QImage GradientEnergy::conv(double* mat, bool sum){
int width = grey.width();
int height = grey.height();
const unsigned int* src = (const unsigned int*)grey.bits();
unsigned int* dst = (unsigned int*)malloc(sizeof(unsigned int)*width*height);
for(int y=0;y<height;y++)
{
for(int x=0;x<width;x++)
{
int color=0;
//Convolute repair 180 degree
for(int cy=-1;cy<=1;cy++)
{
for(int cx=-1;cx<=1;cx++)
{
int c=0;
if((cx+x>=0 && cy+y>=0) && (cx+x<width && cy+y<height))
{
c = round(qRed(src[(x+cx)+(y+cy)*image.width()])*mat[(2-(cx+1))+((2-(cy+1))*3)]);
}
else if(cx+x<0)
{
if(cy+y<0)
{
c = round(qRed(src[(0)+(0)*image.width()])*mat[(2-(cx+1))+((2-(cy+1))*3)]);
}
else if(cy+y>=height)
{
c = round(qRed(src[(0)+(height-1)*image.width()])*mat[(2-(cx+1))+((2-(cy+1))*3)]);
}
else
{
c = round(qRed(src[(0)+(y+cy)*image.width()])*mat[(2-(cx+1))+((2-(cy+1))*3)]);
}
}
else if(cx+x>=width)
{
if(cy+y<0)
{
c = round(qRed(src[(width-1)+(0)*image.width()])*mat[(2-(cx+1))+((2-(cy+1))*3)]);
}
else if(cy+y>=height)
{
c = round(qRed(src[(width-1)+(height-1)*image.width()])*mat[(2-(cx+1))+((2-(cy+1))*3)]);
}
else
{
c = round(qRed(src[(width-1)+(y+cy)*image.width()])*mat[(2-(cx+1))+((2-(cy+1))*3)]);
}
}
else if(cy+y<0)
{
if(cx+x<0)
{
c = round(qRed(src[(0)+(0)*image.width()])*mat[(2-(cx+1))+((2-(cy+1))*3)]);
}
else if(cx+x>=width)
{
c = round(qRed(src[(width-1)+(0)*image.width()])*mat[(2-(cx+1))+((2-(cy+1))*3)]);
}
else
{
c = round(qRed(src[(cx+x)+(0)*image.width()])*mat[(2-(cx+1))+((2-(cy+1))*3)]);
}
}
else if(cy+y>height)
{
if(cx+x<0)
{
c = round(qRed(src[(0)+(height-1)*image.width()])*mat[(2-(cx+1))+((2-(cy+1))*3)]);
}
else if(cx+x>=width)
{
c = round(qRed(src[(width-1)+(height-1)*image.width()])*mat[(2-(cx+1))+((2-(cy+1))*3)]);
}
else
{
c = round(qRed(src[(width)+(height-1)*image.width()])*mat[(2-(cx+1))+((2-(cy+1))*3)]);
}
}
color+=c;
}
}
if (sum)
color+=128;
if(color>255)
{
color=255;
}
else if(color<0)
{
color = 0;
}
dst[x+y*width]=qRgb(color,color,color);
}
}
QImage conv_img((unsigned char*)dst,width,height,QImage::Format_ARGB32);
return conv_img;
}
static void test_conv_image()
{
printf("test_conv_image...");
unsigned int img_width = 10;
unsigned int img_height = 10;
unsigned int bitsperpixel = 0;
int no_of_layers = 3;
int max_features = 20;
int reduction_factor = 6;
int pooling_factor = 2;
float error_threshold[] = {0.0, 0.0, 0.0};
unsigned int random_seed = 648326;
unsigned char * img, * img2;
deeplearn_conv conv;
float BPerror = -1;
char plot_filename[256];
char plot_title[256];
/* load image from file */
assert(deeplearn_read_png_file((char*)"Lenna.png",
&img_width, &img_height,
&bitsperpixel, &img)==0);
img2 = (unsigned char*)malloc(128*128*3*sizeof(unsigned char));
assert(img2);
deeplearn_downsample(img, img_width, img_height,
img2, 128, 128);
free(img);
img = img2;
img_width = 128;
img_height = 128;
assert(conv_init(no_of_layers,
img_width, img_height,
bitsperpixel/8, max_features,
reduction_factor, pooling_factor,
&conv, error_threshold,
&random_seed) == 0);
int conv0_size =
conv.layer[0].units_across *
conv.layer[0].units_down * max_features;
for (int i = 0; i < 4; i++) {
for (int j = 0; j < conv0_size; j++) {
conv.layer[0].convolution[j] = -9999;
}
assert(conv_img(img, &conv) == 0);
/* check that some convolution happened */
for (int j = 0; j < conv0_size; j++) {
assert(conv.layer[0].convolution[j] != -9999);
}
/* error should be >= 0 */
assert(conv.BPerror >= 0);
/* error should be reducing */
if (i > 0) {
assert(conv.BPerror < BPerror);
}
BPerror = conv.BPerror;
}
/* move to hte next layer */
conv.BPerror = -1;
conv.current_layer++;
int conv1_size =
conv.layer[1].units_across *
conv.layer[1].units_down * max_features;
for (int i = 0; i < 4; i++) {
for (int j = 0; j < conv1_size; j++) {
conv.layer[1].convolution[j] = -9999;
}
assert(conv_img(img, &conv) == 0);
/* check that some convolution happened */
for (int j = 0; j < conv1_size; j++) {
assert(conv.layer[1].convolution[j] != -9999);
}
/* error should be >= 0 */
if (!(conv.BPerror >= 0)) {
printf("\nBPerror: %f\n",conv.BPerror);
}
assert(conv.BPerror >= 0);
/* error should be reducing */
if (i > 0) {
assert(conv.BPerror < BPerror);
}
BPerror = conv.BPerror;
}
sprintf(plot_filename,"/tmp/%s","libdeep_conv.png");
sprintf(plot_title,"%s","Convolution Training Error");
assert(conv_plot_history(&conv, plot_filename,
plot_title,
1024, 640) == 0);
conv_free(&conv);
free(img);
printf("Ok\n");
}