o ?e;@sdZddlmZddlmZddlmZddlmZddlm Z ddl m Z ddl m Z dd l m Z dd lmZGd d d eZ dddZdddZddZddZejfddZd ejd fddZddZddZd S) z$Utilities related to loss functions.)distribute_lib)ops)tensor_conversion)backend) keras_tensor) array_opscond)math_ops) ragged_tensorc@s8eZdZdZdZdZdZdZeddZ edd Z d S) ReductionV2aiTypes of loss reduction. Contains the following values: * `AUTO`: Indicates that the reduction option will be determined by the usage context. For almost all cases this defaults to `SUM_OVER_BATCH_SIZE`. When used with `tf.distribute.Strategy`, outside of built-in training loops such as `tf.keras` `compile` and `fit`, we expect reduction value to be `SUM` or `NONE`. Using `AUTO` in that case will raise an error. * `NONE`: No **additional** reduction is applied to the output of the wrapped loss function. When non-scalar losses are returned to Keras functions like `fit`/`evaluate`, the unreduced vector loss is passed to the optimizer but the reported loss will be a scalar value. Caution: **Verify the shape of the outputs when using** `Reduction.NONE`. The builtin loss functions wrapped by the loss classes reduce one dimension (`axis=-1`, or `axis` if specified by loss function). `Reduction.NONE` just means that no **additional** reduction is applied by the class wrapper. For categorical losses with an example input shape of `[batch, W, H, n_classes]` the `n_classes` dimension is reduced. For pointwise losses your must include a dummy axis so that `[batch, W, H, 1]` is reduced to `[batch, W, H]`. Without the dummy axis `[batch, W, H]` will be incorrectly reduced to `[batch, W]`. * `SUM`: Scalar sum of weighted losses. * `SUM_OVER_BATCH_SIZE`: Scalar `SUM` divided by number of elements in losses. This reduction type is not supported when used with `tf.distribute.Strategy` outside of built-in training loops like `tf.keras` `compile`/`fit`. You can implement 'SUM_OVER_BATCH_SIZE' using global batch size like: ``` with strategy.scope(): loss_obj = tf.keras.losses.CategoricalCrossentropy( reduction=tf.keras.losses.Reduction.NONE) .... loss = tf.reduce_sum(loss_obj(labels, predictions)) * (1. / global_batch_size) ``` Please see the [custom training guide]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details on this. autononesumZsum_over_batch_sizecCs|j|j|j|jfSN)AUTONONESUMSUM_OVER_BATCH_SIZE)clsrk/home/www/facesmatcher.com/pyenv/lib/python3.10/site-packages/tensorflow/python/keras/utils/losses_utils.pyallPszReductionV2.allcCs||vr td|dS)NzInvalid Reduction Key %s.)r ValueError)rkeyrrrvalidateTs  zReductionV2.validateN) __name__ __module__ __qualname____doc__rrrr classmethodrrrrrrr s- r Nc st|pdttjstttjstj}|j}j}|j}|durl|durl||}||dkrL|j d drLt dgn||dkra|j d drat dgfWdSt t }|dus|j d drtt|d|fddfdd|dus|j d drtt|d|fddfd dfWdS1swYdS) a$Squeeze last dim if ranks differ from expected by exactly 1. In the common case where we expect shapes to match, `expected_rank_diff` defaults to 0, and we squeeze the last dimension of the larger rank if they differ by 1. But, for example, if `labels` contains class IDs and `predictions` contains 1 probability per class, we expect `predictions` to have 1 more dimension than `labels`, so `expected_rank_diff` would be 1. In this case, we'd squeeze `labels` if `rank(predictions) - rank(labels) == 0`, and `predictions` if `rank(predictions) - rank(labels) == 2`. This will use static shape if available. Otherwise, it will add graph operations, which could result in a performance hit. Args: labels: Label values, a `Tensor` whose dimensions match `predictions`. predictions: Predicted values, a `Tensor` of arbitrary dimensions. expected_rank_diff: Expected result of `rank(predictions) - rank(labels)`. name: Name of the op. Returns: Tuple of `labels` and `predictions`, possibly with last dim squeezed. remove_squeezable_dimensionsNctdgSNr#rsqueezer predictionsrrz.remove_squeezable_dimensions..cSrrrr(rrr*cr$r%r&rlabelsrrr*r+cr,rrrr.rrr*r-)r name_scope isinstancer RaggedTensorr"convert_to_tensor_v2_with_dispatchshapendimsdimsZis_compatible_withrr'rankr r equal) r/r)Zexpected_rank_diffnameZpredictions_shapeZpredictions_rankZ labels_shapeZ labels_rank rank_diffr)r/r)rr!ZsT         $r!c sj}|j}dur^j}|j}|dur,|dur,||dks$|ddkr+t\n2ttfddtdtdfdd}ttd|\durffSj}|j} | dkrufS|dur| dur| |dkrtdgn || dkrt dgfSt} | tfddfd d fd d } tt| dfd d| fS)aSqueeze or expand last dimension if needed. 1. Squeezes last dim of `y_pred` or `y_true` if their rank differs by 1 (using `remove_squeezable_dimensions`). 2. Squeezes or expands last dim of `sample_weight` if its rank differs by 1 from the new rank of `y_pred`. If `sample_weight` is scalar, it is kept scalar. This will use static shape if available. Otherwise, it will add graph operations, which could result in a performance hit. Args: y_pred: Predicted values, a `Tensor` of arbitrary dimensions. y_true: Optional label `Tensor` whose dimensions match `y_pred`. sample_weight: Optional weight scalar or `Tensor` whose dimensions match `y_pred`. Returns: Tuple of `y_pred`, `y_true` and `sample_weight`. Each of them possibly has the last dimension squeezed, `sample_weight` could be extended by one dimension. If `sample_weight` is None, (y_pred, y_true) is returned. Nr"r#cs tSr)r!ry_predy_truerrr*sz.squeeze_or_expand_dimensions..cstfddS)NcsfSrrrr;rrr*sz@squeeze_or_expand_dimensions....rr) is_last_dim_1 squeeze_dimsr<r=rrr*srcr$r%r&r sample_weightrrr*r+cs*fdd}ttd|fddS)Ncr$r%)r expand_dimsrr@rrr*r+zMsqueeze_or_expand_dimensions.._maybe_expand_weights..r#cr,rrrr@rrr*r-r r r8)Zexpand_weights)r:rArr_maybe_expand_weightss z;squeeze_or_expand_dimensions.._maybe_expand_weightscsttdS)Nr"rCr)rDmaybe_squeeze_weightsr:rr_maybe_adjust_weightss z;squeeze_or_expand_dimensions.._maybe_adjust_weightscr,rrrr@rrr*r-) r4r5r!rr7r r8r r'rB) r<r=rAZ y_pred_shapeZ y_pred_rankZ y_true_shapeZ y_true_rankZmaybe_squeeze_dimsZ weights_shapeZ weights_rankZweights_rank_tensorrFr)rDr>rEr:rAr?r<r=rsqueeze_or_expand_dimensionssP       rGcCst|}tj||ddS)a,Computes a safe mean of the losses. Args: losses: `Tensor` whose elements contain individual loss measurements. num_present: The number of measurable elements in `losses`. Returns: A scalar representing the mean of `losses`. If `num_present` is zero, then zero is returned. valuer9)r reduce_sumZ div_no_nan)lossesZ num_presentZ total_lossrrr _safe_means rLcCsHtd}tjtj||d|jdWdS1swYdS)z3Computes the number of elements in `losses` tensor.Z num_elementsrI)dtypeN)rr0r castrsizerM)rKscoperrr _num_elementss $rQcCs8|tjkr |}|St|}|tjkrt|t|}|S)z2Reduces the individual weighted loss measurements.)r rr rJrrLrQ)weighted_losses reductionlossrrrreduce_weighted_loss s  rUcCst||tjkr tj}|durd}t|pdQ|t_t |t j t j fs.t|}|j}t |t j sqsz/cast_losses_to_common_dtype..)rMZ is_floatingrOZ is_complex)rKrTrr]rcast_losses_to_common_dtypeZs r_)rN)NN)rZtensorflow.python.distributerZtensorflow.python.frameworkrrZtensorflow.python.kerasrZtensorflow.python.keras.enginerZtensorflow.python.opsrr r Ztensorflow.python.ops.raggedr objectr r!rGrLrQrrUrZr[r_rrrrs0         > AY   <