o  ¢i·ã@súddlmZmZmZddlmZmZmZmZm Z m Z ddl m Z ddl mZddlmZddlmZddlmZd d lmZd d lmZ d"d eeeee fdeddededededeedefdd„Zdd„Zdd„Zdd„Zdd„Zd d!„Z d S)#é)ÚListÚOptionalÚcast)ÚLinearÚModelÚchainÚ list2arrayÚuse_opsÚ zero_init)ÚFloats2dé)ÚLiteral)ÚErrors)ÚDoc)Úregistryé©ÚPrecomputableAffine)ÚTransitionModelNÚtok2vecÚ state_type)ÚparserÚnerÚextra_state_tokensÚ hidden_widthÚ maxout_piecesÚ use_upperÚnOÚreturnc CsÞ|dkr |rdnd}n|dkr|rdnd}n ttjj|dƒ‚| d¡r)| d¡nd }t|tƒt||ƒƒ}|  d|¡t |r@|n||| d¡|d } d } |rht d ƒt |d d } Wd ƒn1scwYt || | tƒS) a‘ Build a transition-based parser model. Can apply to NER or dependency-parsing. Transition-based parsing is an approach to structured prediction where the task of predicting the structure is mapped to a series of state transitions. You might find this tutorial helpful as background: https://explosion.ai/blog/parsing-english-in-python The neural network state prediction model consists of either two or three subnetworks: * tok2vec: Map each token into a vector representations. This subnetwork is run once for each batch. * lower: Construct a feature-specific vector for each (token, feature) pair. This is also run once for each batch. Constructing the state representation is then simply a matter of summing the component features and applying the non-linearity. * upper (optional): A feed-forward network that predicts scores from the state representation. If not present, the output from the lower model is used as action scores directly. tok2vec (Model[List[Doc], List[Floats2d]]): Subnetwork to map tokens into vector representations. state_type (str): String value denoting the type of parser model: "parser" or "ner" extra_state_tokens (bool): Whether or not to use additional tokens in the context to construct the state vector. Defaults to `False`, which means 3 and 8 for the NER and parser respectively. When set to `True`, this would become 6 feature sets (for the NER) or 13 (for the parser). hidden_width (int): The width of the hidden layer. maxout_pieces (int): How many pieces to use in the state prediction layer. Recommended values are 1, 2 or 3. If 1, the maxout non-linearity is replaced with a ReLu non-linearity if use_upper=True, and no non-linearity if use_upper=False. use_upper (bool): Whether to use an additional hidden layer after the state vector in order to predict the action scores. It is recommended to set this to False for large pretrained models such as transformers, and True for smaller networks. The upper layer is computed on CPU, which becomes a bottleneck on larger GPU-based models, where it's also less necessary. nO (int or None): The number of actions the model will predict between. Usually inferred from data at the beginning of training, or loaded from disk. ré érér )ÚvaluerN©rÚnFÚnIÚnPÚcpu©rr%)Ú ValueErrorrÚE917ÚformatÚhas_dimÚget_dimrrrÚset_dimÚ _define_lowerr Ú _define_upperrÚ resize_output) rrrrrrrÚnr_feature_tokensÚ t2v_widthÚlowerÚupper©r6úJ/home/ubuntu/.local/lib/python3.10/site-packages/spacy/ml/models/parser.pyÚbuild_tb_parser_models04ý  ü þr8cCst||tdS)N)rr%Úinit_W)rr r(r6r6r7r0]sr0cCst||||dS)Nr#rr#r6r6r7r/asr/cCs|jdr t||ƒSt||ƒS)NÚ has_upper)ÚattrsÚ _resize_upperÚ _resize_lower)ÚmodelÚnew_nOr6r6r7r1es   r1c Cs2| d¡}| d¡dur| d|¡|S|| d¡kr|S|}| d¡}tdƒt||d}Wdƒn1s9wY| d¡rŒ|j  ||¡}|j  |¡}|  d¡}|  d¡} | d¡r€| d¡} ||d| …<| |d| …<t | |ƒD] } |j d | ¡qu| d|¡| d|¡||jd <| d|¡|S) Nr5rr%r'r(ÚWÚbÚunseen_classeséÿÿÿÿ)Úget_refr,r.r-Ú maybe_get_dimr r0Ú has_paramÚopsÚalloc2fÚalloc1fÚ get_paramÚranger;ÚaddÚ set_paramÚ_layersÚset_ref) r>r?r5Úsmallerr%ÚlargerÚlarger_WÚlarger_bÚ smaller_WÚ smaller_bÚold_nOÚir6r6r7r<ks6    ÿ            r<cCsz| d¡}| d¡dur| d|¡|S|}| d¡}| d¡}| d¡}t||||d}| d¡r°|j ||||¡}|j ||¡} |j d|||¡} |  d¡} |  d ¡} |  d ¡} | d¡rž|  d¡}| |dd…d |…dd…dd…f<| | dd…dd…d |…dd…f<| | d |…dd…f<t ||ƒD] }|j d   |¡q“| d|¡| d | ¡| d | ¡||jd<| d|¡|S) Nr4rr%r$r&)rr%r$r&r@érAÚpadrrB)rDr,r.rEr/rFrGÚalloc4frHrJr-rKr;rLrMrNrO)r>r?r4rPr%r$r&rQrRrSÚ larger_padrTrUÚ smaller_padrVrWr6r6r7r=s:                  r=)N)!ÚtypingrrrÚ thinc.apirrrrr r Ú thinc.typesr Úcompatr ÚerrorsrÚtokensrÚutilrÚ_precomputable_affinerÚ tb_frameworkrÚboolÚintr8r0r/r1r<r=r6r6r6r7Ús@         ùÿþýüûúù øO "