CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-06 09:46:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml-cpu : bicubic interpolation (#16891)

Browse Source
This commit is contained in:
Acly
2025-11-04 13:12:20 +01:00
committed by GitHub
parent d945834366
commit cc98f8d349
2 changed files with 53 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml/include/ggml.h
View File

@@ -2108,6 +2108,7 @@ extern "C" {
enum ggml_scale_mode {
GGML_SCALE_MODE_NEAREST = 0,
GGML_SCALE_MODE_BILINEAR = 1,
GGML_SCALE_MODE_BICUBIC = 2,
GGML_SCALE_MODE_COUNT
};

59
ggml/src/ggml-cpu/ops.cpp
View File

@@ -7507,10 +7507,17 @@ static void ggml_compute_forward_upscale_f32(
float sf1 = (float)ne1/src0->ne[1];
float sf2 = (float)ne2/src0->ne[2];
float sf3 = (float)ne3/src0->ne[3];
float pixel_offset = 0.5f;
const int32_t mode_flags = ggml_get_op_params_i32(dst, 0);
const ggml_scale_mode mode = (ggml_scale_mode) (mode_flags & 0xFF);
if (mode_flags & GGML_SCALE_FLAG_ALIGN_CORNERS) {
pixel_offset = 0.0f;
sf0 = ne0 > 1 && ne00 > 1 ? (float)(ne0 - 1) / (ne00 - 1) : sf0;
sf1 = ne1 > 1 && ne01 > 1 ? (float)(ne1 - 1) / (ne01 - 1) : sf1;
}
if (mode == GGML_SCALE_MODE_NEAREST) {
for (int64_t i3 = 0; i3 < ne3; i3++) {
const int64_t i03 = i3 / sf3;
@@ -7530,13 +7537,6 @@ static void ggml_compute_forward_upscale_f32(
}
}
} else if (mode == GGML_SCALE_MODE_BILINEAR) {
float pixel_offset = 0.5f;
if (mode_flags & GGML_SCALE_FLAG_ALIGN_CORNERS) {
pixel_offset = 0.0f;
sf0 = ne0 > 1 && ne00 > 1 ? (float)(ne0 - 1) / (ne00 - 1) : sf0;
sf1 = ne1 > 1 && ne01 > 1 ? (float)(ne1 - 1) / (ne01 - 1) : sf1;
}
for (int64_t i3 = 0; i3 < ne3; i3++) {
const int64_t i03 = i3 / sf3;
for (int64_t i2 = ith; i2 < ne2; i2 += nth) {
@@ -7571,6 +7571,51 @@ static void ggml_compute_forward_upscale_f32(
const float val = a*(1 - dx)*(1 - dy) + b*dx*(1 - dy) + c*(1 - dx)*dy + d*dx*dy;
float * y_dst = (float *)((char *)dst->data + i0*nb0 + i1*nb1 + i2*nb2 + i3*nb3);
*y_dst = val;
}
}
}
}
} else if (mode == GGML_SCALE_MODE_BICUBIC) {
// https://en.wikipedia.org/wiki/Bicubic_interpolation#Bicubic_convolution_algorithm
const float a = -0.75f; // use alpha = -0.75 (same as PyTorch)
auto weight1 = [a](float x) { return ((a + 2) * x - (a + 3)) * x * x + 1; };
auto weight2 = [a](float x) { return ((a * x - 5 * a) * x + 8 * a) * x - 4 * a; };
auto bicubic = [=](float p0, float p1, float p2, float p3, float x) {
const float w0 = weight2(x + 1);
const float w1 = weight1(x + 0);
const float w2 = weight1(1 - x);
const float w3 = weight2(2 - x);
return p0*w0 + p1*w1 + p2*w2 + p3*w3;
};
for (int64_t i3 = 0; i3 < ne3; i3++) {
const int64_t i03 = i3 / sf3;
for (int64_t i2 = ith; i2 < ne2; i2 += nth) {
const int64_t i02 = i2 / sf2;
for (int64_t i1 = 0; i1 < ne1; i1++) {
const float y = ((float)i1 + pixel_offset) / sf1 - pixel_offset;
const int64_t y0 = (int64_t)floorf(y);
const float dy = y - (float)y0;
for (int64_t i0 = 0; i0 < ne0; i0++) {
const float x = ((float)i0 + pixel_offset) / sf0 - pixel_offset;
const int64_t x0 = (int64_t)floorf(x);
const float dx = x - (float)x0;
auto p = [=](int64_t x_off, int64_t y_off) -> float {
int64_t i00 = std::max(int64_t(0), std::min(x0 + x_off, ne00 - 1));
int64_t i01 = std::max(int64_t(0), std::min(y0 + y_off, ne01 - 1));
return *(const float *)((const char *)src0->data + i00*nb00 + i01*nb01 + i02*nb02 + i03*nb03);
};
const float val = bicubic(
bicubic(p(-1,-1), p(0,-1), p(1,-1), p(2,-1), dx),
bicubic(p(-1, 0), p(0, 0), p(1, 0), p(2, 0), dx),
bicubic(p(-1, 1), p(0, 1), p(1, 1), p(2, 1), dx),
bicubic(p(-1, 2), p(0, 2), p(1, 2), p(2, 2), dx), dy);
float * y_dst = (float *)((char *)dst->data + i0*nb0 + i1*nb1 + i2*nb2 + i3*nb3);
*y_dst = val;
}