From: Tae-Young Chung <ty83.chung@samsung.com>
Date: Wed, 8 Apr 2020 04:17:10 +0000 (+0900)
Subject: Add dummy buffer to inference_engine_tensor_buffers for output buffers
X-Git-Tag: submit/tizen/20200423.063253~2
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=2566e835f8f920f851941b2eebe11d46cb3717fa;p=platform%2Fcore%2Fmultimedia%2Finference-engine-opencv.git

Add dummy buffer to inference_engine_tensor_buffers for output buffers

In case of object detection, mobilenet-ssd, its output may be null and
it causes the memory allocation at inference-engine-interface
not from opencv itself.
To handle that case, temporally add dummy buffer.

Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
---

diff --git a/src/inference_engine_opencv.cpp b/src/inference_engine_opencv.cpp
index 80ce922..1e04003 100644
--- a/src/inference_engine_opencv.cpp
+++ b/src/inference_engine_opencv.cpp
@@ -150,6 +150,12 @@ int InferenceOpenCV::GetOutputTensorBuffers(std::vector<inference_engine_tensor_
         buffers.push_back(buffer);
     }
 
+    if (buffers.empty()) {
+        LOGI("buff empty");
+        inference_engine_tensor_buffer buffer = { nullptr, TENSOR_DATA_TYPE_FLOAT32, 0, 1};
+        buffers.push_back(buffer);
+    }
+
     LOGI("LEAVE");
 
     return INFERENCE_ENGINE_ERROR_NONE;