diff --git a/paddle/function/CMakeLists.txt b/paddle/function/CMakeLists.txt
index 5e170714cf5b183fcf6e76d34746333397e6b060..19f64eefd184e9fa6ba0ddc0ddf83ed6a54c811b 100644
--- a/paddle/function/CMakeLists.txt
+++ b/paddle/function/CMakeLists.txt
@@ -29,6 +29,7 @@ if(WITH_GPU)
     add_simple_unittest(MulOpTest)
     add_simple_unittest(CosSimOpTest)
     add_simple_unittest(RowConvOpTest)
+    add_simple_unittest(ImageExpandOpTest)
 endif()
 
 add_simple_unittest(ConvOpTest)
diff --git a/paddle/function/ImageExpandOp.cpp b/paddle/function/ImageExpandOp.cpp
index ca1d117db8845c3dca814dcee575cd73e6cf5a5a..00a2571936b399d62b5cea90874a034f6771e310 100644
--- a/paddle/function/ImageExpandOp.cpp
+++ b/paddle/function/ImageExpandOp.cpp
@@ -116,6 +116,7 @@ public:
     CHECK_EQ(numInputs_, inputs.size());
     CHECK_EQ(numOutputs_, outputs.size());
     check(inputs, outputs);
+    CHECK_EQ(outputs[0].getArgType(), ASSIGN_TO);
     const TensorShape& image = inputs[0].shape();
     const TensorShape& sequence = outputs[0].shape();
 
diff --git a/paddle/function/ImageExpandOpTest.cpp b/paddle/function/ImageExpandOpTest.cpp
new file mode 100644
index 0000000000000000000000000000000000000000..fb312549dc758ee6edb0df34332a9c1d8d0035a7
--- /dev/null
+++ b/paddle/function/ImageExpandOpTest.cpp
@@ -0,0 +1,107 @@
+/* Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserve.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License. */
+
+#include <gtest/gtest.h>
+#include "FunctionTest.h"
+
+namespace paddle {
+
+TEST(ImageExpandForward, real) {
+  for (size_t batchSize : {5, 32}) {
+    for (size_t channels : {1, 5, 32}) {
+      for (size_t inputHeight : {5, 33, 100}) {
+        for (size_t inputWidth : {5, 32, 96}) {
+          for (size_t block : {1, 3, 5}) {
+            for (size_t stride : {1, 2}) {
+              for (size_t padding : {0, 1}) {
+                // init Test object
+                std::vector<size_t> strides = {stride, stride};
+                std::vector<size_t> paddings = {padding, padding};
+                std::vector<size_t> blocks = {block, block};
+                CpuGpuFuncCompare test("ImageExpand",
+                                       FuncConfig()
+                                           .set("strides", strides)
+                                           .set("paddings", paddings)
+                                           .set("blocks", blocks));
+
+                size_t outputHeight =
+                    1 +
+                    (inputHeight + 2 * padding - block + stride - 1) / stride;
+                size_t outputWidth =
+                    1 +
+                    (inputWidth + 2 * padding - block + stride - 1) / stride;
+                TensorShape inputShape =
+                    TensorShape({batchSize, channels, inputHeight, inputWidth});
+                TensorShape outputShape =
+                    TensorShape({batchSize,
+                                 outputHeight * outputWidth,
+                                 channels * block * block});
+                test.addInputs(BufferArg(VALUE_TYPE_FLOAT, inputShape));
+                test.addOutputs(BufferArg(VALUE_TYPE_FLOAT, outputShape));
+                // run Function
+                test.run();
+              }
+            }
+          }
+        }
+      }
+    }
+  }
+}
+
+TEST(ImageExpandBackward, real) {
+  for (size_t batchSize : {5, 32}) {
+    for (size_t channels : {1, 5, 32}) {
+      for (size_t inputHeight : {5, 33, 100}) {
+        for (size_t inputWidth : {5, 32, 96}) {
+          for (size_t block : {1, 3, 5}) {
+            for (size_t stride : {1, 2}) {
+              for (size_t padding : {0, 1}) {
+                // init Test object
+                std::vector<size_t> strides = {stride, stride};
+                std::vector<size_t> paddings = {padding, padding};
+                std::vector<size_t> blocks = {block, block};
+                CpuGpuFuncCompare test("ImageExpandGrad",
+                                       FuncConfig()
+                                           .set("strides", strides)
+                                           .set("paddings", paddings)
+                                           .set("blocks", blocks));
+
+                size_t outputHeight =
+                    1 +
+                    (inputHeight + 2 * padding - block + stride - 1) / stride;
+                size_t outputWidth =
+                    1 +
+                    (inputWidth + 2 * padding - block + stride - 1) / stride;
+                TensorShape inputShape =
+                    TensorShape({batchSize, channels, inputHeight, inputWidth});
+                TensorShape outputShape =
+                    TensorShape({batchSize,
+                                 outputHeight * outputWidth,
+                                 channels * block * block});
+                test.addInputs(BufferArg(VALUE_TYPE_FLOAT, outputShape));
+                test.addOutputs(BufferArg(VALUE_TYPE_FLOAT, inputShape),
+                                ADD_TO);
+                // run Function
+                test.run();
+              }
+            }
+          }
+        }
+      }
+    }
+  }
+}
+
+}  // namespace paddle