diff --git a/ggml/include/ggml.h b/ggml/include/ggml.h index 8bd3ca929..f8238f315 100644 --- a/ggml/include/ggml.h +++ b/ggml/include/ggml.h @@ -1867,6 +1867,12 @@ extern "C" { enum ggml_scale_mode { GGML_SCALE_MODE_NEAREST = 0, GGML_SCALE_MODE_BILINEAR = 1, + + GGML_SCALE_MODE_COUNT + }; + + enum ggml_scale_flag { + GGML_SCALE_FLAG_ALIGN_CORNERS = (1 << 8) }; // interpolate @@ -1879,14 +1885,26 @@ extern "C" { // interpolate // interpolate scale to specified dimensions - GGML_API struct ggml_tensor * ggml_upscale_ext( + GGML_DEPRECATED(GGML_API struct ggml_tensor * ggml_upscale_ext( struct ggml_context * ctx, struct ggml_tensor * a, int ne0, int ne1, int ne2, int ne3, - enum ggml_scale_mode mode); + enum ggml_scale_mode mode), + "use ggml_interpolate instead"); + + // Up- or downsamples the input to the specified size. + // 2D scale modes (eg. bilinear) are applied to the first two dimensions. + GGML_API struct ggml_tensor * ggml_interpolate( + struct ggml_context * ctx, + struct ggml_tensor * a, + int64_t ne0, + int64_t ne1, + int64_t ne2, + int64_t ne3, + uint32_t mode); // ggml_scale_mode [ | ggml_scale_flag...] // pad each dimension with zeros: [x, ..., x] -> [x, ..., x, 0, ..., 0] GGML_API struct ggml_tensor * ggml_pad( diff --git a/ggml/src/ggml-cpu/ops.cpp b/ggml/src/ggml-cpu/ops.cpp index 6948c00b4..dd83efde7 100644 --- a/ggml/src/ggml-cpu/ops.cpp +++ b/ggml/src/ggml-cpu/ops.cpp @@ -7276,12 +7276,13 @@ static void ggml_compute_forward_upscale_f32( GGML_TENSOR_UNARY_OP_LOCALS - const float sf0 = (float)ne0/src0->ne[0]; - const float sf1 = (float)ne1/src0->ne[1]; - const float sf2 = (float)ne2/src0->ne[2]; - const float sf3 = (float)ne3/src0->ne[3]; + float sf0 = (float)ne0/src0->ne[0]; + float sf1 = (float)ne1/src0->ne[1]; + float sf2 = (float)ne2/src0->ne[2]; + float sf3 = (float)ne3/src0->ne[3]; - const ggml_scale_mode mode = (ggml_scale_mode) ggml_get_op_params_i32(dst, 0); + 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 == GGML_SCALE_MODE_NEAREST) { for (int64_t i3 = 0; i3 < ne3; i3++) { @@ -7302,8 +7303,12 @@ static void ggml_compute_forward_upscale_f32( } } } else if (mode == GGML_SCALE_MODE_BILINEAR) { - // setting a pixel offset of 0 would replicate the behavior of pytorch interpolate with align_corners=True - const float pixel_offset = 0.5f; + float pixel_offset = 0.5f; + if (mode_flags & GGML_SCALE_FLAG_ALIGN_CORNERS) { + pixel_offset = 0.0f; + sf0 = (float)(ne0 - 1) / (src0->ne[0] - 1); + sf1 = (float)(ne1 - 1) / (src0->ne[1] - 1); + } for (int64_t i3 = 0; i3 < ne3; i3++) { const int64_t i03 = i3 / sf3; diff --git a/ggml/src/ggml.c b/ggml/src/ggml.c index 47fe37b13..b499f3785 100644 --- a/ggml/src/ggml.c +++ b/ggml/src/ggml.c @@ -4447,24 +4447,21 @@ struct ggml_tensor * ggml_pool_2d_back( return result; } -// ggml_upscale +// ggml_upscale / ggml_interpolate -static struct ggml_tensor * ggml_upscale_impl( +static struct ggml_tensor * ggml_interpolate_impl( struct ggml_context * ctx, struct ggml_tensor * a, - int ne0, - int ne1, - int ne2, - int ne3, - enum ggml_scale_mode mode) { - GGML_ASSERT(a->ne[0] <= ne0); - GGML_ASSERT(a->ne[1] <= ne1); - GGML_ASSERT(a->ne[2] <= ne2); - GGML_ASSERT(a->ne[3] <= ne3); - + int64_t ne0, + int64_t ne1, + int64_t ne2, + int64_t ne3, + uint32_t mode) { + GGML_ASSERT((mode & 0xFF) < GGML_SCALE_MODE_COUNT); + struct ggml_tensor * result = ggml_new_tensor_4d(ctx, a->type, ne0, ne1, ne2, ne3); - ggml_set_op_params_i32(result, 0, mode); + ggml_set_op_params_i32(result, 0, (int32_t)mode); result->op = GGML_OP_UPSCALE; result->src[0] = a; @@ -4477,7 +4474,8 @@ struct ggml_tensor * ggml_upscale( struct ggml_tensor * a, int scale_factor, enum ggml_scale_mode mode) { - return ggml_upscale_impl(ctx, a, a->ne[0] * scale_factor, a->ne[1] * scale_factor, a->ne[2], a->ne[3], mode); + GGML_ASSERT(scale_factor > 1); + return ggml_interpolate_impl(ctx, a, a->ne[0] * scale_factor, a->ne[1] * scale_factor, a->ne[2], a->ne[3], mode); } struct ggml_tensor * ggml_upscale_ext( @@ -4488,7 +4486,18 @@ struct ggml_tensor * ggml_upscale_ext( int ne2, int ne3, enum ggml_scale_mode mode) { - return ggml_upscale_impl(ctx, a, ne0, ne1, ne2, ne3, mode); + return ggml_interpolate_impl(ctx, a, ne0, ne1, ne2, ne3, mode); +} + +struct ggml_tensor * ggml_interpolate( + struct ggml_context * ctx, + struct ggml_tensor * a, + int64_t ne0, + int64_t ne1, + int64_t ne2, + int64_t ne3, + uint32_t mode) { + return ggml_interpolate_impl(ctx, a, ne0, ne1, ne2, ne3, mode); } // ggml_pad diff --git a/tests/test-backend-ops.cpp b/tests/test-backend-ops.cpp index dd2dfcc0a..43be1e928 100644 --- a/tests/test-backend-ops.cpp +++ b/tests/test-backend-ops.cpp @@ -3296,28 +3296,28 @@ struct test_upscale : public test_case { } }; -// GGML_OP_UPSCALE (ext) -struct test_upscale_ext : public test_case { +// GGML_OP_UPSCALE (via ggml_interpolate) +struct test_interpolate : public test_case { const ggml_type type; const std::array ne; const std::array ne_tgt; - const ggml_scale_mode mode = GGML_SCALE_MODE_NEAREST; + const uint32_t mode = GGML_SCALE_MODE_NEAREST; std::string vars() override { return VARS_TO_STR4(type, ne, ne_tgt, mode); } - test_upscale_ext(ggml_type type = GGML_TYPE_F32, + test_interpolate(ggml_type type = GGML_TYPE_F32, std::array ne = {2, 5, 7, 11}, std::array ne_tgt = {5, 7, 11, 13}, - ggml_scale_mode mode = GGML_SCALE_MODE_NEAREST) + uint32_t mode = GGML_SCALE_MODE_NEAREST) : type(type), ne(ne), ne_tgt(ne_tgt), mode(mode) {} ggml_tensor * build_graph(ggml_context * ctx) override { ggml_tensor * a = ggml_new_tensor(ctx, type, 4, ne.data()); ggml_set_name(a, "a"); - ggml_tensor * out = ggml_upscale_ext(ctx, a, ne_tgt[0], ne_tgt[1],ne_tgt[2], ne_tgt[3], mode); + ggml_tensor * out = ggml_interpolate(ctx, a, ne_tgt[0], ne_tgt[1],ne_tgt[2], ne_tgt[3], mode); ggml_set_name(out, "out"); return out; @@ -4799,8 +4799,10 @@ static std::vector> make_test_cases_eval() { for (ggml_scale_mode mode : {GGML_SCALE_MODE_NEAREST, GGML_SCALE_MODE_BILINEAR}) { test_cases.emplace_back(new test_upscale(GGML_TYPE_F32, {512, 512, 3, 2}, 2, mode)); test_cases.emplace_back(new test_upscale(GGML_TYPE_F32, {512, 512, 3, 2}, 2, mode, true)); - test_cases.emplace_back(new test_upscale_ext(GGML_TYPE_F32, {2, 5, 7, 11}, {5, 7, 11, 13}, mode)); + test_cases.emplace_back(new test_interpolate(GGML_TYPE_F32, {2, 5, 7, 11}, {5, 7, 11, 13}, mode)); + test_cases.emplace_back(new test_interpolate(GGML_TYPE_F32, {5, 7, 11, 13}, {2, 5, 7, 11}, mode)); } + test_cases.emplace_back(new test_interpolate(GGML_TYPE_F32, {2, 5, 7, 11}, {5, 7, 11, 13}, GGML_SCALE_MODE_BILINEAR | GGML_SCALE_FLAG_ALIGN_CORNERS)); test_cases.emplace_back(new test_sum()); test_cases.emplace_back(new test_sum_rows());