Created by: qingqing01

For example:

import paddle.v2.fluid as fluid
import paddle.v2.fluid.layers as layers

dshape = [4, 3, 28, 28]
data = layers.data(name='data', shape=[3, 28, 28], dtype='float32')
conv = layers.conv2d(data, 20, 3, stride=[1, 1], padding=[1, 1])

print conv.shape

The output is：

(-1L, 20L, 28L, 28L)

Since the type of dimension in Tensor is int64_t, the integer in shape is 20L, 28L.