From: Inki Dae <inki.dae@samsung.com>
Date: Thu, 11 Jun 2020 07:16:42 +0000 (+0900)
Subject: Set supported_device_types according to MLAPI backend type
X-Git-Tag: submit/tizen/20200626.050805~4
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=f911018186326850d1f3c883e3f0d4a63ec25cbe;p=platform%2Fcore%2Fmultimedia%2Finference-engine-mlapi.git

Set supported_device_types according to MLAPI backend type

NNFW supports only CPU and GPU accelerated NN runtime so
Consider using NNFW tensor filter plugin of NNStreamer.

Change-Id: I3ed4ae5018b984c812f8bad69eebbfdae69dd030
Signed-off-by: Inki Dae <inki.dae@samsung.com>
---

diff --git a/src/inference_engine_mlapi.cpp b/src/inference_engine_mlapi.cpp
index ab36c9b..d6d4706 100644
--- a/src/inference_engine_mlapi.cpp
+++ b/src/inference_engine_mlapi.cpp
@@ -366,7 +366,12 @@ namespace MLAPIImpl
 		}
 
 		// TODO. flag supported accel device types according to a given ML Single API of nnstreamer backend.
-		capacity->supported_accel_devices = INFERENCE_TARGET_CUSTOM;
+		if (mPluginType == INFERENCE_BACKEND_MLAPI) {
+			capacity->supported_accel_devices = INFERENCE_TARGET_CUSTOM;
+		} else {
+			capacity->supported_accel_devices = INFERENCE_TARGET_GPU |
+												INFERENCE_TARGET_CPU;
+		}
 
 		LOGI("LEAVE");