diff --git a/paddle/operators/ctc_align_op.cu b/paddle/operators/ctc_align_op.cu
index 918df83effb3af75e831447aa332061f85b8c14c..cea595d7c5d461b40198e622abf08248e7ca69e1 100644
--- a/paddle/operators/ctc_align_op.cu
+++ b/paddle/operators/ctc_align_op.cu
@@ -82,7 +82,7 @@ class CTCAlignOpCUDAKernel : public framework::OpKernel<T> {
     output->Resize({static_cast<int64_t>(host_out_lod0.back()), 1});
 
     if (host_out_lod0.back() == 0) {
-      output->Resize({1});
+      output->Resize({1, 1});
       output->mutable_data<T>(ctx.GetPlace());
       math::SetConstant<platform::CUDADeviceContext, T> set_constant;
       set_constant(ctx.template device_context<platform::CUDADeviceContext>(),
diff --git a/paddle/operators/ctc_align_op.h b/paddle/operators/ctc_align_op.h
index 7a063870f3c96a1980ac966806b052646f00d9d8..54ad1d6f5cc96c884c9e0c101c44d8d629792f8f 100644
--- a/paddle/operators/ctc_align_op.h
+++ b/paddle/operators/ctc_align_op.h
@@ -71,7 +71,7 @@ class CTCAlignKernel : public framework::OpKernel<T> {
     output->Resize({static_cast<int64_t>(output_lod0.back()), 1});
     // for empty sequence
     if (output_lod0.back() == 0) {
-      output->Resize({1});
+      output->Resize({1, 1});
       output_data = output->mutable_data<T>(ctx.GetPlace());
       output_data[0] = -1;
     }
diff --git a/python/paddle/v2/fluid/layers/nn.py b/python/paddle/v2/fluid/layers/nn.py
index 2209625344e08f9ab82474c597b07f02226a2606..0b3b56bc22a535efd6da95c3c26364f268f0eb61 100644
--- a/python/paddle/v2/fluid/layers/nn.py
+++ b/python/paddle/v2/fluid/layers/nn.py
@@ -2526,7 +2526,7 @@ def ctc_greedy_decoder(input, blank, name=None):
 
     Returns:
         Variable: CTC greedy decode result. If all the sequences in result were
-        empty, the result LoDTensor will be [-1] with LoD [[0]] and dims [1].
+        empty, the result LoDTensor will be [-1] with LoD [[0]] and dims [1, 1].
 
     Examples:
         .. code-block:: python