2VhddlmZddlmZddlmZddlmZddlmZddlmZddl m Z dZ ed Gd d eZ ed Gd deZ edGdde Zy))backend) initializers)losses)ops) keras_export)Metric)serialization_libc |xstj}tj|}tj||}|tj ||}|#t jj|||d}t jj||\}}t|j}t|j}||kDr||tt||}tj|tj|}||z}|dkDr||ttd|}t|j}|dkDr||ttd|}||fS)Ndtypesumr reduction)axis)rfloatxget_keras_maskrcastconvert_to_tensorrloss apply_masksqueeze_or_expand_to_same_ranklenshapelistrange broadcast_to)values sample_weight reduce_fnr mask weight_ndim values_ndims S/home/dcms/DCMS/lib/python3.12/site-packages/keras/src/metrics/reduction_metrics.pyreduce_to_samplewise_valuesr% sY  %W^^%E  ! !& )D XXfE *F --m5I  "KK22t5E3M!' J J M!  ---. &,,'  $T% ["ABF (( &8IJ -' ?%Dq+)>$?Mfll#KQ6U1k-B(CD =  zkeras.metrics.Sumc8eZdZdZdfd ZddZdZdZxZS)SumaCompute the (weighted) sum of the given values. For example, if `values` is `[1, 3, 5, 7]` then their sum is 16. If `sample_weight` was specified as `[1, 1, 0, 0]` then the sum would be 4. This metric creates one variable, `total`. This is ultimately returned as the sum value. Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Example: >>> m = metrics.Sum() >>> m.update_state([1, 3, 5, 7]) >>> m.result() 16.0 >>> m = metrics.Sum() >>> m.update_state([1, 3, 5, 7], sample_weight=[1, 1, 0, 0]) >>> m.result() 4.0 ct||||jdtj|j d|_y)Nnamer totalr initializerr r+)super__init__ add_variablerZerosr r-selfr+r __class__s r$r1z Sum.__init__JsE d%0&&$**,** '  r&ct||tj|j\}}|jj tj|y)Nr r )r%rr r r- assign_add)r5rr_s r$ update_statezSum.update_stateSs=/ MSWWDJJ  cggfo.r&c:|jjdyNr)r-assignr5s r$ reset_statezSum.reset_stateYs !r&cVtj|j|jSN)rrr-r r?s r$resultz Sum.result\sxx DJJ//r&)r NrB __name__ __module__ __qualname____doc__r1r;r@rC __classcell__r6s@r$r(r(/s2 / 0r&r(zkeras.metrics.Meanc8eZdZdZdfd ZddZdZdZxZS)MeanaCompute the (weighted) mean of the given values. For example, if values is `[1, 3, 5, 7]` then the mean is 4. If `sample_weight` was specified as `[1, 1, 0, 0]` then the mean would be 2. This metric creates two variables, `total` and `count`. The mean value returned is simply `total` divided by `count`. Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Example: >>> m = Mean() >>> m.update_state([1, 3, 5, 7]) >>> m.result() 4.0 >>> m.reset_state() >>> m.update_state([1, 3, 5, 7], sample_weight=[1, 1, 0, 0]) >>> m.result() 2.0 ct||||jdtj|j d|_|jdtj|j d|_y)Nr*r,r-r.count)r0r1r2rr3r r-rNr4s r$r1z Mean.__init__{sw d%0&&$**,** '  &&$**,** '  r&ct||tj|j\}}|jj tj ||tj |}n3t|jdk\rtj|d}nd}|jj tj||jy)Nr8rrr ) r%rmeanr r-r9r rrrNr)r5rr num_sampless r$r;zMean.update_states ; MSXXTZZ!   cggfo.  $''-0K  ! #))F+A.KK chh{$**EFr&cp|jjd|jjdyr=)r-r>rNr?s r$r@zMean.reset_states& ! !r&ctj|jtj|j|j S)Nr )r divide_no_nanr-rrNr r?s r$rCz Mean.results1  JJ4::>  r&)rPNrBrDrJs@r$rLrL`s2   G r&rLzkeras.metrics.MeanMetricWrappercJeZdZdZdfd Zdfd ZfdZedZxZ S)MeanMetricWrapperaWrap a stateless metric function with the `Mean` metric. You could use this class to quickly build a mean metric from a function. The function needs to have the signature `fn(y_true, y_pred)` and return a per-sample loss array. `MeanMetricWrapper.result()` will return the average metric value across all samples seen so far. For example: ```python def mse(y_true, y_pred): return (y_true - y_pred) ** 2 mse_metric = MeanMetricWrapper(fn=mse) ``` Args: fn: The metric function to wrap, with signature `fn(y_true, y_pred, **kwargs)`. name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. **kwargs: Keyword arguments to pass on to `fn`. c t|||||_||_|jtj vs>tOP(+(((r&cDd|vrtj|}|di|S)Nr^r,)r deserialize_keras_object)clsrhs r$ from_configzMeanMetricWrapper.from_configs% 6>&??GF}V}r&)NNrB) rErFrGrHr1r;rd classmethodrlrIrJs@r$rVrVs,0 %I) r&rVN) keras.srcrrrrkeras.src.api_exportrkeras.src.metrics.metricrkeras.src.savingr r%r(rLrVr,r&r$rrs"-+."!J!"-0&-0#-0`"#= 6= $= @/0::1:r&