Applying coding ruletizen_8.0_m2_releasetizen_7.0_m2_releasesubmit/tizen/20220824.063348accepted/tizen/unified/20220825.063540accepted/tizen/8.0/unified/20231005.093425accepted/tizen/7.0/unified/hotfix/20221116.105401accepted/tizen/7.0/unified/20221110.060702tizen_8.0tizen_7.0_hotfixtizen_7.0tizenaccepted/tizen_unifiedaccepted/tizen_8.0_unifiedaccepted/tizen_7.0_unified_hotfixaccepted/tizen_7.0_unified

Change-Id: Ieb020b720fa19cccd1826706d67ae7887332002b
Signed-off-by: Hyunsoo Park <hance.park@samsung.com>

2 files changed, 29 insertions, 41 deletions

diff --git a/packaging/inference-engine-tflite.spec b/packaging/inference-engine-tflite.spec
index 8277bda..566eae8 100644
--- a/packaging/inference-engine-tflite.spec
+++ b/packaging/inference-engine-tflite.spec
@@ -1,6 +1,6 @@
 Name:       inference-engine-tflite
 Summary:    Tensorflow-Lite based implementation of inference-engine-interface
-Version:    0.0.4
+Version:    0.0.5
 Release:    0
 Group:      Multimedia/Libraries
 License:    Apache-2.0
diff --git a/src/inference_engine_tflite.cpp b/src/inference_engine_tflite.cpp
index e78b971..8f22bd9 100644
--- a/src/inference_engine_tflite.cpp
+++ b/src/inference_engine_tflite.cpp
@@ -161,16 +161,15 @@ namespace TFLiteImpl
 		for (auto& layer : mInputLayers) {
 			size_t size = 1;
 			inference_engine_tensor_buffer buffer;
-			for (auto& dim : layer.second.shape) {
+			for (auto& dim : layer.second.shape)
 				size *= dim;
-			}
 
-			if ( (layer.second).data_type == INFERENCE_TENSOR_DATA_TYPE_UINT8) {
+			if ((layer.second).data_type == INFERENCE_TENSOR_DATA_TYPE_UINT8) {
 				mInputData.push_back(
 						mInterpreter->typed_tensor<uint8_t>(mInputLayerId[layer.first]));
 				pBuff = mInputData.back();
 				buffer = { pBuff, INFERENCE_TENSOR_DATA_TYPE_UINT8, size, 1 };
-			} else if ( (layer.second).data_type == INFERENCE_TENSOR_DATA_TYPE_FLOAT32) {
+			} else if ((layer.second).data_type == INFERENCE_TENSOR_DATA_TYPE_FLOAT32) {
 				mInputData.push_back(
 						mInterpreter->typed_tensor<float>(mInputLayerId[layer.first]));
 				pBuff = mInputData.back();
@@ -198,11 +197,8 @@ namespace TFLiteImpl
 		for (auto& layer : mOutputLayers) {
 			inference_engine_tensor_buffer buffer;
 			size_t size = 1;
-			for (int idx2 = 0;
-				 idx2 < mInterpreter->tensor(mOutputLayerId[layer.first])->dims->size;
-				 ++idx2) {
+			for (int idx2 = 0; idx2 < mInterpreter->tensor(mOutputLayerId[layer.first])->dims->size; ++idx2)
 				size *= mInterpreter->tensor(mOutputLayerId[layer.first])->dims->data[idx2];
-			}
 
 			if (mInterpreter->tensor(mOutputLayerId[layer.first])->type == kTfLiteUInt8) {
 				LOGI("type is kTfLiteUInt8");
@@ -245,30 +241,25 @@ namespace TFLiteImpl
 	{
 		LOGI("ENTER");
 
-		std::map<std::string, inference_engine_tensor_info>().swap(mOutputLayers);
+		mOutputLayers.clear();
 
 		for (auto& layer :mOutputLayerId) {
-			LOGI("output layer ID: %d", layer.second);
-			if ( layer.second < 0) {
-				LOGE("Invalid output layer");
+			if (layer.second < 0) {
+				LOGE("Invalid output layer ID [%d]", layer.second);
 				return INFERENCE_ENGINE_ERROR_INVALID_OPERATION;
 			}
 
 			inference_engine_tensor_info tensor_info;
 
