vocab.py 文件源码

def set_vectors(self, stoi, vectors, dim, unk_init=torch.Tensor.zero_):
        """
        Set the vectors for the Vocab instance from a collection of Tensors.

        Arguments:
            stoi: A dictionary of string to the index of the associated vector
                in the `vectors` input argument.
            vectors: An indexed iterable (or other structure supporting __getitem__) that
                given an input index, returns a FloatTensor representing the vector
                for the token associated with the index. For example,
                vector[stoi["string"]] should return the vector for "string".
            dim: The dimensionality of the vectors.
            unk_init (callback): by default, initialize out-of-vocabulary word vectors
                to zero vectors; can be any function that takes in a Tensor and
                returns a Tensor of the same size. Default: torch.Tensor.zero_
        """
        self.vectors = torch.Tensor(len(self), dim)
        for i, token in enumerate(self.itos):
            wv_index = stoi.get(token, None)
            if wv_index is not None:
                self.vectors[i] = vectors[wv_index]
            else:
                self.vectors[i] = unk_init(self.vectors[i])