o .wi1@sddlZddlZddlZddlmZmZddlmZddlm Z ddl m Z m Z m Z mZddlmZddlZddlmZddlmZeejd d Zeejd dZd ed edefddZd ed eddfddZ d5d ed ededeeeffddZ  d6ded ed edede edeeeeff ddZ d5d ed ededeeeffddZ d7de de d e!defd!d"Z"eddgd#d$fd%ed&e e#e$e fd'e e#e$e fd(eed)eddf d*d+Z%d,e$d-e&d.e&defd/d0Z'efd1e d2edefd3d4Z(dS)8N)MappingSequence)partial) perf_counter)AnyCallableOptional no_type_check)Mock)Tensor)MetricDOCTEST_DOWNLOAD_TIMEOUTxSKIP_SLOW_DOCTESTpredstargetreturncCs ||ko dkSS)Nr)numelrrrZ/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/utilities/checks.py_check_for_empty_tensors s rcCs*|j|jkrtd|jd|jddS)zHCheck that predictions and target have the same shape, else raise error.zEPredictions and targets are expected to have the same shape, but got z and .N)shape RuntimeErrorrrrr_check_same_shape$s rFallow_non_binary_targetcCs:|j|jkr td|r|stdt|||dS)a9Check ``preds`` and ``target`` tensors are of the same shape and of the correct data type. Args: preds: either tensor with scores/logits target: tensor with ground true labels allow_non_binary_target: whether to allow target to contain non-binary values Raises: ValueError: If ``preds`` and ``target`` don't have the same shape, if they are empty or not of the correct ``dtypes``. Returns: preds: as torch.float32 target: as torch.long if not floating point else torch.float32 z.`preds` and `target` must be of the same shapez=`preds` and `target` must be non-empty and non-scalar tensorsr)r ValueErrorrsize,_check_retrieval_target_and_prediction_typesrrrrrr"_check_retrieval_functional_inputs,s r"indexes ignore_indexcCs|j|jks |j|jkrtd|jtjurtd|dur0||k}||||||}}}|r8|sres1res2atolcsxttr tj|dSttrkSttr'tddtDSttr8tfddDSkS)zFRecursively asserting that two results are within a certain tolerance.)r5css|] \}}t||VqdSN_allclose_recursive).0r1r2rrr sz&_allclose_recursive..c3s"|] }t||VqdSr6r7)r9kr3r4rrr<s ) isinstancer r&allclosestrrallzipr)r3r4r5rr>rr8s    r8) di metric_class init_args input_argsnum_update_to_comparerepsc Cs*|pi}|pi}Gddd|}Gddd|}|di|}|di|}d} zt|dD]} | t|di||di|@} q/Wn tyOd} Ynw|} z|} Wn tyed} Ynw| t| | @} | sutdd Std t||} t||gD]5\}}t|D],\}}t|D]#}t }t|D] } |di|} qt }||| |||f<| qqqt | d }t | d }tt|D]3}td ||d |d|fd|d|fdtd||d |d|fdd|d|fdq|d|dk }td| dd S)aCheck if the new ``full_state_update`` property works as intended. This function checks if the property can safely be set to ``False`` which will for most metrics results in a speedup when using ``forward``. Args: metric_class: metric class object that should be checked init_args: dict containing arguments for initializing the metric class input_args: dict containing arguments to pass to ``forward`` num_update_to_compare: if we successfully detect that the flag is safe to set to ``False`` we will run some speedup test. This arg should be a list of integers for how many steps to compare over. reps: number of repetitions of speedup test Example (states in ``update`` are independent, save to set ``full_state_update=False``) >>> from torchmetrics.classification import MulticlassConfusionMatrix >>> check_forward_full_state_property( # doctest: +SKIP ... MulticlassConfusionMatrix, ... init_args = {'num_classes': 3}, ... input_args = {'preds': torch.randint(3, (100,)), 'target': torch.randint(3, (100,))}, ... ) Full state for 10 steps took: ... Partial state for 10 steps took: ... Full state for 100 steps took: ... Partial state for 100 steps took: ... Full state for 1000 steps took: ... Partial state for 1000 steps took: ... Recommended setting `full_state_update=False` Example (states in ``update`` are dependent meaning that ``full_state_update=True``): >>> from torchmetrics.classification import MulticlassConfusionMatrix >>> class MyMetric(MulticlassConfusionMatrix): ... def update(self, preds, target): ... super().update(preds, target) ... # by construction make future states dependent on prior states ... if self.confmat.sum() > 20: ... self.reset() >>> check_forward_full_state_property( ... MyMetric, ... init_args = {'num_classes': 3}, ... input_args = {'preds': torch.randint(3, (10,)), 'target': torch.randint(3, (10,))}, ... ) Recommended setting `full_state_update=True` c@eZdZdZdS)z4check_forward_full_state_property..FullStateTN__name__ __module__ __qualname__full_state_updaterrrr FullStaterRc@rL)z4check_forward_full_state_property..PartStateFNrMrrrr PartStaterSrTTrFz,Recommended setting `full_state_update=True`NzFull state for z steps took: z+-z0.3fzPartial state for r+)r+rV)rrVz'Recommended setting `full_state_update=`r)ranger8rcomputeprintr&zeroslen enumeraterresetmeanstditem)rGrHrIrJrKrRrT fullstate partstateequal_r3r4resimetricjtrstartendr_r`fasterrrr!check_forward_full_state_propertysX5$       04ro method_nameinstanceparentcCs~t||d}|dur dSt|dr|j}t|tr|j}nt|tr%|j}|dur+dSt||d}|dur9td|j |j kS)zRCheck if a method has been overridden by an instance compared to its parent class.NF __wrapped__z#The parent should define the method) getattrhasattrrsr?r _mock_wrapsrfuncr__code__)rprqrr instance_attr parent_attrrrr is_overriddens      r{fntimeoutcCsrtj|d}td|jd|dtjd||||s$dStd|jd|d tjd| d S) aYCheck if a certain function is taking too long to execute. Function will only be executed if running inside a doctest context. Currently, does not support Windows. Args: fn: function to check timeout: timeout for function Returns: Bool indicating if the function finished within the specified timeout )rzTrying to run `z` for zs...)fileTrWz` did not complete with z%, killing process and returning FalseF) multiprocessingProcessrZrNsysstderrrljoinis_alivekill)r|r}procrrr_try_proceed_with_timeout-s  r)F)FN)r2))rosrcollections.abcrr functoolsrtimertypingrrrr unittest.mockr r&r torchmetrics.metricr r-environget_DOCTEST_DOWNLOAD_TIMEOUTr,_SKIP_SLOW_DOCTESTrrtupler"r*r r1r8dictrAroobjectr{rrrrrs         #  4    i