame_id, img_id, best_class_id, names[best_class_id]);
            //save_image(cropped_im, image_name);
            //free_image(cropped_im);

            if (im.c == 1) {
                draw_box_width_bw(im, left, top, right, bot, width, 0.8);    // 1 channel Black-White
            }
            else {
                draw_box_width(im, left, top, right, bot, width, red, green, blue); // 3 channels RGB
            }
            if (alphabet) {
                char labelstr[4096] = { 0 };
                strcat(labelstr, names[selected_detections[i].best_class]);
                char prob_str[10];
                sprintf(prob_str, ": %.2f", selected_detections[i].det.prob[selected_detections[i].best_class]);
                strcat(labelstr, prob_str);
                int j;
                for (j = 0; j < classes; ++j) {
                    if (selected_detections[i].det.prob[j] > thresh && j != selected_detections[i].best_class) {
                        strcat(labelstr, ", ");
                        strcat(labelstr, names[j]);
                    }
                }
                image label = get_label_v3(alphabet, labelstr, (im.h*.02));
                //draw_label(im, top + width, left, label, rgb);
                draw_weighted_label(im, top + width, left, label, rgb, 0.7);
                free_image(label);
            }
            if (selected_detections[i].det.mask) {
                image mask = float_to_image(14, 14, 1, selected_detections[i].det.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);
            }
    }
    free(selected_detections);
}

void draw_detections(image im, int num, float thresh, box *boxes, float **probs, char **names, image **alphabet, int classes)
{
    int i;

    for(i = 0; i < num; ++i){
        int class_id = max_index(probs[i], classes);
        float prob = probs[i][class_id];
        if(prob > thresh){

            //// for comparison with OpenCV version of DNN Darknet Yolo v2
            //printf("\n %f, %f, %f, %f, ", boxes[i].x, boxes[i].y, boxes[i].w, boxes[i].h);
            // int k;
            //for (k = 0; k < classes; ++k) {
            //    printf("%f, ", probs[i][k]);
            //}
            //printf("\n");

            int width = im.h * .012;

            if(0){
                width = pow(prob, 1./2.)*10+1;
                alphabet = 0;
            }

            int offset = class_id*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 = boxes[i];

            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;
            printf("%s: %.0f%%", names[class_id], prob * 100);

            printf(" - id: %d, x_center: %d, y_center: %d, width: %d, height: %d",
                class_id, (right + left) / 2, (bot - top) / 2, right - left, bot - top);

            printf("\n");
            draw_box_width(im, left, top, right, bot, width, red, green, blue);
            if (alphabet) {
                image label = get_label(alphabet, names[class_id], (im.h*.03)/10);
                draw_label(im, top + width, left, label, rgb);
            }
        }
    }
}

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 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 = (float*)xcalloc(p.c, sizeof(float));
    float* max = (float*)xcalloc(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_inplace(image src, image dst)
{
    memcpy(dst.data, src.data, src.h*src.w*src.c * sizeof(float));
}

image copy_image(image p)
{
    image copy = p;
    copy.data = (float*)xcalloc(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;
    }
}

void show_image(image p, const char *name)
{
#ifdef OPENCV
    show_image_cv(p, name);
#else
    fprintf(stderr, "Not compiled with OpenCV, saving to %s.png instead\n", name);
    save_image(p, name);
#endif  // OPENCV
}

void save_image_png(image im, const char *name)
{
    char buff[256];
    //sprintf(buff, "%s (%d)", name, windows);
    sprintf(buff, "%s.png", name);
    unsigned char* data = (unsigned char*)xcalloc(im.w * im.h * im.c, sizeof(unsigned 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 = stbi_write_png(buff, im.w, im.h, im.c, data, im.w*im.c);
    free(data);
    if(!success) fprintf(stderr, "Failed to write image %s\n", buff);
}

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 = (unsigned char*)xcalloc(im.w * im.h * im.c, sizeof(unsigned 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);
}

void save_image(image im, const char *name)
{
    save_image_options(im, name, JPG, 80);
}

void save_image_jpg(image p, const char *name)
{
    save_image_options(p, name, JPG, 80);
}

void show_image_layers(image p, char *name)
{
    int i;
    char buff[256];
    for(i = 0; i < p.c; ++i){
        sprintf(buff, "%s - Layer %d", name, i);
        image layer = get_image_layer(p, i);
        show_image(layer, buff);
        free_image(layer);
    }
}

void show_image_collapsed(image p, char *name)
{
    image c = collapse_image_layers(p, 1);
    show_image(c, name);
    free_image(c);
}

image make_empty_image(int w, int h, int c)
{
    image out;
    out.data = 0;
    out.h = h;
    out.w = w;
    out.c = c;
    return out;
}

image make_image(int w, int h, int c)
{
    image out = make_empty_image(w,h,c);
    out.data = (float*)xcalloc(h * w * c, sizeof(float));
    return out;
}

image make_random_image(int w, int h, int c)
{
    image out = make_empty_image(w,h,c);
    out.data = (float*)xcalloc(h * w * c, sizeof(float));
    int i;
    for(i = 0; i < w*h*c; ++i){
        out.data[i] = (rand_normal() * .25) + .5;
    }
    return out;
}

image float_to_image_scaled(int w, int h, int c, float *data)
{
    image out = make_image(w, h, c);
    int abs_max = 0;
    int i = 0;
    for (i = 0; i < w*h*c; ++i) {
        if (fabs(data[i]) > abs_max) abs_max = fabs(data[i]);
    }
    for (i = 0; i < w*h*c; ++i) {
        out.data[i] = data[i] / abs_max;
    }
    return out;
}

