Initialize and prunes weights if needed.

r""" Instantiates one of the base model classes of the library from a pre-trained model configuration. The model class to instantiate

Prune a linear layer (a model parameters) to keep only entries in index. Return the pruned layer as a new layer with requires_grad=True.

labels_paths: [[],[],[],....] pred_paths: [[],[],[],.....] :param label_paths: :param pred_paths: :ret

Tie or clone module weights depending of weither we are using TorchScript or not

projection

读取数据

Converts a single token, or a sequence of tokens, (str/unicode) in a single integer id (resp. a sequence of ids), using the vocabulary.

Project hidden states to a specific head with a 4D-shape.

Reads a tab separated value file.

Creates a `truncated_normal_initializer` with the given range.

Build a resized Embedding Module from a provided token Embedding Module. Increasing the size will add newly initialized vectors at the en

Converts a string in a sequence of ids (integer), using the tokenizer and vocabulary. Same as doing ``self.convert_tokens_to_ids(sel

Returns a list of the shape of tensor, preferring static dimensions. Args: tensor: A tf.Tensor object to find the shape of. expected_rank:

:param logits: [batch_size, num_steps, num_tags]float32, logits :param lengths: [batch_size]int32, real length of each sequence

Save a model and its configuration file to a directory, so that it can be re-loaded using the `:func:`~transformers.PreTrainedModel.from_

Conv1D layer as defined by Radford et al. for OpenAI GPT (and also used in GPT-2) Basically works like a Linear layer but the weights are

Converts a sequence of ids (integer) in a string, using the tokenizer and vocabulary with options to remove special tokens and clean

Basic Tokenization of a piece of text. Split on "white spaces" only, for sub-word tokenization, see WordPieceTokenizer. Args:

:param seq: :param id2label: :param markup: :return:

See base class.

Save the tokenizer vocabulary and merge files to a directory.

设置整个开发环境的seed :param seed: :param device: :return:

Performs a single optimization step. Arguments: closure (callable, optional): A closure that reevaluates the model

Constructs a `BertConfig` from a json file of parameters.

Prune a Conv1D layer (a model parameters) to keep only entries in index. A Conv1D work as a Linear layer (see e.g. BERT) but the weights are

Tokenizes a piece of text.

Given something that might be a URL (or might be a local path), determine which. If it's a URL, download the file and cache it, and retur

Converts a sequence of [tokens|ids] using the vocab.

Converts a sequence of [tokens|ids] using the vocab.

Perform dropout. Args: input_tensor: float Tensor. dropout_prob: Python float. The probability of dropping out a value (NOT of *keepi

:param sess: session to run the model :param data: list of data :param id_to_tag: index to tag name :return: evalua

Gets final hidden layer of encoder. Returns: float Tensor of shape [batch_size, seq_length, hidden_size] corresponding to the final h

Post-attention processing.

Core relative positional attention operations.

Core relative positional attention operations.

Creates examples for the training and dev sets.

Creates examples for the training and dev sets.

Creates examples for the training and dev sets.

Creates examples for the training and dev sets.

Creates examples for the training and dev sets.

Creates examples for the training and dev sets.

Creates examples for the training and dev sets.

See base class.

Converts `text` to Unicode (if it's not already), assuming utf-8 input.

Create a mapping (item to ID / ID to item) from a dictionary. Items are ordered by decreasing frequency.

Convert a set of `InputExample`s to a TFRecord file.

Creates an `input_fn` closure to be passed to TPUEstimator.

See base class.

Create a schedule with a learning rate that decreases linearly after linearly increasing during a warmup period.

See base class.

See base class.