6bijDSrSSKJs Jr SSKJr SSKJr SSK J r SSK J r SSKJr \"S5"S S \ R 55r\"S 5"S S \ R 55r\"S5"SS\ R 55r\"S5"SS\ R 55rSr\\R,l\"S5"SS\ R 55r\"S5"SS\ R 55r\\R,lSr\"S5\R4R6R8S&Sj55r\"S5\R4R6R8S55r\"S 5\R4R6R8S!55r\"S"5\R4R6R8S'S#j55r \"S$5\R4R6R8S'S%j55r!g)(zAccuracy metrics.N)backend)utils) base_metric) metrics_utils) keras_exportzkeras.metrics.AccuracycN^\rSrSrSr\R SU4Sjj5rSrU=r $)AccuracyaCalculates how often predictions equal labels. This metric creates two local variables, `total` and `count` that are used to compute the frequency with which `y_pred` matches `y_true`. This frequency is ultimately returned as `binary accuracy`: an idempotent operation that simply divides `total` by `count`. If `sample_weight` is `None`, weights default to 1. Use `sample_weight` of 0 to mask values. Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Standalone usage: >>> m = tf.keras.metrics.Accuracy() >>> m.update_state([[1], [2], [3], [4]], [[0], [2], [3], [4]]) >>> m.result().numpy() 0.75 >>> m.reset_state() >>> m.update_state([[1], [2], [3], [4]], [[0], [2], [3], [4]], ... sample_weight=[1, 1, 0, 0]) >>> m.result().numpy() 0.5 Usage with `compile()` API: ```python model.compile(optimizer='sgd', loss='mse', metrics=[tf.keras.metrics.Accuracy()]) ``` c*>[TU][XS9 gNdtype)super__init__accuracyselfnamer __class__s _/home/james-whalen/.local/lib/python3.13/site-packages/tf_keras/src/metrics/accuracy_metrics.pyrAccuracy.__init__Bs 45)rN __name__ __module__ __qualname____firstlineno____doc__ dtensor_utils inject_meshr__static_attributes__ __classcell__rs@rr r s#"H66rr zkeras.metrics.BinaryAccuracycN^\rSrSrSr\R SU4Sjj5rSrU=r $)BinaryAccuracyGa\Calculates how often predictions match binary labels. This metric creates two local variables, `total` and `count` that are used to compute the frequency with which `y_pred` matches `y_true`. This frequency is ultimately returned as `binary accuracy`: an idempotent operation that simply divides `total` by `count`. If `sample_weight` is `None`, weights default to 1. Use `sample_weight` of 0 to mask values. Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. threshold: (Optional) Float representing the threshold for deciding whether prediction values are 1 or 0. Standalone usage: >>> m = tf.keras.metrics.BinaryAccuracy() >>> m.update_state([[1], [1], [0], [0]], [[0.98], [1], [0], [0.6]]) >>> m.result().numpy() 0.75 >>> m.reset_state() >>> m.update_state([[1], [1], [0], [0]], [[0.98], [1], [0], [0.6]], ... sample_weight=[1, 0, 0, 1]) >>> m.result().numpy() 0.5 Usage with `compile()` API: ```python model.compile(optimizer='sgd', loss='mse', metrics=[tf.keras.metrics.BinaryAccuracy()]) ``` c@>[TU][RXUS9 g)N)r threshold)rrrbinary_matches)rrrr)rs rrBinaryAccuracy.__init__os"   ( ($y  rr)binary_accuracyN?rr$s@rr&r&Gs#$L  rr&z!keras.metrics.CategoricalAccuracycN^\rSrSrSr\R SU4Sjj5rSrU=r $)CategoricalAccuracyva%Calculates how often predictions match one-hot labels. You can provide logits of classes as `y_pred`, since argmax of logits and probabilities are same. This metric creates two local variables, `total` and `count` that are used to compute the frequency with which `y_pred` matches `y_true`. This frequency is ultimately returned as `categorical accuracy`: an idempotent operation that simply divides `total` by `count`. `y_pred` and `y_true` should be passed in as vectors of probabilities, rather than as labels. If necessary, use `tf.one_hot` to expand `y_true` as a vector. If `sample_weight` is `None`, weights default to 1. Use `sample_weight` of 0 to mask values. Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Standalone usage: >>> m = tf.keras.metrics.CategoricalAccuracy() >>> m.update_state([[0, 0, 1], [0, 1, 0]], [[0.1, 0.9, 0.8], ... [0.05, 0.95, 0]]) >>> m.result().numpy() 0.5 >>> m.reset_state() >>> m.update_state([[0, 0, 1], [0, 1, 0]], [[0.1, 0.9, 0.8], ... [0.05, 0.95, 0]], ... sample_weight=[0.7, 0.3]) >>> m.result().numpy() 0.3 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[tf.keras.metrics.CategoricalAccuracy()]) ``` c&>[TU]SUUS9 g)Nch[R"[RR USS9U5$Naxisrsparse_categorical_matchestfmathargmaxy_truey_preds r.CategoricalAccuracy.