model.py 文件源码

def __call__(self, X, return_last=False):
        batchsize = X.shape[0]
        seq_length = X.shape[1]
        enmbedding = self.embed(X)
        enmbedding = F.swapaxes(enmbedding, 1, 2)
        residual_input = enmbedding if self.ndim_h == self.ndim_embedding else 0

        out_data = self._forward_layer(0, enmbedding)
        for layer_index in xrange(1, self.num_blocks * self.num_layers_per_block):
            out_data = self._forward_layer(layer_index, out_data)
            if (layer_index + 1) % self.num_layers_per_block == 0:
                if self.using_dropout:
                    out_data = F.dropout(out_data, ratio=self.dropout)
                out_data += residual_input
                residual_input = out_data

        if return_last:
            out_data = out_data[:, :, -1, None]

        out_data = self.dense(out_data)
        out_data = F.reshape(F.swapaxes(out_data, 1, 2), (-1, self.vocab_size))

        return out_data