Change OutputLayer to OutputTensor 47/274047/2 accepted/tizen/6.5/unified/20220425.133226 submit/tizen_6.5/20220422.005247
authorTae-Young Chung <ty83.chung@samsung.com>
Wed, 20 Apr 2022 09:14:04 +0000 (18:14 +0900)
committerTae-Young Chung <ty83.chung@samsung.com>
Thu, 21 Apr 2022 01:40:41 +0000 (10:40 +0900)
[Version] 0.0.7-0
[Issue type] bug fix

MediaVision uses the final output buffer(or tensor) name to access the memory.
In SPNE, even though a single OutputLayer has a name but there are final multiple OutputTensors
which have different names. So, change the OutputLayer to OutputTensor.

Change-Id: I1f2f1712699bb6d51dce831a11137b60303267c7
Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
packaging/inference-engine-mlapi.spec
src/inference_engine_mlapi.cpp

index 316f9f9..a6c4f9a 100644 (file)
@@ -1,6 +1,6 @@
 Name:       inference-engine-mlapi
 Summary:    ML Single API backend of NNStreamer for MediaVision
-Version:    0.0.6
+Version:    0.0.7
 Release:    0
 Group:      Multimedia/Libraries
 License:    Apache-2.0
index 0e92655..766abc7 100644 (file)
@@ -305,7 +305,7 @@ namespace MLAPIImpl
 
                if (!mOutputProperty.layers.empty()){
                        size_t layerSize = mOutputProperty.layers.size();
-                       custom += ",OutputLayer:";
+                       custom += ",OutputTensor:";
 
                        for (auto& layer : mOutputProperty.layers) {
                                LOGI("output layer name = %s", layer.first.c_str());