__init__..s%=#K#KvB/$rr rrrs rrCategoricalAccuracy.__init__s"     rr)categorical_accuracyNrr$s@rr/r/vs#,\  rr/z'keras.metrics.SparseCategoricalAccuracycN^\rSrSrSr\R SU4Sjj5rSrU=r $)SparseCategoricalAccuracyaCalculates how often predictions match integer labels. ```python acc = np.dot(sample_weight, np.equal(y_true, np.argmax(y_pred, axis=1)) ``` You can provide logits of classes as `y_pred`, since argmax of logits and probabilities are same. This metric creates two local variables, `total` and `count` that are used to compute the frequency with which `y_pred` matches `y_true`. This frequency is ultimately returned as `sparse categorical accuracy`: an idempotent operation that simply divides `total` by `count`. If `sample_weight` is `None`, weights default to 1. Use `sample_weight` of 0 to mask values. Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Standalone usage: >>> m = tf.keras.metrics.SparseCategoricalAccuracy() >>> m.update_state([[2], [1]], [[0.1, 0.6, 0.3], [0.05, 0.95, 0]]) >>> m.result().numpy() 0.5 >>> m.reset_state() >>> m.update_state([[2], [1]], [[0.1, 0.6, 0.3], [0.05, 0.95, 0]], ... sample_weight=[0.7, 0.3]) >>> m.result().numpy() 0.3 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[tf.keras.metrics.SparseCategoricalAccuracy()]) ``` c>>[TU][RXS9 gr )rrrr8rs rr"SparseCategoricalAccuracy.__init__s    4 4d  rr)sparse_categorical_accuracyNrr$s@rrErEs#*X  rrEaAccumulates metric statistics. For sparse categorical metrics, the shapes of `y_true` and `y_pred` are different. Args: y_true: Ground truth label values. shape = `[batch_size, d0, .. dN-1]` or shape = `[batch_size, d0, .. dN-1, 1]`. y_pred: The predicted probability values. shape = `[batch_size, d0, .. dN]`. sample_weight: Optional `sample_weight` acts as a coefficient for the metric. If a scalar is provided, then the metric is simply scaled by the given value. If `sample_weight` is a tensor of size `[batch_size]`, then the metric for each sample of the batch is rescaled by the corresponding element in the `sample_weight` vector. If the shape of `sample_weight` is `[batch_size, d0, .. dN-1]` (or can be broadcasted to this shape), then each metric element of `y_pred` is scaled by the corresponding value of `sample_weight`. (Note on `dN-1`: all metric functions reduce by 1 dimension, usually the last axis (-1)). Returns: Update op. z%keras.metrics.TopKCategoricalAccuracycN^\rSrSrSr\R SU4Sjj5rSrU=r $)TopKCategoricalAccuracyia;Computes how often targets are in the top `K` predictions. Args: k: (Optional) Number of top elements to look at for computing accuracy. Defaults to `5`. name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Standalone usage: >>> m = tf.keras.metrics.TopKCategoricalAccuracy(k=1) >>> m.update_state([[0, 0, 1], [0, 1, 0]], ... [[0.1, 0.9, 0.8], [0.05, 0.95, 0]]) >>> m.result().numpy() 0.5 >>> m.reset_state() >>> m.update_state([[0, 0, 1], [0, 1, 0]], ... [[0.1, 0.9, 0.8], [0.05, 0.95, 0]], ... sample_weight=[0.7, 0.3]) >>> m.result().numpy() 0.3 Usage with `compile()` API: ```python model.compile(optimizer='sgd', loss='mse', metrics=[tf.keras.metrics.TopKCategoricalAccuracy()]) ``` c(>[TU]SUUUS9 g)Nch[R"[RR USS9X5$r3r sparse_top_k_categorical_matchesr9r:r;)ytypks rr?2TopKCategoricalAccuracy.__init__..'s%mLLr+RrrrRrArrRrrrs rr TopKCategoricalAccuracy.__init__$s%     rr)top_k_categorical_accuracyNrr$s@rrKrKs#@  rrKz+keras.metrics.SparseTopKCategoricalAccuracycP^\rSrSrSr\R SU4Sjj5rSrU=r $)SparseTopKCategoricalAccuracyi0aComputes how often integer targets are in the top `K` predictions. Args: k: (Optional) Number of top elements to look at for computing accuracy. Defaults to `5`. name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Standalone usage: >>> m = tf.keras.metrics.SparseTopKCategoricalAccuracy(k=1) >>> m.update_state([2, 1], [[0.1, 0.9, 0.8], [0.05, 0.95, 0]]) >>> m.result().numpy() 0.5 >>> m.reset_state() >>> m.update_state([2, 1], [[0.1, 0.9, 0.8], [0.05, 0.95, 0]], ... sample_weight=[0.7, 0.3]) >>> m.result().numpy() 0.3 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[tf.keras.metrics.SparseTopKCategoricalAccuracy()]) ``` cB>[TU][RUUUS9 g)NrT)rrrrOrUs rr&SparseTopKCategoricalAccuracy.