paddle.fluid.nets. sequence_conv_pool ( input, num_filters, filter_size, param_attr=None, act='sigmoid', pool_type='max', bias_attr=None ) [source]

Static Graph

This api takes input as an LoDTensor. If input is a Tensor, please use api_fluid_nets_simple_img_conv_pool instead

The sequence_conv_pool is composed of api_fluid_layers_sequence_conv and api_fluid_layers_sequence_pool .

  • input (Tensor) – 2-D LoDTensor, the input of sequence_conv, which supports variable-time length input sequence. The underlying of input is a matrix with shape (T, N), where T is the total time steps in this mini-batch and N is the input_hidden_size. The data type is float32 or float64.

  • num_filters (int) – The number of filter.

  • filter_size (int) – The filter size.

  • param_attr (ParamAttr) – The parameters of the sequence_conv Layer. Default: None.

  • act (str|None) – Activation type for Sequence_conv Layer. If set to None, no activation will be applied. Default: “sigmoid”.

  • pool_type (str) – Pooling type can be \(max\) for max-pooling, \(average\) for average-pooling, \(sum\) for sum-pooling, \(sqrt\) for sqrt-pooling. Default \(max\).

  • bias_attr (ParamAttr|bool|None) – The parameter attribute for the bias of sequence_conv. If it is set to False, no bias will be added to the output units. If it is set to None or one attribute of ParamAttr, sequence_conv will create ParamAttr as bias_attr. If the Initializer of the bias_attr is not set, the bias is initialized zero. Default: None.


The final result after sequence_conv and sequence_pool. It is a 2-D Tensor, with the same data type as input

Return Type:



import paddle.fluid as fluid
import paddle
input_dim = 100 #len(word_dict)
emb_dim = 128
hid_dim = 512
data ="words", shape=[None, 1], dtype="int64", lod_level=1)
emb = fluid.layers.embedding(input=data, size=[input_dim, emb_dim], is_sparse=True)
seq_conv = fluid.nets.sequence_conv_pool(input=emb,