diff --git a/src/armnnTfLiteParser/TfLiteParser.cpp b/src/armnnTfLiteParser/TfLiteParser.cpp
index e5af76b..e3306b3 100644
--- a/src/armnnTfLiteParser/TfLiteParser.cpp
+++ b/src/armnnTfLiteParser/TfLiteParser.cpp
@@ -452,6 +452,7 @@
     m_ParserFunctions[tflite::BuiltinOperator_SQUEEZE]           =  &TfLiteParser::ParseSqueeze;
     m_ParserFunctions[tflite::BuiltinOperator_ADD]               =  &TfLiteParser::ParseAdd;
     m_ParserFunctions[tflite::BuiltinOperator_MUL]               =  &TfLiteParser::ParseMul;
+    m_ParserFunctions[tflite::BuiltinOperator_MEAN]              =  &TfLiteParser::ParseMean;
 }
 
 void TfLiteParser::ResetParser()
@@ -1049,6 +1050,42 @@
     RegisterOutputSlots(subgraphIndex, operatorIndex, layer, {outputTensorIndexes[0]});
 }
 
+void TfLiteParser::ParseMean(size_t subgraphIndex, size_t operatorIndex)
+{
+    CHECK_MODEL(m_Model, subgraphIndex, operatorIndex);
+
+    auto inputs = GetInputs(m_Model, subgraphIndex, operatorIndex);
+
+    auto outputs = GetOutputs(m_Model, subgraphIndex, operatorIndex);
+    CHECK_VALID_SIZE(outputs.size(), 1);
+
+    armnn::TensorInfo dimTensorInfo = ToTensorInfo(inputs[1]);
+    BufferRawPtr bufferPtr = GetBuffer(m_Model, inputs[1]->buffer);
+
+    armnn::MeanDescriptor desc;
+    std::vector<unsigned int> axis(dimTensorInfo.GetNumElements());
+    ::memcpy(axis.data(), bufferPtr->data.data(), dimTensorInfo.GetNumBytes());
+    desc.m_Axis = axis;
+
+    armnn::TensorInfo inputTensorInfo  = ToTensorInfo(inputs[0]);
+    armnn::TensorInfo outputTensorInfo = ToTensorInfo(outputs[0]);
+
+    desc.m_KeepDims =
+        inputTensorInfo.GetNumDimensions() == outputTensorInfo.GetNumDimensions() ?
+            true : false;
+
+    auto layerName = boost::str(boost::format("Mean:%1%:%2%") % subgraphIndex % operatorIndex);
+    IConnectableLayer* layer = m_Network->AddMeanLayer(desc, layerName.c_str());
+
+    layer->GetOutputSlot(0).SetTensorInfo(outputTensorInfo);
+
+    auto inputTensorIndexes = AsUnsignedVector(GetInputTensorIds(m_Model, subgraphIndex, operatorIndex));
+    RegisterInputSlots(subgraphIndex, operatorIndex, layer, {inputTensorIndexes[0]});
+
+    auto outputTensorIndexes = AsUnsignedVector(GetOutputTensorIds(m_Model, subgraphIndex, operatorIndex));
+    RegisterOutputSlots(subgraphIndex, operatorIndex, layer, {outputTensorIndexes[0]});
+}
+
 void TfLiteParser::ParseRelu(size_t subgraphIndex, size_t operatorIndex)
 {
     CHECK_MODEL(m_Model, subgraphIndex, operatorIndex);
diff --git a/src/armnnTfLiteParser/TfLiteParser.hpp b/src/armnnTfLiteParser/TfLiteParser.hpp
index 42e1814..581e012 100644
--- a/src/armnnTfLiteParser/TfLiteParser.hpp
+++ b/src/armnnTfLiteParser/TfLiteParser.hpp
@@ -103,6 +103,7 @@
     void ParseSqueeze(size_t subgraphIndex, size_t operatorIndex);
     void ParseAdd(size_t subgraphIndex, size_t operatorIndex);
     void ParseMul(size_t subgraphIndex, size_t operatorIndex);
+    void ParseMean(size_t subgraphIndex, size_t operatorIndex);
 