-			LOGI("mInterpreter->tensor(%d)->dims name[%s]",
-				 layer.second, mInterpreter->tensor(layer.second)->name);
-			LOGI("mInterpreter->tensor(%d)->dims size[%d]",
-				 layer.second, mInterpreter->tensor(layer.second)->dims->size);
-			LOGI("mInterpreter->tensor(%d)->dims type[%d]",
-				 layer.second, mInterpreter->tensor(layer.second)->type);
+			LOGI("mInterpreter->tensor(%d)->dims name[%s] size[%d] type[%d]",
+				 layer.second,
+				 mInterpreter->tensor(layer.second)->name,
+				 mInterpreter->tensor(layer.second)->dims->size,
+				 mInterpreter->tensor(layer.second)->type);
 
 			std::vector<size_t> shape_nhwc;
-			for (int idx = 0; idx < mInterpreter->tensor(layer.second)->dims->size;
-				 idx++) {
-				shape_nhwc.push_back(
-						mInterpreter->tensor(layer.second)->dims->data[idx]);
-			}
+			for (int idx = 0; idx < mInterpreter->tensor(layer.second)->dims->size; idx++)
+				shape_nhwc.push_back(mInterpreter->tensor(layer.second)->dims->data[idx]);
 
 			//tflite only supports NHWC (https://www.tensorflow.org/lite/guide/ops_compatibility).
 			tensor_info.shape = shape_nhwc;
@@ -287,9 +278,10 @@ namespace TFLiteImpl
 				return INFERENCE_ENGINE_ERROR_NOT_SUPPORTED_FORMAT;
 			}
 			tensor_info.size = 1;
-			for (auto & dim : tensor_info.shape) {
+
+			for (auto & dim : tensor_info.shape)
 				tensor_info.size *= dim;
-			}
+
 			mOutputLayers.insert(std::make_pair(mInterpreter->tensor(layer.second)->name, tensor_info));
 		}
 
@@ -304,10 +296,10 @@ namespace TFLiteImpl
 	{
 		LOGI("ENTER");
 
-		for (auto& layer : property.layers) {
+		for (auto& layer : property.layers)
 			LOGI("input layer name = %s", layer.first.c_str());
-		}
-		std::map<std::string, inference_engine_tensor_info>().swap(mInputLayers);
+
+		mInputLayers.clear();
 		mInputLayers = property.layers;
 
 		LOGI("LEAVE");
@@ -320,10 +312,10 @@ namespace TFLiteImpl
 	{
 		LOGI("ENTER");
 
-		for (auto& layer : property.layers) {
+		for (auto& layer : property.layers)
 			LOGI("input layer name = %s", layer.first.c_str());
-		}
-		std::map<std::string, inference_engine_tensor_info>().swap(mOutputLayers);
+
+		mOutputLayers.clear();
 		mOutputLayers = property.layers;
 
 		LOGI("LEAVE");
@@ -420,19 +412,15 @@ namespace TFLiteImpl
 
 			std::vector<size_t> shape_nhwc;
 
-			for (int idx = 0;
-					idx < mInterpreter->tensor(layer.second)->dims->size; idx++) {
-				shape_nhwc.push_back(
-						mInterpreter->tensor(layer.second)->dims->data[idx]);
-			}
+			for (int idx = 0; idx < mInterpreter->tensor(layer.second)->dims->size; idx++)
+				shape_nhwc.push_back(mInterpreter->tensor(layer.second)->dims->data[idx]);
 
 			inference_engine_tensor_info tensor_info {
 				shape_nhwc, INFERENCE_TENSOR_SHAPE_NHWC,
 				INFERENCE_TENSOR_DATA_TYPE_NONE, 1
 			};
 
-			switch (mInterpreter->tensor(layer.second)->type)
-			{
+			switch (mInterpreter->tensor(layer.second)->type) {
 			case kTfLiteUInt8:
 				LOGI("type is kTfLiteUInt8");
 				tensor_info.data_type = INFERENCE_TENSOR_DATA_TYPE_UINT8;
@@ -446,9 +434,9 @@ namespace TFLiteImpl
 				return INFERENCE_ENGINE_ERROR_NOT_SUPPORTED_FORMAT;
 			}
 
-			for (auto& dim : tensor_info.shape) {
+			for (auto& dim : tensor_info.shape)
 				tensor_info.size *= dim;
-			}
+
 			layers.insert(std::make_pair(mInterpreter->tensor(layer.second)->name, tensor_info));
 
 		}