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

Bell/fix gpu load model file wrong lifecycle (#14347)

Browse Source 
* ensure correct lifecycle with load model file

Signed-off-by: fishbell <bell.song@intel.com>

* clang format

Signed-off-by: fishbell <bell.song@intel.com>

* enable tests

Signed-off-by: fishbell <bell.song@intel.com>

Signed-off-by: fishbell <bell.song@intel.com>
This commit is contained in:
yanlan song authored and GitHub committed 2022-12-06 11:29:07 +03:00
1 parent bf0d2cea4b
commit 4f1ad3bf3d
12 files changed
+50 -15
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/plugins/auto/plugin.cpp
+2 -2
View File
@@ -302,9 +302,9 @@ InferenceEngine::Parameter MultiDeviceInferencePlugin::GetMetric(const std::stri
}
// Is called only when caching is enabled
IExecutableNetworkInternal::Ptr MultiDeviceInferencePlugin::LoadNetwork(const std::string& modelPath,
ov::SoPtr<InferenceEngine::IExecutableNetworkInternal> MultiDeviceInferencePlugin::LoadNetwork(const std::string& modelPath,
const std::map<std::string, std::string>& config) {
return LoadNetworkImpl(modelPath, {}, config);
return {LoadNetworkImpl(modelPath, {}, config), nullptr};
}
IExecutableNetworkInternal::Ptr MultiDeviceInferencePlugin::LoadExeNetworkImpl(const CNNNetwork &network,
src/plugins/auto/plugin.hpp
+1 -1
View File
@@ -33,7 +33,7 @@ public:
InferenceEngine::IExecutableNetworkInternal::Ptr LoadExeNetworkImpl(const InferenceEngine::CNNNetwork& network,
const std::map<std::string, std::string>& config) override;
InferenceEngine::IExecutableNetworkInternal::Ptr LoadNetwork(const std::string& modelPath,
ov::SoPtr<InferenceEngine::IExecutableNetworkInternal> LoadNetwork(const std::string& modelPath,
const std::map<std::string, std::string>& config) override;
void SetConfig(const std::map<std::string, std::string>& config) override;