     void ParsePool(size_t subgraphIndex, size_t operatorIndex, armnn::PoolingAlgorithm algorithm);
 
diff --git a/src/armnnTfLiteParser/test/Mean.cpp b/src/armnnTfLiteParser/test/Mean.cpp
new file mode 100644
index 0000000..d7cb2a2
--- /dev/null
+++ b/src/armnnTfLiteParser/test/Mean.cpp
@@ -0,0 +1,99 @@
+//
+// Copyright © 2017 Arm Ltd. All rights reserved.
+// SPDX-License-Identifier: MIT
+//
+
+#include <boost/test/unit_test.hpp>
+#include "ParserFlatbuffersFixture.hpp"
+#include "../TfLiteParser.hpp"
+
+#include <string>
+#include <iostream>
+
+BOOST_AUTO_TEST_SUITE(TensorflowLiteParser)
+
+struct MeanNoReduceFixture : public ParserFlatbuffersFixture
+{
+    explicit MeanNoReduceFixture(const std::string & inputShape,
+                                 const std::string & outputShape,
+                                 const std::string & dimShape,
+                                 const std::string & dimData)
+    {
+        m_JsonString = R"(
+            {
+                "version": 3,
+                "operator_codes": [ { "builtin_code": "MEAN" } ],
+                "subgraphs": [ {
+                    "tensors": [
+                        {
+                            "shape": )" + inputShape + R"(,
+                            "type": "FLOAT32",
+                            "buffer": 0,
+                            "name": "inputTensor",
+                            "quantization": {
+                                "min": [ 0.0 ],
+                                "max": [ 255.0 ],
+                                "scale": [ 1.0 ],
+                                "zero_point": [ 0 ],
+                            }
+                        },
+                        {
+                            "shape": )" + outputShape + R"( ,
+                            "type": "FLOAT32",
+                            "buffer": 1,
+                            "name": "outputTensor",
+                            "quantization": {
+                                "min": [ 0.0 ],
+                                "max": [ 255.0 ],
+                                "scale": [ 1.0 ],
+                                "zero_point": [ 0 ],
+                            }
+                        },
+                        {
+                            "shape": )" + dimShape + R"( ,
+                            "type": "INT32",
+                            "buffer": 2,
+                            "name": "dimShape",
+                            "quantization": {
+                                "min": [ 0.0 ],
+                                "max": [ 255.0 ],
+                                "scale": [ 1.0 ],
+                                "zero_point": [ 0 ],
+                            }
+                        }
+                    ],
+                    "inputs": [ 0 ],
+                    "outputs": [ 1 ],
+                    "operators": [
+                        {
+                            "opcode_index": 0,
+                            "inputs": [ 0 , 2 ],
+                            "outputs": [ 1 ],
+                            "custom_options_format": "FLEXBUFFERS"
+                        }
+                    ],
+                } ],
+                "buffers" : [
+                    { },
+                    { },
+                    { "data": )" + dimData + R"(, },
+                ]
+            }
+        )";
+        SetupSingleInputSingleOutput("inputTensor", "outputTensor");
+    }
+};
+
+struct SimpleMeanNoReduceFixture : public MeanNoReduceFixture
+{
+    SimpleMeanNoReduceFixture() : MeanNoReduceFixture("[ 2, 2 ]", "[ 1, 1 ]", "[ 0 ]", "[ ]") {}
+};
+
+BOOST_FIXTURE_TEST_CASE(ParseMeanNoReduce, SimpleMeanNoReduceFixture)
+{
+    RunTest<2, float>(0, {{ "inputTensor", { 1.0f, 1.0f, 2.0f, 2.0f } } },
+                         {{ "outputTensor", { 1.5f } } });
+}
+
+BOOST_AUTO_TEST_SUITE_END()
+