paddle.fluid.contrib.layers.nn. search_pyramid_hash ( input, num_emb, space_len, pyramid_layer, rand_len, drop_out_percent, is_training, use_filter, white_list_len, black_list_len, seed, lr, param_attr=None, param_attr_wl=None, param_attr_bl=None, name=None, distribute_update_vars=None, dtype='float32' ) [source]

Pyramid hash embedding

  • input (Variable) – LoDTensor<int32> Variable contained the IDs’ information.

  • num_emb (int) – The embedding size of output.

  • space_len (int) – The length of pyramid hash embedding space.

  • pyramid_layer (int) – The number of pyramid layers. It should be greater than 2.

  • rand_len (int) – The minimum length of pyramid hash cell.

  • drop_out_percent (float) – The probability of dropping out the input token randomly. It should satisfy: [0., 1.]

  • is_training (bool) – Whether in training or testing phrase.

  • use_filter (bool) – If set True, the white filter and black filter should be given by param_attr_wl and param_attr_bl .

  • white_list_len (int) – If set \(white_list_len>0\) , white filter with shape [white_list_len, 1] should be provided by param_attr_wl.

  • black_list_len (int) – If set \(black_list_len>0\) , black filter with shape [black_list_len, 1] should be provided by param_attr_bl.

  • seed (int) – The number of random seed.

  • lr (float) – The learning rate of weight created by param_attr with shape [space_len+rand_len, 1] in this layer.

  • param_attr (ParamAttr) – To specify the weight parameter property. Default: None, which means the default weight parameter property is used. See usage for details in api_fluid_ParamAttr .

  • param_attr_wl (ParamAttr) – Specified parameters of white filter.

  • param_attr_bl (ParamAttr) – Specified parameters of black filter.

  • distribute_update_vars (list[]) – Decided which params should be updated in distribute training. Used in Distribute Transpiler to create a trainer/server program.

  • 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 .

  • dtype (str) – The data type of output variable, float32.


LoDTensor of pyramid hash embedding.

Return type