image float_to_image(int w, int h, int c, float *data)
{
    image out = make_empty_image(w,h,c);
    out.data = data;
    return out;
}


image rotate_crop_image(image im, float rad, float s, int w, int h, float dx, float dy, float aspect)
{
    int x, y, c;
    float cx = im.w/2.;
    float cy = im.h/2.;
    image rot = make_image(w, h, im.c);
    for(c = 0; c < im.c; ++c){
        for(y = 0; y < h; ++y){
            for(x = 0; x < w; ++x){
                float rx = cos(rad)*((x - w/2.)/s*aspect + dx/s*aspect) - sin(rad)*((y - h/2.)/s + dy/s) + cx;
                float ry = sin(rad)*((x - w/2.)/s*aspect + dx/s*aspect) + cos(rad)*((y - h/2.)/s + dy/s) + cy;
                float val = bilinear_interpolate(im, rx, ry, c);
                set_pixel(rot, x, y, c, val);
            }
        }
    }
    return rot;
}

image rotate_image(image im, float rad)
{
    int x, y, c;
    float cx = im.w/2.;
    float cy = im.h/2.;
    image rot = make_image(im.w, im.h, im.c);
    for(c = 0; c < im.c; ++c){
        for(y = 0; y < im.h; ++y){
            for(x = 0; x < im.w; ++x){
                float rx = cos(rad)*(x-cx) - sin(rad)*(y-cy) + cx;
                float ry = sin(rad)*(x-cx) + cos(rad)*(y-cy) + cy;
                float val = bilinear_interpolate(im, rx, ry, c);
                set_pixel(rot, x, y, c, val);
            }
        }
    }
    return rot;
}

void translate_image(image m, float s)
{
    int i;
    for(i = 0; i < m.h*m.w*m.c; ++i) m.data[i] += s;
}

void scale_image(image m, float s)
{
    int i;
    for(i = 0; i < m.h*m.w*m.c; ++i) m.data[i] *= s;
}

image crop_image(image im, int dx, int dy, int w, int h)
{
    image cropped = make_image(w, h, im.c);
    int i, j, k;
    for(k = 0; k < im.c; ++k){
        for(j = 0; j < h; ++j){
            for(i = 0; i < w; ++i){
                int r = j + dy;
                int c = i + dx;
                float val = 0;
                r = constrain_int(r, 0, im.h-1);
                c = constrain_int(c, 0, im.w-1);
                if (r >= 0 && r < im.h && c >= 0 && c < im.w) {
                    val = get_pixel(im, c, r, k);
                }
                set_pixel(cropped, i, j, k, val);
            }
        }
    }
    return cropped;
}

int best_3d_shift_r(image a, image b, int min, int max)
{
    if(min == max) return min;
    int mid = floor((min + max) / 2.);
    image c1 = crop_image(b, 0, mid, b.w, b.h);
    image c2 = crop_image(b, 0, mid+1, b.w, b.h);
    float d1 = dist_array(c1.data, a.data, a.w*a.h*a.c, 10);
    float d2 = dist_array(c2.data, a.data, a.w*a.h*a.c, 10);
    free_image(c1);
    free_image(c2);
    if(d1 < d2) return best_3d_shift_r(a, b, min, mid);
    else return best_3d_shift_r(a, b, mid+1, max);
}

int best_3d_shift(image a, image b, int min, int max)
{
    int i;
    int best = 0;
    float best_distance = FLT_MAX;
    for(i = min; i <= max; i += 2){
        image c = crop_image(b, 0, i, b.w, b.h);
        float d = dist_array(c.data, a.data, a.w*a.h*a.c, 100);
        if(d < best_distance){
            best_distance = d;
            best = i;
        }
        printf("%d %f\n", i, d);
        free_image(c);
    }
    return best;
}

void composite_3d(char *f1, char *f2, char *out, int delta)
{
    if(!out) out = "out";
    image a = load_image(f1, 0,0,0);
    image b = load_image(f2, 0,0,0);
    int shift = best_3d_shift_r(a, b, -a.h/100, a.h/100);

    image c1 = crop_image(b, 10, shift, b.w, b.h);
    float d1 = dist_array(c1.data, a.data, a.w*a.h*a.c, 100);
    image c2 = crop_image(b, -10, shift, b.w, b.h);
    float d2 = dist_array(c2.data, a.data, a.w*a.h*a.c, 100);

    if(d2 < d1 && 0){
        image swap = a;
        a = b;
        b = swap;
        shift = -shift;
        printf("swapped, %d\n", shift);
    }
    else{
        printf("%d\n", shift);
    }

    image c = crop_image(b, delta, shift, a.w, a.h);
    int i;
    for(i = 0; i < c.w*c.h; ++i){
        c.data[i] = a.data[i];
    }
#ifdef OPENCV
    save_image_jpg(c, out);
#else
    save_image(c, out);
#endif
}

void fill_image(image m, float s)
{
    int i;
    for (i = 0; i < m.h*m.w*m.c; ++i) m.data[i] = s;
}

void letterbox_image_into(image im, int w, int h, image boxed)
{
    int new_w = im.w;
    int new_h = im.h;
    if (((float)w / im.w) < ((float)h / im.h)) {
        new_w = w;
        new_h = (im.h * w) / im.w;
    }
    else {
        new_h = h;
        new_w = (im.w * h) / im.h;
    }
    image resized = resize_image(im, new_w, new_h);
    embed_image(resized, boxed, (w - new_w) / 2, (h - new_h) / 2);
    free_image(resized);
}

image letterbox_image(image im, int w, int h)
{
    int new_w = im.w;
    int new_h = im.h;
    if (((float)w / im.w) < ((float)h / im.h)) {
...

This file has been truncated, please download it to see its full contents.