IntenseWebs/openvino
3
0 Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[Transformations] CompressQuantizeWeights: fp16 weights support (#16323)

Browse Source 
* [Transformations] CompressQuantizeWeights: fp16 weights support

* Code style fix

* Code style fix
This commit is contained in:
Vladislav Golubev authored and GitHub committed 2023-03-17 14:43:32 +04:00
1 parent d7c88fd694
commit 249d57f37e
2 files changed
+25 -9
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/common/transformations/tests/utils/compress_quantize_weights.cpp
+14 -5
View File
@@ -31,13 +31,18 @@ struct CompressQuantizeWeightsParams {
float zero_point_val;
};
class CompressQuantizeWeightsTests : public testing::WithParamInterface<CompressQuantizeWeightsParams>,
public TransformationTestsF {
class CompressQuantizeWeightsTests
: public testing::WithParamInterface<std::tuple<CompressQuantizeWeightsParams, element::Type>>,
public TransformationTestsF {
void SetUp() override {
TransformationTestsF::SetUp();
auto param = GetParam();
CompressQuantizeWeightsParams param;
ov::element::Type data_prc;
std::tie(param, data_prc) = GetParam();
{
auto data = opset8::Constant::create(element::f32, param.shape, param.weights);
std::shared_ptr<Node> data = opset8::Constant::create(data_prc, param.shape, param.weights);
if (data_prc == element::f16)
data = std::make_shared<opset8::Convert>(data, element::f32);
auto input_low = opset8::Constant::create(element::f32, Shape{}, {param.in_low});
auto input_high = opset8::Constant::create(element::f32, Shape{}, {param.in_high});
auto output_low = opset8::Constant::create(element::f32, Shape{}, {param.out_low});
@@ -116,7 +121,11 @@ static std::vector<CompressQuantizeWeightsParams> params = {
-64.25f},
};
INSTANTIATE_TEST_SUITE_P(TransformationTests, CompressQuantizeWeightsTests, ::testing::ValuesIn(params));
static element::TypeVector data_precisions = {element::f32, element::f16};
INSTANTIATE_TEST_SUITE_P(TransformationTests,
CompressQuantizeWeightsTests,
::testing::Combine(::testing::ValuesIn(params), ::testing::ValuesIn(data_precisions)));
TEST_F(TransformationTestsF, CompressQuantizeWeightsWithDequantizationSubgraph) {
{