__init__Qs)   : :   rr)rW!sparse_top_k_categorical_accuracyNrr$s@rrZrZ0s%>CG  rrZcv[R"X/5uunnnURRUR5 URUR:wa [ R "XR5n[ R "[ R"X5[R"55$)N) r,ragged_assert_compatible_and_get_flat_valuesshapeassert_is_compatible_withrr9castequalrfloatx)r=r>_s rrrbs  E E    LL**6<<8 ||v||#. 77288F+W^^-= >>rzkeras.metrics.binary_accuracycV[R"[R"XU5SS9$)aZCalculates how often predictions match binary labels. Standalone usage: >>> y_true = [[1], [1], [0], [0]] >>> y_pred = [[1], [1], [0], [0]] >>> m = tf.keras.metrics.binary_accuracy(y_true, y_pred) >>> assert m.shape == (4,) >>> m.numpy() array([1., 1., 1., 1.], dtype=float32) Args: y_true: Ground truth values. shape = `[batch_size, d0, .. dN]`. y_pred: The predicted values. shape = `[batch_size, d0, .. dN]`. threshold: (Optional) Float representing the threshold for deciding whether prediction values are 1 or 0. Returns: Binary accuracy values. shape = `[batch_size, d0, .. dN-1]` r4r5)r9 reduce_meanrr*)r=r>r)s rr,r,os'6 >>$$VY?b rz"keras.metrics.categorical_accuracych[R"[RR USS9U5$)aCalculates how often predictions match one-hot labels. Standalone usage: >>> y_true = [[0, 0, 1], [0, 1, 0]] >>> y_pred = [[0.1, 0.9, 0.8], [0.05, 0.95, 0]] >>> m = tf.keras.metrics.categorical_accuracy(y_true, y_pred) >>> assert m.shape == (2,) >>> m.numpy() array([0., 1.], dtype=float32) You can provide logits of classes as `y_pred`, since argmax of logits and probabilities are same. Args: y_true: One-hot ground truth values. y_pred: The prediction values. Returns: Categorical accuracy values. r4r5r7r<s rrCrCs-6  3 3 vB' rz)keras.metrics.sparse_categorical_accuracyc[R"X5nURRS:a+URSS:Xa[R "US/5nU$)aCalculates how often predictions match integer labels. Standalone usage: >>> y_true = [2, 1] >>> y_pred = [[0.1, 0.9, 0.8], [0.05, 0.95, 0]] >>> m = tf.keras.metrics.sparse_categorical_accuracy(y_true, y_pred) >>> assert m.shape == (2,) >>> m.numpy() array([0., 1.], dtype=float32) You can provide logits of classes as `y_pred`, since argmax of logits and probabilities are same. Args: y_true: Integer ground truth values. y_pred: The prediction values. Returns: Sparse categorical accuracy values. r4)rr8r`ndimsr9squeeze)r=r>matchess rrIrIsO866vFG}}Q7==#4#9**Wrd+ Nrz(keras.metrics.top_k_categorical_accuracych[R"[RR USS9X5$)a Computes how often targets are in the top `K` predictions. Standalone usage: >>> y_true = [[0, 0, 1], [0, 1, 0]] >>> y_pred = [[0.1, 0.9, 0.8], [0.05, 0.95, 0]] >>> m = tf.keras.metrics.top_k_categorical_accuracy(y_true, y_pred, k=3) >>> assert m.shape == (2,) >>> m.numpy() array([1., 1.], dtype=float32) Args: y_true: The ground truth values. y_pred: The prediction values. k: (Optional) Number of top elements to look at for computing accuracy. Defaults to `5`. Returns: Top K categorical accuracy value. r4r5rNr=r>rRs rrXrXs-4  9 9 vB' rz/keras.metrics.sparse_top_k_categorical_accuracyc0[R"XU5$)aComputes how often integer targets are in the top `K` predictions. Standalone usage: >>> y_true = [2, 1] >>> y_pred = [[0.1, 0.9, 0.8], [0.05, 0.95, 0]] >>> m = tf.keras.metrics.sparse_top_k_categorical_accuracy( ... y_true, y_pred, k=3) >>> assert m.shape == (2,) >>> m.numpy() array([1., 1.], dtype=float32) Args: y_true: tensor of true targets. y_pred: tensor of predicted targets. k: (Optional) Number of top elements to look at for computing accuracy. Defaults to `5`. Returns: Sparse top K categorical accuracy value. )rrOros rr]r]s8  9 9&! LLr)r-)rW)"rtensorflow.compat.v2compatv2r9 tf_keras.srcrtf_keras.src.dtensorrr tf_keras.src.metricsrtf_keras.src.utilsr tensorflow.python.util.tf_exportrMeanMetricWrapperr r&r/rE*_SPARSE_CATEGORICAL_UPDATE_STATE_DOCSTRING update_staterKrZr __internal__dispatchadd_dispatch_supportr,rCrIrXr]rrrrsB!! 7,,:&''6{,,'6('6T,-+ [22+ .+ \127 +777 37 t781 = =1 91 h.*0/&&. 56* k;;* 7* Z;<) K$A$A) =) Z/**2 ?-...//<23../4<9:.. /; F89../::?@..M/AMr