# SOME DESCRIPTIVE TITLE. # Copyright (C) 2021, PaddleNLP # This file is distributed under the same license as the PaddleNLP package. # FIRST AUTHOR , 2022. # #, fuzzy msgid "" msgstr "" "Project-Id-Version: PaddleNLP \n" "Report-Msgid-Bugs-To: \n" "POT-Creation-Date: 2022-03-18 21:31+0800\n" "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" "Last-Translator: FULL NAME \n" "Language-Team: LANGUAGE \n" "MIME-Version: 1.0\n" "Content-Type: text/plain; charset=utf-8\n" "Content-Transfer-Encoding: 8bit\n" "Generated-By: Babel 2.9.0\n" #: ../source/paddlenlp.seq2vec.encoder.rst:2 msgid "encoder" msgstr "" #: of paddlenlp.seq2vec.encoder.BoWEncoder:1 #: paddlenlp.seq2vec.encoder.CNNEncoder:1 #: paddlenlp.seq2vec.encoder.GRUEncoder:1 #: paddlenlp.seq2vec.encoder.LSTMEncoder:1 #: paddlenlp.seq2vec.encoder.RNNEncoder:1 #: paddlenlp.seq2vec.encoder.TCNEncoder:1 msgid "基类：:class:`paddle.fluid.dygraph.layers.Layer`" msgstr "" #: of paddlenlp.seq2vec.encoder.BoWEncoder:1 msgid "" "A `BoWEncoder` takes as input a sequence of vectors and returns a single " "vector, which simply sums the embeddings of a sequence across the time " "dimension. The input to this encoder is of shape `(batch_size, " "num_tokens, emb_dim)`, and the output is of shape `(batch_size, " "emb_dim)`." msgstr "" #: of paddlenlp.seq2vec.encoder.BoWEncoder #: paddlenlp.seq2vec.encoder.BoWEncoder.forward #: paddlenlp.seq2vec.encoder.CNNEncoder #: paddlenlp.seq2vec.encoder.CNNEncoder.forward #: paddlenlp.seq2vec.encoder.GRUEncoder #: paddlenlp.seq2vec.encoder.GRUEncoder.forward #: paddlenlp.seq2vec.encoder.LSTMEncoder #: paddlenlp.seq2vec.encoder.LSTMEncoder.forward #: paddlenlp.seq2vec.encoder.RNNEncoder #: paddlenlp.seq2vec.encoder.RNNEncoder.forward #: paddlenlp.seq2vec.encoder.TCNEncoder #: paddlenlp.seq2vec.encoder.TCNEncoder.forward msgid "参数" msgstr "" #: of paddlenlp.seq2vec.encoder.BoWEncoder:6 #: paddlenlp.seq2vec.encoder.CNNEncoder:20 msgid "The dimension of each vector in the input sequence." msgstr "" #: of paddlenlp.seq2vec.encoder.BoWEncoder:10 #: paddlenlp.seq2vec.encoder.CNNEncoder:39 #: paddlenlp.seq2vec.encoder.GRUEncoder:44 #: paddlenlp.seq2vec.encoder.LSTMEncoder:43 #: paddlenlp.seq2vec.encoder.RNNEncoder:43 msgid "示例" msgstr "" #: of paddlenlp.seq2vec.encoder.BoWEncoder.get_input_dim:1 msgid "" "Returns the dimension of the vector input for each element in the " "sequence input to a `BoWEncoder`. This is not the shape of the input " "tensor, but the last element of that shape." msgstr "" #: of paddlenlp.seq2vec.encoder.BoWEncoder.get_output_dim:1 msgid "" "Returns the dimension of the final vector output by this `BoWEncoder`. " "This is not the shape of the returned tensor, but the last element of " "that shape." msgstr "" #: of paddlenlp.seq2vec.encoder.BoWEncoder.forward:1 msgid "It simply sums the embeddings of a sequence across the time dimension." msgstr "" #: of paddlenlp.seq2vec.encoder.BoWEncoder.forward:3 msgid "" "Shape as `(batch_size, num_tokens, emb_dim)` and dtype as `float32` or " "`float64`. The sequence length of the input sequence." msgstr "" #: of paddlenlp.seq2vec.encoder.BoWEncoder.forward:6 msgid "" "Shape same as `inputs`. Its each elements identify whether the " "corresponding input token is padding or not. If True, not padding token. " "If False, padding token. Defaults to `None`." msgstr "" #: of paddlenlp.seq2vec.encoder.BoWEncoder.forward #: paddlenlp.seq2vec.encoder.CNNEncoder.forward #: paddlenlp.seq2vec.encoder.GRUEncoder.forward #: paddlenlp.seq2vec.encoder.LSTMEncoder.forward #: paddlenlp.seq2vec.encoder.RNNEncoder.forward #: paddlenlp.seq2vec.encoder.TCNEncoder.forward msgid "返回" msgstr "" #: of paddlenlp.seq2vec.encoder.BoWEncoder.forward:12 msgid "" "Returns tensor `summed`, the result vector of BagOfEmbedding. Its data " "type is same as `inputs` and its shape is `[batch_size, emb_dim]`." msgstr "" #: of paddlenlp.seq2vec.encoder.BoWEncoder.forward #: paddlenlp.seq2vec.encoder.CNNEncoder.forward #: paddlenlp.seq2vec.encoder.GRUEncoder.forward #: paddlenlp.seq2vec.encoder.LSTMEncoder.forward #: paddlenlp.seq2vec.encoder.RNNEncoder.forward #: paddlenlp.seq2vec.encoder.TCNEncoder.forward msgid "返回类型" msgstr "" #: of paddlenlp.seq2vec.encoder.CNNEncoder:1 msgid "" "A `CNNEncoder` takes as input a sequence of vectors and returns a single " "vector, a combination of multiple convolution layers and max pooling " "layers. The input to this encoder is of shape `(batch_size, num_tokens, " "emb_dim)`, and the output is of shape `(batch_size, output_dim)` or " "`(batch_size, len(ngram_filter_sizes) * num_filter)`." msgstr "" #: of paddlenlp.seq2vec.encoder.CNNEncoder:6 msgid "" "The CNN has one convolution layer for each ngram filter size. Each " "convolution operation gives out a vector of size num_filter. The number " "of times a convolution layer will be used is `num_tokens - ngram_size + " "1`. The corresponding maxpooling layer aggregates all these outputs from " "the convolution layer and outputs the max." msgstr "" #: of paddlenlp.seq2vec.encoder.CNNEncoder:11 msgid "" "This operation is repeated for every ngram size passed, and consequently " "the dimensionality of the output after maxpooling is " "`len(ngram_filter_sizes) * num_filter`. This then gets (optionally) " "projected down to a lower dimensional output, specified by `output_dim`." msgstr "" #: of paddlenlp.seq2vec.encoder.CNNEncoder:15 msgid "" "We then use a fully connected layer to project in back to the desired " "output_dim. For more details, refer to `A Sensitivity Analysis of (and " "Practitioners’ Guide to) Convolutional Neural Networks for Sentence " "Classification `__ , Zhang and Wallace " "2016, particularly Figure 1." msgstr "" #: of paddlenlp.seq2vec.encoder.CNNEncoder:22 msgid "" "This is the output dim for each convolutional layer, which is the number " "of \"filters\" learned by that layer." msgstr "" #: of paddlenlp.seq2vec.encoder.CNNEncoder:25 msgid "" "This specifies both the number of convolutional layers we will create and" " their sizes. The default of `(2, 3, 4, 5)` will have four convolutional" " layers, corresponding to encoding ngrams of size 2 to 5 with some number" " of filters." msgstr "" #: of paddlenlp.seq2vec.encoder.CNNEncoder:29 msgid "" "Activation to use after the convolution layers. Defaults to " "`paddle.nn.Tanh()`." msgstr "" #: of paddlenlp.seq2vec.encoder.CNNEncoder:32 msgid "" "After doing convolutions and pooling, we'll project the collected " "features into a vector of this size. If this value is `None`, we will " "just return the result of the max pooling, giving an output of shape " "`len(ngram_filter_sizes) * num_filter`. Defaults to `None`." msgstr "" #: of paddlenlp.seq2vec.encoder.CNNEncoder.get_input_dim:1 msgid "" "Returns the dimension of the vector input for each element in the " "sequence input to a `CNNEncoder`. This is not the shape of the input " "tensor, but the last element of that shape." msgstr "" #: of paddlenlp.seq2vec.encoder.CNNEncoder.get_output_dim:1 msgid "" "Returns the dimension of the final vector output by this `CNNEncoder`. " "This is not the shape of the returned tensor, but the last element of " "that shape." msgstr "" #: of