ó È9i®ãó6•SSKJrJr SSKJr "SS\5rg)é)ÚABCÚabstractmethod)ÚDictcó^•\rSrSrSrSr\S\S\4Sj5r\S5r \S Sj5r S r g ) ÚMetricézÍThe metric base class for computing metrics. The subclasses can either compute a single metric like 'accuracy', or compute the complex metrics for a specific task with or without other Metric subclasses. có•g)N©)ÚselfÚargsÚkwargss ÚW/var/www/html/land-doc-ocr/venv/lib/python3.13/site-packages/modelscope/metrics/base.pyÚ__init__ÚMetric.__init__ s€Ø óÚoutputsÚinputscó•g)aAppend logits and labels within an eval loop. Will be called after every batch finished to gather the model predictions and the labels. Args: outputs: The model prediction outputs. inputs: The mini batch inputs from the dataloader. Returns: None Nr )r rrs rÚaddÚ Metric.adds€ð rcó•g)zšEvaluate the metrics after the eval finished. Will be called after the whole validation finished. Returns: The actual metric dict with standard names. Nr )r s rÚevaluateÚMetric.evaluates€ð rcó•g)zùWhen using data parallel, the data required for different metric calculations are stored in their respective Metric classes, and we need to merge these data to uniformly calculate metric. Args: other: Another Metric instance. Returns: None Nr )r Úothers rÚmergeÚ Metric.merge*s€ð rr N)rr) Ú__name__Ú __module__Ú __qualname__Ú__firstlineno__Ú__doc__rrrrrrÚ__static_attributes__r rrrrsV†ñò  ðð  ˜4ð  ¨ó  óð  ðñ óð ðó  óó  rrN)ÚabcrrÚtypingrrr rrÚr&sðç#Ýô2 ˆSõ2 r