o ߥi! @sddlZddlmZddlZddlmZmZmZddlmZddl m Z ddl m Z ddl mZddlmZdd lmZmZeZe jejejd e jejejd e jejejd e jejejd e jejejd Gd d d eZdS) N)BCEWithLogitsLossCrossEntropyLossMSELoss)Models)MODELS)&AttentionTextClassificationModelOutput)logger)Tasks)MGeoMGeoPreTrainedModel) module_namecsFeZdZddeffdd Z            d ddZZS) MGeoForSequenceClassification single-modal finetune_modec srt||j|_||_t||jt||dd|jdur!|jn|j}t ||_ t |j |j|_|dS)NT)add_pooling_layer)super__init__ num_labelsconfigsetattrbase_model_prefixr classifier_dropouthidden_dropout_probnnDropoutdropoutLinear hidden_size classifier post_init)selfrrkwargsr __class__j/home/ubuntu/.local/lib/python3.10/site-packages/modelscope/models/multi_modal/mgeo/text_classification.pyr*s    z&MGeoForSequenceClassification.__init__Nc Csz| dur| n|jj} |jj|||||||| | | | dd } | d}||}||}d}|dur|jjdurZ|jdkr@d|j_n|jdkrV|jt j ksQ|jt j krVd|j_nd|j_|jjdkrxt }|jdkrr|| | }n+|||}n%|jjdkrt}||d|j|d}n|jjdkrt}|||}| s|f| d d}|dur|f|S|St||| j| jd S) a< Args: input_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`): Indices of input sequence tokens in the vocabulary. Indices can be obtained using :class:`~modelscope.models.nlp.structbert.SbertTokenizer`. See :meth:`transformers.PreTrainedTokenizer.encode` and :meth:`transformers.PreTrainedTokenizer.__call__` for details. attention_mask (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`): Mask to avoid performing attention on padding token indices. Mask values selected in ``[0, 1]``: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. token_type_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`): Segment token indices to indicate first and second portions of the inputs. Indices are selected in ``[0, 1]``: - 0 corresponds to a `sentence A` token, - 1 corresponds to a `sentence B` token. position_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`): Indices of positions of each input sequence tokens in the position embeddings. Selected in the range ``[0, config.max_position_embeddings - 1]``. head_mask (:obj:`torch.FloatTensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`): Mask to nullify selected heads of the self-attention modules. Mask values selected in ``[0, 1]``: - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. inputs_embeds (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`): Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert :obj:`input_ids` indices into associated vectors than the model's internal embedding lookup matrix. output_attentions (:obj:`bool`, `optional`): Whether or not to return the attentions tensors of all attention layers. See ``attentions`` under returned tensors for more detail. output_hidden_states (:obj:`bool`, `optional`): Whether or not to return the hidden states of all layers. See ``hidden_states`` under returned tensors for more detail. return_dict (:obj:`bool`, `optional`): Whether or not to return a :class:`~transformers.ModelOutput` instead of a plain tuple. labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`): Labels for computing the sequence classification/regression loss. Indices should be in :obj:`[0, ..., config.num_labels - 1]`. If :obj:`config.num_labels == 1` a regression loss is computed (Mean-Square loss), If :obj:`config.num_labels > 1` a classification loss is computed (Cross-Entropy). Returns: Returns `modelscope.outputs.AttentionTextClassificationModelOutput` Examples: >>> from modelscope.models import Model >>> from modelscope.preprocessors import Preprocessor >>> model = Model.from_pretrained('damo/nlp_structbert_sentence-similarity_chinese-base') >>> preprocessor = Preprocessor.from_pretrained('damo/nlp_structbert_sentence-similarity_chinese-base') >>> print(model(**preprocessor(('This is a test', 'This is also a test')))) NT) attention_masktoken_type_ids position_ids head_mask inputs_embedsoutput_attentionsoutput_hidden_states return_dictgis_listgis_tpuse_token_typer regressionsingle_label_classificationmulti_label_classification)losslogits hidden_states attentions)ruse_return_dict base_modelforwardrr problem_typerdtypetorchlongintrsqueezerviewrrr9r:)r! input_idsr'r(r)r*r+labelsr,r-r.r/r0outputs pooled_outputr8r7loss_fctoutputr%r%r&r=:sbJ             z%MGeoForSequenceClassification.forward)r) NNNNNNNNNNNN)__name__ __module__ __qualname__strrr= __classcell__r%r%r#r&r!s r)r@torch.nnrtorch.utils.checkpointrrrmodelscope.metainformodelscope.models.builderrmodelscope.outputsrmodelscope.utilsrloggingmodelscope.utils.constantr backboner r get_loggerregister_moduletext_classificationmgeonlisentiment_classificationsentence_similarityzero_shot_classificationrr%r%r%r&s*