:mod:`capreolus.reranker.TFVanillaBert` ======================================= .. py:module:: capreolus.reranker.TFVanillaBert Module Contents --------------- Classes ~~~~~~~ .. autoapisummary:: capreolus.reranker.TFVanillaBert.TFVanillaBert_Class capreolus.reranker.TFVanillaBert.TFVanillaBERT .. data:: logger .. py:class:: TFVanillaBert_Class(extractor, config, *args, **kwargs) Bases: :class:`tensorflow.keras.Model` .. method:: call(self, x, **kwargs) During training, both posdoc and negdoc are passed During eval, both posdoc and negdoc are passed but negdoc would be a zero tensor Whether negdoc is a legit doc tensor or a dummy zero tensor is determined by which sampler is used (eg: sampler.TrainDataset) as well as the extractor (eg: EmbedText) .. py:class:: TFVanillaBERT Bases: :class:`capreolus.reranker.Reranker` .. attribute:: module_name :annotation: = TFVanillaBERT .. attribute:: dependencies .. attribute:: config_spec .. method:: build_model(self)