Switch to fast resize

This commit is contained in:
Joseph Redmon 2015-07-21 11:46:24 -07:00
parent 8ed0a5538e
commit e56d1eff13
5 changed files with 7 additions and 43 deletions

View File

@ -1,5 +1,5 @@
GPU=1 GPU=0
OPENCV=1 OPENCV=0
DEBUG=0 DEBUG=0
ARCH= -arch=sm_52 ARCH= -arch=sm_52

View File

@ -78,7 +78,7 @@ __device__ float3 hsv_to_rgb_kernel(float3 hsv)
return make_float3(r, g, b); return make_float3(r, g, b);
} }
__device__ float billinear_interpolate_kernel(float *image, int w, int h, float x, float y, int c) __device__ float bilinear_interpolate_kernel(float *image, int w, int h, float x, float y, int c)
{ {
int ix = (int) floorf(x); int ix = (int) floorf(x);
int iy = (int) floorf(y); int iy = (int) floorf(y);
@ -170,7 +170,7 @@ __global__ void forward_crop_layer_kernel(float *input, float *rand, int size, i
float rx = cos(angle)*(x-cx) - sin(angle)*(y-cy) + cx; float rx = cos(angle)*(x-cx) - sin(angle)*(y-cy) + cx;
float ry = sin(angle)*(x-cx) + cos(angle)*(y-cy) + cy; float ry = sin(angle)*(x-cx) + cos(angle)*(y-cy) + cy;
output[count] = billinear_interpolate_kernel(input, w, h, rx, ry, k); output[count] = bilinear_interpolate_kernel(input, w, h, rx, ry, k);
} }
extern "C" void forward_crop_layer_gpu(crop_layer layer, network_state state) extern "C" void forward_crop_layer_gpu(crop_layer layer, network_state state)

View File

@ -425,18 +425,10 @@ data load_data_detection_jitter_random(int n, char **paths, int m, int classes,
d.X.vals = calloc(d.X.rows, sizeof(float*)); d.X.vals = calloc(d.X.rows, sizeof(float*));
d.X.cols = h*w*3; d.X.cols = h*w*3;
clock_t time;
clock_t load = 0;
clock_t resize = 0;
clock_t crop = 0;
int k = num_boxes*num_boxes*(4+classes+background); int k = num_boxes*num_boxes*(4+classes+background);
d.y = make_matrix(n, k); d.y = make_matrix(n, k);
for(i = 0; i < n; ++i){ for(i = 0; i < n; ++i){
time=clock();
image orig = load_image_color(random_paths[i], 0, 0); image orig = load_image_color(random_paths[i], 0, 0);
load += clock() - time;
time = clock();
int oh = orig.h; int oh = orig.h;
int ow = orig.w; int ow = orig.w;
@ -465,9 +457,6 @@ data load_data_detection_jitter_random(int n, char **paths, int m, int classes,
int flip = rand_r(&data_seed)%2; int flip = rand_r(&data_seed)%2;
image cropped = crop_image(orig, pleft, ptop, swidth, sheight); image cropped = crop_image(orig, pleft, ptop, swidth, sheight);
crop += clock() - time;
time = clock();
float dx = ((float)pleft/ow)/sx; float dx = ((float)pleft/ow)/sx;
float dy = ((float)ptop /oh)/sy; float dy = ((float)ptop /oh)/sy;
@ -475,15 +464,11 @@ data load_data_detection_jitter_random(int n, char **paths, int m, int classes,
if(flip) flip_image(sized); if(flip) flip_image(sized);
d.X.vals[i] = sized.data; d.X.vals[i] = sized.data;
resize += clock() - time;
time = clock();
fill_truth_detection(random_paths[i], d.y.vals[i], classes, num_boxes, flip, background, dx, dy, 1./sx, 1./sy); fill_truth_detection(random_paths[i], d.y.vals[i], classes, num_boxes, flip, background, dx, dy, 1./sx, 1./sy);
free_image(orig); free_image(orig);
free_image(cropped); free_image(cropped);
} }
printf("load: %f, crop: %f, resize: %f\n", sec(load), sec(crop), sec(resize));
free(random_paths); free(random_paths);
return d; return d;
} }

View File

@ -332,7 +332,7 @@ image rotate_image(image im, float rad)
for(x = 0; x < im.w; ++x){ for(x = 0; x < im.w; ++x){
float rx = cos(rad)*(x-cx) - sin(rad)*(y-cy) + cx; float rx = cos(rad)*(x-cx) - sin(rad)*(y-cy) + cx;
float ry = sin(rad)*(x-cx) + cos(rad)*(y-cy) + cy; float ry = sin(rad)*(x-cx) + cos(rad)*(y-cy) + cy;
float val = billinear_interpolate(im, rx, ry, c); float val = bilinear_interpolate(im, rx, ry, c);
set_pixel(rot, x, y, c, val); set_pixel(rot, x, y, c, val);
} }
} }
@ -549,7 +549,7 @@ void saturate_exposure_image(image im, float sat, float exposure)
} }
*/ */
float billinear_interpolate(image im, float x, float y, int c) float bilinear_interpolate(image im, float x, float y, int c)
{ {
int ix = (int) floorf(x); int ix = (int) floorf(x);
int iy = (int) floorf(y); int iy = (int) floorf(y);
@ -564,27 +564,7 @@ float billinear_interpolate(image im, float x, float y, int c)
return val; return val;
} }
// #wikipedia
image resize_image(image im, int w, int h) image resize_image(image im, int w, int h)
{
image resized = make_image(w, 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 < h; ++r){
for(c = 0; c < w; ++c){
float sx = c*w_scale;
float sy = r*h_scale;
float val = billinear_interpolate(im, sx, sy, k);
set_pixel(resized, c, r, k, val);
}
}
}
return resized;
}
image resize_image2(image im, int w, int h)
{ {
image resized = make_image(w, h, im.c); image resized = make_image(w, h, im.c);
image part = make_image(w, im.h, im.c); image part = make_image(w, im.h, im.c);
@ -607,7 +587,6 @@ image resize_image2(image im, int w, int h)
} }
} }
} }
for(k = 0; k < im.c; ++k){ for(k = 0; k < im.c; ++k){
for(r = 0; r < h; ++r){ for(r = 0; r < h; ++r){
float sy = r*h_scale; float sy = r*h_scale;

View File

@ -64,7 +64,7 @@ float get_pixel(image m, int x, int y, int c);
float get_pixel_extend(image m, int x, int y, int c); float get_pixel_extend(image m, int x, int y, int c);
void set_pixel(image m, int x, int y, int c, float val); void set_pixel(image m, int x, int y, int c, float val);
void add_pixel(image m, int x, int y, int c, float val); void add_pixel(image m, int x, int y, int c, float val);
float billinear_interpolate(image im, float x, float y, int c); float bilinear_interpolate(image im, float x, float y, int c);
image get_image_layer(image m, int l); image get_image_layer(image m, int l);