2Vh)ddlmZddlmZddlmZddlmZddlmZddlmZddlm Z edGd d e jZ ed Gd d e jZ edGdde jZ edGdde jZedGdde jZy)) keras_export)binary_crossentropy)categorical_crossentropy) kl_divergence)poisson)sparse_categorical_crossentropy)reduction_metricszkeras.metrics.KLDivergencec*eZdZdZdfd ZdZxZS) KLDivergenceaComputes Kullback-Leibler divergence metric between `y_true` and `y_pred`. Formula: ```python metric = y_true * log(y_true / y_pred) ``` `y_true` and `y_pred` are expected to be probability distributions, with values between 0 and 1. They will get clipped to the `[0, 1]` range. Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Examples: >>> m = keras.metrics.KLDivergence() >>> m.update_state([[0, 1], [0, 0]], [[0.6, 0.4], [0.4, 0.6]]) >>> m.result() 0.45814306 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[0.6, 0.4], [0.4, 0.6]], ... sample_weight=[1, 0]) >>> m.result() 0.9162892 Usage with `compile()` API: ```python model.compile(optimizer='sgd', loss='mse', metrics=[keras.metrics.KLDivergence()]) ``` c2t|t||yN)fnnamedtype)super__init__rselfrr __class__s W/home/dcms/DCMS/lib/python3.12/site-packages/keras/src/metrics/probabilistic_metrics.pyrzKLDivergence.__init__3s MEBc4|j|jdSNrrrrs r get_configzKLDivergence.get_config6 DJJ77r)rN__name__ __module__ __qualname____doc__rr __classcell__rs@rr r s%NC8rr zkeras.metrics.Poissonc*eZdZdZdfd ZdZxZS)PoissonaComputes the Poisson metric between `y_true` and `y_pred`. Formula: ```python metric = y_pred - y_true * log(y_pred) ``` Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Examples: >>> m = keras.metrics.Poisson() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result() 0.49999997 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]], ... sample_weight=[1, 0]) >>> m.result() 0.99999994 Usage with `compile()` API: ```python model.compile(optimizer='sgd', loss='mse', metrics=[keras.metrics.Poisson()]) ``` c2t|t||yr )rrrrs rrzPoisson.__init__^s G$e 0, label values are smoothed, meaning the confidence on label values are relaxed. e.g. `label_smoothing=0.2` means that we will use a value of 0.1 for label "0" and 0.9 for label "1". Examples: >>> m = keras.metrics.BinaryCrossentropy() >>> m.update_state([[0, 1], [0, 0]], [[0.6, 0.4], [0.4, 0.6]]) >>> m.result() 0.81492424 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[0.6, 0.4], [0.4, 0.6]], ... sample_weight=[1, 0]) >>> m.result() 0.9162905 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[keras.metrics.BinaryCrossentropy()]) ``` c`t|t||||||_||_d|_y)N)r from_logitslabel_smoothingdown)rrrr,r- _direction)rrrr,r-rs rrzBinaryCrossentropy.__init__s?   #+  '. rc`|j|j|j|jdS)Nrrr,r-r1rs rrzBinaryCrossentropy.get_configs,IIZZ++#33   r)rNFrrr$s@rr*r*es!&T# !& rr*z%keras.metrics.CategoricalCrossentropyc4eZdZdZ dfd ZdZxZS)CategoricalCrossentropyaComputes the crossentropy metric between the labels and predictions. This is the crossentropy metric class to be used when there are multiple label classes (2 or more). It assumes that labels are one-hot encoded, e.g., when labels values are `[2, 0, 1]`, then `y_true` is `[[0, 0, 1], [1, 0, 0], [0, 1, 0]]`. Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. from_logits: (Optional) Whether output is expected to be a logits tensor. By default, we consider that output encodes a probability distribution. label_smoothing: (Optional) Float in `[0, 1]`. When > 0, label values are smoothed, meaning the confidence on label values are relaxed. e.g. `label_smoothing=0.2` means that we will use a value of 0.1 for label "0" and 0.9 for label "1". axis: (Optional) Defaults to `-1`. The dimension along which entropy is computed. Examples: >>> # EPSILON = 1e-7, y = y_true, y` = y_pred >>> # y` = clip_ops.clip_by_value(output, EPSILON, 1. - EPSILON) >>> # y` = [[0.05, 0.95, EPSILON], [0.1, 0.8, 0.1]] >>> # xent = -sum(y * log(y'), axis = -1) >>> # = -((log 0.95), (log 0.1)) >>> # = [0.051, 2.302] >>> # Reduced xent = (0.051 + 2.302) / 2 >>> m = keras.metrics.CategoricalCrossentropy() >>> m.update_state([[0, 1, 0], [0, 0, 1]], ... [[0.05, 0.95, 0], [0.1, 0.8, 0.1]]) >>> m.result() 1.1769392 >>> m.reset_state() >>> m.update_state([[0, 1, 0], [0, 0, 1]], ... [[0.05, 0.95, 0], [0.1, 0.8, 0.1]], ... sample_weight=np.array([0.3, 0.7])) >>> m.result() 1.6271976 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[keras.metrics.CategoricalCrossentropy()]) ``` cpt|t|||||||_||_||_d|_y)N)rr,r-axisr.)rrrr,r-r5r/)rrrr,r-r5rs rrz CategoricalCrossentropy.__init__sI  $ #+  '.  rcv|j|j|j|j|jdS)Nrrr,r-r5r7rs rrz"CategoricalCrossentropy.get_configs3IIZZ++#33II   r)rNFrrr$s@rr3r3s$3n(  !, rr3z+keras.metrics.SparseCategoricalCrossentropyc2eZdZdZ dfd ZdZxZS)SparseCategoricalCrossentropyaComputes the crossentropy metric between the labels and predictions. Use this crossentropy metric when there are two or more label classes. It expects labels to be provided as integers. If you want to provide labels that are one-hot encoded, please use the `CategoricalCrossentropy` metric instead. There should be `num_classes` floating point values per feature for `y_pred` and a single floating point value per feature for `y_true`. Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. from_logits: (Optional) Whether output is expected to be a logits tensor. By default, we consider that output encodes a probability distribution. axis: (Optional) Defaults to `-1`. The dimension along which entropy is computed. Examples: >>> # y_true = one_hot(y_true) = [[0, 1, 0], [0, 0, 1]] >>> # logits = log(y_pred) >>> # softmax = exp(logits) / sum(exp(logits), axis=-1) >>> # softmax = [[0.05, 0.95, EPSILON], [0.1, 0.8, 0.1]] >>> # xent = -sum(y * log(softmax), 1) >>> # log(softmax) = [[-2.9957, -0.0513, -16.1181], >>> # [-2.3026, -0.2231, -2.3026]] >>> # y_true * log(softmax) = [[0, -0.0513, 0], [0, 0, -2.3026]] >>> # xent = [0.0513, 2.3026] >>> # Reduced xent = (0.0513 + 2.3026) / 2 >>> m = keras.metrics.SparseCategoricalCrossentropy() >>> m.update_state([1, 2], ... [[0.05, 0.95, 0], [0.1, 0.8, 0.1]]) >>> m.result() 1.1769392 >>> m.reset_state() >>> m.update_state([1, 2], ... [[0.05, 0.95, 0], [0.1, 0.8, 0.1]], ... sample_weight=np.array([0.3, 0.7])) >>> m.result() 1.6271976 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[keras.metrics.SparseCategoricalCrossentropy()]) ``` c`t|t||||||_||_d|_y)Nrrr,r5r.)rrrr,r5r/)rrrr,r5rs rrz&SparseCategoricalCrossentropy.__init__:s>  +#  '  rc`|j|j|j|jdS)Nr<r<rs rrz(SparseCategoricalCrossentropy.get_configMs*IIZZ++II   r)rNFr8rr$s@rr:r:s!4p/  !& rr:N)keras.src.api_exportrkeras.src.losses.lossesrrrrrkeras.src.metricsr MeanMetricWrapperr r&r*r3r:rrrCs-7<1+C/*+,8$66,8,,8^%&'811'8''8T01B *<<B 2B J56S /AAS 7S l;<P $5$G$GP =P r