paddlenlp.seq2vec.encoder.CNNEncoder.forward:1 msgid "The combination of multiple convolution layers and max pooling layers." msgstr "" #: of paddlenlp.seq2vec.encoder.CNNEncoder.forward:3 msgid "" "Shape as `(batch_size, num_tokens, emb_dim)` and dtype as `float32` or " "`float64`. Tensor containing the features of the input sequence." msgstr "" #: of paddlenlp.seq2vec.encoder.CNNEncoder.forward:6 msgid "" "Shape shoule be same as `inputs` and dtype as `int32`, `int64`, `float32`" " or `float64`. Its each elements identify whether the corresponding input" " token is padding or not. If True, not padding token. If False, padding " "token. Defaults to `None`." msgstr "" #: of paddlenlp.seq2vec.encoder.CNNEncoder.forward:12 msgid "" "Returns tensor `result`. If output_dim is None, the result shape is of " "`(batch_size, output_dim)` and dtype is `float`; If not, the result shape" " is of `(batch_size, len(ngram_filter_sizes) * num_filter)`." msgstr "" #: of paddlenlp.seq2vec.encoder.GRUEncoder:1 msgid "" "A GRUEncoder takes as input a sequence of vectors and returns a single " "vector, which is a combination of multiple `paddle.nn.GRU " "`__ subclass. The input to this encoder " "is of shape `(batch_size, num_tokens, input_size)`, The output is of " "shape `(batch_size, hidden_size * 2)` if GRU is bidirection; If not, " "output is of shape `(batch_size, hidden_size)`." msgstr "" #: of paddlenlp.seq2vec.encoder.GRUEncoder:9 msgid "" "Paddle's GRU have two outputs: the hidden state for every time step at " "last layer, and the hidden state at the last time step for every layer. " "If `pooling_type` is not None, we perform the pooling on the hidden state" " of every time step at last layer to create a single vector. If None, we " "use the hidden state of the last time step at last layer as a single " "output (shape of `(batch_size, hidden_size)`); And if direction is " "bidirection, the we concat the hidden state of the last forward gru and " "backward gru layer to create a single vector (shape of `(batch_size, " "hidden_size * 2)`)." msgstr "" #: of paddlenlp.seq2vec.encoder.GRUEncoder:17 #: paddlenlp.seq2vec.encoder.LSTMEncoder:17 #: paddlenlp.seq2vec.encoder.RNNEncoder:17 #: paddlenlp.seq2vec.encoder.TCNEncoder:14 msgid "The number of expected features in the input (the last dimension)." msgstr "" #: of paddlenlp.seq2vec.encoder.GRUEncoder:19 #: paddlenlp.seq2vec.encoder.LSTMEncoder:19 #: paddlenlp.seq2vec.encoder.RNNEncoder:19 msgid "The number of features in the hidden state." msgstr "" #: of paddlenlp.seq2vec.encoder.GRUEncoder:21 msgid "" "Number of recurrent layers. E.g., setting num_layers=2 would mean " "stacking two GRUs together to form a stacked GRU, with the second GRU " "taking in outputs of the first GRU and computing the final results. " "Defaults to 1." msgstr "" #: of paddlenlp.seq2vec.encoder.GRUEncoder:26 msgid "" "The direction of the network. It can be \"forward\" and \"bidirect\" (it " "means bidirection network). If \"bidirect\", it is a birectional GRU, and" " returns the concat output from both directions. Defaults to \"forward\"." msgstr "" #: of paddlenlp.seq2vec.encoder.GRUEncoder:31 msgid "" "If non-zero, introduces a Dropout layer on the outputs of each GRU layer " "except the last layer, with dropout probability equal to dropout. " "Defaults to 0.0." msgstr "" #: of paddlenlp.seq2vec.encoder.GRUEncoder:35 msgid "" "If `pooling_type` is None, then the GRUEncoder will return the hidden " "state of the last time step at last layer as a single vector. If " "pooling_type is not None, it must be one of \"sum\", \"max\" and " "\"mean\". Then it will be