diff --git a/paddle/fluid/operators/dropout_op.h b/paddle/fluid/operators/dropout_op.h
index 9d9eb4a82a075f27764a73d0e976dbf3f7181cb1..161c4282ec277a19c19921267eaa4cb46b859900 100644
--- a/paddle/fluid/operators/dropout_op.h
+++ b/paddle/fluid/operators/dropout_op.h
@@ -29,6 +29,10 @@ template <typename T, int MajorType = Eigen::RowMajor,
           typename IndexType = Eigen::DenseIndex>
 using EigenMatrix = framework::EigenMatrix<T, MajorType, IndexType>;
 
+template <typename T, int MajorType = Eigen::RowMajor,
+          typename IndexType = Eigen::DenseIndex>
+using EigenVector = framework::EigenVector<T, MajorType, IndexType>;
+
 template <typename DeviceContext, typename T>
 class CPUDropoutKernel : public framework::OpKernel<T> {
  public:
@@ -116,9 +120,9 @@ class DropoutGradKernel : public framework::OpKernel<T> {
     auto* mask = context.Input<Tensor>("Mask");
     grad_x->mutable_data<T>(context.GetPlace());
 
-    auto M = EigenMatrix<uint8_t>::Reshape(*mask, 1);
-    auto dX = EigenMatrix<T>::Reshape(*grad_x, 1);
-    auto dY = EigenMatrix<T>::Reshape(*grad_y, 1);
+    auto M = EigenVector<uint8_t>::Flatten(*mask);
+    auto dX = EigenVector<T>::Flatten(*grad_x);
+    auto dY = EigenVector<T>::Flatten(*grad_y);
 
     auto& place =
         *context.template device_context<DeviceContext>().eigen_device();
diff --git a/python/paddle/fluid/tests/unittests/test_dropout_op.py b/python/paddle/fluid/tests/unittests/test_dropout_op.py
index ceec1190279212fbe6f3f128bdd1397cdb9ea1a2..97137e91aa75975d189342f9ad6b9e1caf5b2346 100644
--- a/python/paddle/fluid/tests/unittests/test_dropout_op.py
+++ b/python/paddle/fluid/tests/unittests/test_dropout_op.py
@@ -40,6 +40,23 @@ class TestDropoutOp(OpTest):
         self.check_grad(['X'], 'Out')
 
 
+class TestDropoutOpInput1d(OpTest):
+    def setUp(self):
+        self.op_type = "dropout"
+        self.inputs = {'X': np.random.random((2000)).astype("float32")}
+        self.attrs = {'dropout_prob': 0.0, 'fix_seed': True, 'is_test': False}
+        self.outputs = {
+            'Out': self.inputs['X'],
+            'Mask': np.ones((2000)).astype('uint8')
+        }
+
+    def test_check_output(self):
+        self.check_output()
+
+    def test_check_grad_normal(self):
+        self.check_grad(['X'], 'Out')
+
+
 class TestDropoutOp2(TestDropoutOp):
     def setUp(self):
         self.op_type = "dropout"
@@ -436,6 +453,13 @@ class TestDropoutFAPIError(unittest.TestCase):
 
             self.assertRaises(ValueError, test_axis_max)
 
+            def test_axis_min():
+                # minimum of axis should greater equal than 0
+                x2 = fluid.data(name='x2', shape=[3, 4, 5, 6], dtype="float32")
+                paddle.nn.functional.dropout(x2, axis=[0, -1])
+
+            self.assertRaises(ValueError, test_axis_min)
+
             def test_axis_len():
                 # length of axis should not greater than dimensions of x
                 x2 = fluid.data(name='x2', shape=[3, 4, 5, 6], dtype="float32")
diff --git a/python/paddle/nn/functional/common.py b/python/paddle/nn/functional/common.py
index 623af3277fba0e29fb77b02c711e258602f1f75a..633920dc7e804d18ff63cce4ddb9aa2b215c0bd5 100644
--- a/python/paddle/nn/functional/common.py
+++ b/python/paddle/nn/functional/common.py
@@ -910,12 +910,12 @@ def dropout(x,
             #get mask shape
             input_shape = x.shape
             drop_axes = [axis] if isinstance(axis, int) else axis
-            if max(drop_axes) > len(input_shape) - 1:
-                raise ValueError("axis value should less than dimensions of x:{}, but get drop_axes value:{} " \
+            if min(drop_axes) < 0 or max(drop_axes) > len(input_shape) - 1:
+                raise ValueError("axis value should be greater than or equal to 0 and less than dimensions of x:{}, but get axis value:{} " \
                                  .format(len(input_shape), max(drop_axes)))
             if len(drop_axes) > len(input_shape):
                 raise ValueError(
-                    "length of axis should not greater than dimensions of x:{}, but get length of drop axes: {}".
+                    "length of axis should not be greater than dimensions of x:{}, but get length of axis: {}".
                     format(len(input_shape), len(drop_axes)))
             mask_shape = [1] * len(input_shape)
             for i in drop_axes: