diff --git a/paddle/fluid/API.spec b/paddle/fluid/API.spec
index 1a59d0be4c2593783dfefbefee84693b0fe48b49..393412c590041bb0d8ff50b4ce18177f3b542d78 100644
--- a/paddle/fluid/API.spec
+++ b/paddle/fluid/API.spec
@@ -119,8 +119,8 @@ paddle.fluid.layers.adaptive_pool3d (ArgSpec(args=['input', 'pool_size', 'pool_t
 paddle.fluid.layers.batch_norm (ArgSpec(args=['input', 'act', 'is_test', 'momentum', 'epsilon', 'param_attr', 'bias_attr', 'data_layout', 'in_place', 'name', 'moving_mean_name', 'moving_variance_name', 'do_model_average_for_mean_and_var', 'fuse_with_relu', 'use_global_stats'], varargs=None, keywords=None, defaults=(None, False, 0.9, 1e-05, None, None, 'NCHW', False, None, None, None, False, False, False)), ('document', '4cc22c3553e73a958e8b9a240d894431'))
 paddle.fluid.layers.data_norm (ArgSpec(args=['input', 'act', 'epsilon', 'param_attr', 'data_layout', 'in_place', 'name', 'moving_mean_name', 'moving_variance_name', 'do_model_average_for_mean_and_var'], varargs=None, keywords=None, defaults=(None, 1e-05, None, 'NCHW', False, None, None, None, False)), ('document', '2460b30fb87037555208fa8ac6fc1787'))
 paddle.fluid.layers.beam_search_decode (ArgSpec(args=['ids', 'scores', 'beam_size', 'end_id', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '83e08f21af41ac8bac37aeab1f86fdd0'))
-paddle.fluid.layers.conv2d_transpose (ArgSpec(args=['input', 'num_filters', 'output_size', 'filter_size', 'padding', 'stride', 'dilation', 'groups', 'param_attr', 'bias_attr', 'use_cudnn', 'act', 'name'], varargs=None, keywords=None, defaults=(None, None, 0, 1, 1, None, None, None, True, None, None)), ('document', '903ac9a778e0bf1bf649bd71e9d0ba0c'))
-paddle.fluid.layers.conv3d_transpose (ArgSpec(args=['input', 'num_filters', 'output_size', 'filter_size', 'padding', 'stride', 'dilation', 'groups', 'param_attr', 'bias_attr', 'use_cudnn', 'act', 'name'], varargs=None, keywords=None, defaults=(None, None, 0, 1, 1, None, None, None, True, None, None)), ('document', '9b1f13c1fc872f76f8f84cf11e955f53'))
+paddle.fluid.layers.conv2d_transpose (ArgSpec(args=['input', 'num_filters', 'output_size', 'filter_size', 'padding', 'stride', 'dilation', 'groups', 'param_attr', 'bias_attr', 'use_cudnn', 'act', 'name'], varargs=None, keywords=None, defaults=(None, None, 0, 1, 1, None, None, None, True, None, None)), ('document', 'b99808e42a00c2656e8e90d9e360eb35'))
+paddle.fluid.layers.conv3d_transpose (ArgSpec(args=['input', 'num_filters', 'output_size', 'filter_size', 'padding', 'stride', 'dilation', 'groups', 'param_attr', 'bias_attr', 'use_cudnn', 'act', 'name'], varargs=None, keywords=None, defaults=(None, None, 0, 1, 1, None, None, None, True, None, None)), ('document', 'b4ad2a81becb8a492e9494d3974df662'))
 paddle.fluid.layers.sequence_expand (ArgSpec(args=['x', 'y', 'ref_level', 'name'], varargs=None, keywords=None, defaults=(-1, None)), ('document', '10e122eb755c2bd1f78ef2332b28f1a0'))
 paddle.fluid.layers.sequence_expand_as (ArgSpec(args=['x', 'y', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '858c432e7cbd8bb952cc2eb555457d50'))
 paddle.fluid.layers.sequence_pad (ArgSpec(args=['x', 'pad_value', 'maxlen', 'name'], varargs=None, keywords=None, defaults=(None, None)), ('document', '1ba3ccfe13ed5091e113c09c13dc3a20'))
diff --git a/python/paddle/fluid/layers/nn.py b/python/paddle/fluid/layers/nn.py
index c0d430d7f180bb4160eed566d09eb86b19997782..ee5ede577125c526cc43f58839a11ef4bee23f5c 100644
--- a/python/paddle/fluid/layers/nn.py
+++ b/python/paddle/fluid/layers/nn.py
@@ -1470,7 +1470,7 @@ def dropout(x,
             'dropout_prob': dropout_prob,
             'is_test': is_test,
             'fix_seed': seed is not None,
-            'seed': seed if seed is not None else 0,
+            'seed': seed,
             'dropout_implementation': dropout_implementation,
         })
     return out
@@ -3690,7 +3690,7 @@ def conv2d_transpose(input,
     Parameters(dilations, strides, paddings) are two elements. These two elements
     represent height and width, respectively. The details of convolution transpose
     layer, please refer to the following explanation and references
-    `therein <http://www.matthewzeiler.com/wp-content/uploads/2017/07/cvpr2010.pdf>`_.
+    `therein <https://ieeexplore.ieee.org/document/5539957>`_.
     If bias attribution and activation type are provided, bias is added to
     the output of the convolution, and the corresponding activation function
     is applied to the final result.
@@ -3728,8 +3728,15 @@ def conv2d_transpose(input,
 
            H^\prime_{out} &= (H_{in} - 1) * strides[0] - 2 * paddings[0] + dilations[0] * (H_f - 1) + 1 \\\\
            W^\prime_{out} &= (W_{in} - 1) * strides[1] - 2 * paddings[1] + dilations[1] * (W_f - 1) + 1 \\\\
-           H_{out} &\in [ H^\prime_{out}, H^\prime_{out} + strides[0] ) \\\\
-           W_{out} &\in [ W^\prime_{out}, W^\prime_{out} + strides[1] )
+           H_{out} &\in [ H^\prime_{out}, H^\prime_{out} + strides[0] ] \\\\
+           W_{out} &\in [ W^\prime_{out}, W^\prime_{out} + strides[1] ] 
+
+    Note:
+          if output_size is None, :math:`H_{out} = H^\prime_{out}, W_{out} = W^\prime_{out}`; 
+          else, the :math:`H_{out}` of the output size must between :math:`H^\prime_{out}` 
+          and :math:`H^\prime_{out} + strides[0]`, and the :math:`W_{out}` of the output size must 
+          between :math:`W^\prime_{out}` and :math:`W^\prime_{out} + strides[1]`, 
+          conv2d_transpose can compute the kernel size automatically.
 
     Args:
         input(Variable): The input image with [N, C, H, W] format.
@@ -3882,7 +3889,7 @@ def conv3d_transpose(input,
     is the width of the feature. Parameters(dilations, strides, paddings) are
     two elements. These two elements represent height and width, respectively.
     The details of convolution transpose layer, please refer to the following
-    explanation and references `therein <http://www.matthewzeiler.com/wp-content/uploads/2017/07/cvpr2010.pdf>`_.
+    explanation and references `therein <https://ieeexplore.ieee.org/document/5539957>`_.
     If bias attribution and activation type are provided, bias is added to
     the output of the convolution, and the corresponding activation function
     is applied to the final result.