pooled on the GRU output (the hidden state of " "every time step at last layer) to create a single vector. Defaults to " "`None`" msgstr "" #: of paddlenlp.seq2vec.encoder.GRUEncoder.get_input_dim:1 msgid "" "Returns the dimension of the vector input for each element in the " "sequence input to a `GRUEncoder`. This is not the shape of the input " "tensor, but the last element of that shape." msgstr "" #: of paddlenlp.seq2vec.encoder.GRUEncoder.get_output_dim:1 msgid "" "Returns the dimension of the final vector output by this `GRUEncoder`. " "This is not the shape of the returned tensor, but the last element of " "that shape." msgstr "" #: of paddlenlp.seq2vec.encoder.GRUEncoder.forward:1 msgid "" "GRUEncoder takes the a sequence of vectors and returns a single " "vector, which is a combination of multiple GRU layers. The input to this " "encoder is of shape `(batch_size, num_tokens, input_size)`, The output is" " of shape `(batch_size, hidden_size * 2)` if GRU is bidirection; If not, " "output is of shape `(batch_size, hidden_size)`." msgstr "" #: of paddlenlp.seq2vec.encoder.GRUEncoder.forward:7 #: paddlenlp.seq2vec.encoder.LSTMEncoder.forward:7 #: paddlenlp.seq2vec.encoder.RNNEncoder.forward:7 msgid "" "Shape as `(batch_size, num_tokens, input_size)`. Tensor containing the " "features of the input sequence." msgstr "" #: of paddlenlp.seq2vec.encoder.GRUEncoder.forward:10 #: paddlenlp.seq2vec.encoder.LSTMEncoder.forward:10 #: paddlenlp.seq2vec.encoder.RNNEncoder.forward:10 msgid "Shape as `(batch_size)`. The sequence length of the input sequence." msgstr "" #: of paddlenlp.seq2vec.encoder.GRUEncoder.forward:14 #: paddlenlp.seq2vec.encoder.LSTMEncoder.forward:14 #: paddlenlp.seq2vec.encoder.RNNEncoder.forward:14 msgid "" "Returns tensor `output`, the hidden state at the last time step for every" " layer. Its data type is `float` and its shape is `[batch_size, " "hidden_size]`." msgstr "" #: of paddlenlp.seq2vec.encoder.LSTMEncoder:1 msgid "" "An LSTMEncoder takes as input a sequence of vectors and returns a single " "vector, which is a combination of multiple `paddle.nn.LSTM " "`__ subclass. The input to this encoder" " is of shape `(batch_size, num_tokens, input_size)`. The output is of " "shape `(batch_size, hidden_size * 2)` if LSTM is bidirection; If not, " "output is of shape `(batch_size, hidden_size)`." msgstr "" #: of paddlenlp.seq2vec.encoder.LSTMEncoder:9 msgid "" "Paddle's LSTM have two outputs: the hidden state for every time step at " "last layer, and the hidden state and cell at the last time step for every" " layer. If `pooling_type` is not None, we perform the pooling on the " "hidden state of every time step at last layer to create a single vector. " "If None, we use the hidden state of the last time step at last layer as a" " single output (shape of `(batch_size, hidden_size)`); And if direction " "is bidirection, the we concat the hidden state of the last forward lstm " "and backward lstm layer to create a single vector (shape of `(batch_size," " hidden_size * 2)`)." msgstr "" #: of paddlenlp.seq2vec.encoder.LSTMEncoder:21 msgid "" "Number of recurrent layers. E.g., setting num_layers=2 would mean " "stacking two LSTMs together to form a stacked LSTM, with the second LSTM " "taking in outputs of the first LSTM and computing the final results. " "Defaults to 1." msgstr "" #: of paddlenlp.seq2vec.encoder.LSTMEncoder:26 msgid "" "The direction of the network. It can be \"forward\" or \"bidirect\" (it " "means bidirection network). If \"bidirect\", it is a birectional LSTM, " "and returns the concat output from both directions. Defaults