paddle.fluid.layers.tensor. zeros ( shape, dtype, force_cpu=False, name=None ) [source]

The OP creates a tensor of specified shape and dtype, and fills it with 0. Its stop_gradient will be set to True to stop gradient computation.

  • shape (tuple|list|Tensor) – Shape of output Tensor, the data type of shape is int32 or int64.

  • dtype (np.dtype|str) – Data type of output Tensor, it supports bool, float16, float32, float64, int32 and int64.

  • force_cpu (bool, optional) – Whether force to store the output Tensor in CPU memory. If force_cpu is False, the output Tensor will be stored in running device memory. Default: False.

  • name (str, optional) – The default value is None. Normally there is no need for user to set this property. For more information, please refer to Name.


A tensor of data type dtype with shape shape and all elements set to 0.

Return type



import paddle.fluid as fluid
data = fluid.layers.zeros(shape=[3, 2], dtype='float32') # [[0., 0.], [0., 0.], [0., 0.]]

# shape is a Tensor
shape = fluid.layers.fill_constant(shape=[2], dtype='int32', value=2)
data1 = fluid.layers.zeros(shape=shape, dtype='int32') #[[0, 0], [0, 0]]