to " "\"forward\"." msgstr "" #: of paddlenlp.seq2vec.encoder.LSTMEncoder:30 msgid "" "If non-zero, introduces a Dropout layer on the outputs of each LSTM layer" " except the last layer, with dropout probability equal to dropout. " "Defaults to 0.0 ." msgstr "" #: of paddlenlp.seq2vec.encoder.LSTMEncoder:34 msgid "" "If `pooling_type` is None, then the LSTMEncoder will return the hidden " "state of the last time step at last layer as a single vector. If " "pooling_type is not None, it must be one of \"sum\", \"max\" and " "\"mean\". Then it will be pooled on the LSTM output (the hidden state of " "every time step at last layer) to create a single vector. Defaults to " "`None`." msgstr "" #: of paddlenlp.seq2vec.encoder.LSTMEncoder.get_input_dim:1 msgid "" "Returns the dimension of the vector input for each element in the " "sequence input to a `LSTMEncoder`. This is not the shape of the input " "tensor, but the last element of that shape." msgstr "" #: of paddlenlp.seq2vec.encoder.LSTMEncoder.get_output_dim:1 msgid "" "Returns the dimension of the final vector output by this `LSTMEncoder`. " "This is not the shape of the returned tensor, but the last element of " "that shape." msgstr "" #: of paddlenlp.seq2vec.encoder.LSTMEncoder.forward:1 msgid "" "LSTMEncoder takes the a sequence of vectors and returns a single " "vector, which is a combination of multiple LSTM layers. The input to this" " encoder is of shape `(batch_size, num_tokens, input_size)`, The output " "is of shape `(batch_size, hidden_size * 2)` if LSTM is bidirection; If " "not, output is of shape `(batch_size, hidden_size)`." msgstr "" #: of paddlenlp.seq2vec.encoder.RNNEncoder:1 msgid "" "A RNNEncoder takes as input a sequence of vectors and returns a single " "vector, which is a combination of multiple `paddle.nn.RNN " "`__ subclass. The input to this encoder " "is of shape `(batch_size, num_tokens, input_size)`, The output is of " "shape `(batch_size, hidden_size * 2)` if RNN is bidirection; If not, " "output is of shape `(batch_size, hidden_size)`." msgstr "" #: of paddlenlp.seq2vec.encoder.RNNEncoder:9 msgid "" "Paddle's RNN have two outputs: the hidden state for every time step at " "last layer, and the hidden state at the last time step for every layer. " "If `pooling_type` is not None, we perform the pooling on the hidden state" " of every time step at last layer to create a single vector. If None, we " "use the hidden state of the last time step at last layer as a single " "output (shape of `(batch_size, hidden_size)`); And if direction is " "bidirection, the we concat the hidden state of the last forward rnn and " "backward rnn layer to create a single vector (shape of `(batch_size, " "hidden_size * 2)`)." msgstr "" #: of paddlenlp.seq2vec.encoder.RNNEncoder:21 msgid "" "Number of recurrent layers. E.g., setting num_layers=2 would mean " "stacking two RNNs together to form a stacked RNN, with the second RNN " "taking in outputs of the first RNN and computing the final results. " "Defaults to 1." msgstr "" #: of paddlenlp.seq2vec.encoder.RNNEncoder:26 msgid "" "The direction of the network. It can be \"forward\" and \"bidirect\" (it " "means bidirection network). If \"biderect\", it is a birectional RNN, and" " returns the concat output from both directions. Defaults to \"forward\"" msgstr "" #: of paddlenlp.seq2vec.encoder.RNNEncoder:30 msgid "" "If non-zero, introduces a Dropout layer on the outputs of each RNN layer " "except the last layer, with dropout probability equal to dropout. " "Defaults to 0.0." msgstr "" #: of paddlenlp.seq2vec.encoder.RNNEncoder:34 msgid "" "If `pooling_type` is None, then the RNNEncoder will return the hidden " "state of the last time step at last layer as a single vector. If " "pooling_type is not None, it must be one of \"sum\", \"max\" and " "\"mean\". Then it will be pooled on the RNN output (the hidden state of " "every time step at last layer) to create a single vector. Defaults to " "`None`." msgstr "" #: of paddlenlp.seq2vec.encoder.RNNEncoder.get_input_dim:1 msgid "" "Returns the dimension of the vector input for each element in the " "sequence input to a `RNNEncoder`. This is not the shape of the input " "tensor, but the last element of that shape." msgstr "" #: of paddlenlp.seq2vec.encoder.RNNEncoder.get_output_dim:1 msgid "" "Returns the dimension of the final vector output by this `RNNEncoder`. " "This is not the shape of the returned tensor, but the last element of " "that shape." msgstr "" #: of paddlenlp.seq2vec.encoder.RNNEncoder.forward:1 msgid "" "RNNEncoder takes the a sequence of vectors and returns a single " "vector, which is a combination of multiple RNN layers. The input to this " "encoder is of shape `(batch_size, num_tokens, input_size)`. The output is" " of shape `(batch_size, hidden_size * 2)` if RNN is bidirection; If not, " "output is of shape `(batch_size, hidden_size)`." msgstr "" #: of paddlenlp.seq2vec.encoder.TCNEncoder:1 msgid "" "A `TCNEncoder` takes as input a sequence of vectors and returns a single " "vector, which is the last one time step in the feature map. The input to " "this encoder is of shape `(batch_size, num_tokens, input_size)`, and the " "output is of shape `(batch_size, num_channels[-1])` with a receptive " "filed:" msgstr "" #: of paddlenlp.seq2vec.encoder.TCNEncoder:7 #: paddlenlp.seq2vec.encoder.TCNEncoder.forward:7 msgid "" "receptive filed = 2 * " "\\sum_{i=0}^{len(num\\_channels)-1}2^i(kernel\\_size-1)." msgstr "" #: of paddlenlp.seq2vec.encoder.TCNEncoder:11 msgid "" "Temporal Convolutional Networks is a simple convolutional architecture. " "It outperforms canonical recurrent networks such as LSTMs in many tasks. " "See https://arxiv.org/pdf/1803.01271.pdf for more details." msgstr "" #: of paddlenlp.seq2vec.encoder.TCNEncoder:16 msgid "The number of channels in different layer." msgstr "" #: of paddlenlp.seq2vec.encoder.TCNEncoder:18 msgid "The kernel size. Defaults to 2." msgstr "" #: of paddlenlp.seq2vec.encoder.TCNEncoder:20 msgid "The dropout probability. Defaults to 0.2." msgstr "" #: of paddlenlp.seq2vec.encoder.TCNEncoder.get_input_dim:1 msgid "" "Returns the dimension of the vector input for each element in the " "sequence input to a `TCNEncoder`. This is not the shape of the input " "tensor, but the last element of that shape." msgstr "" #: of paddlenlp.seq2vec.encoder.TCNEncoder.get_output_dim:1 msgid "" "Returns the dimension of the final vector output by this `TCNEncoder`. " "This is not the shape of the returned tensor, but the last element of " "that shape." msgstr "" #: of paddlenlp.seq2vec.encoder.TCNEncoder.forward:1 msgid "" "TCNEncoder takes as input a sequence of vectors and returns a single " "vector, which is the last one time step in the feature map. The input to " "this encoder is of shape `(batch_size, num_tokens, input_size)`, and the " "output is of shape `(batch_size, num_channels[-1])` with a receptive " "filed:" msgstr "" #: of paddlenlp.seq2vec.encoder.TCNEncoder.forward:11 msgid "The input tensor with shape `[batch_size, num_tokens, input_size]`." msgstr "" #: of paddlenlp.seq2vec.encoder.TCNEncoder.forward:14 msgid "Returns tensor `output` with shape `[batch_size, num_channels[-1]]`." msgstr ""