&VfjMddlZddlmZddlmZddlmZddlmZddlm Z ddlm Z ddlm Z dd lm Z dd lm Z dd lmZdd lmZed GddejZedGddejZedGddejZedGddejZedGddejZedGddejZedGd d!ejZed"Gd#d$ejZd'd&ZdS)(N) initializers)ops) keras_export)squeeze_or_expand_to_same_rank)log_cosh)mean_absolute_error)mean_absolute_percentage_error)mean_squared_error)mean_squared_logarithmic_error)reduction_metrics) normalizezkeras.metrics.MeanSquaredErrorc*eZdZdZdfd ZdZxZS)MeanSquaredErroraComputes the mean squared error between `y_true` and `y_pred`. Formula: ```python loss = mean(square(y_true - y_pred)) ``` Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Example: >>> m = keras.metrics.MeanSquaredError() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result() 0.25 r Nchtt||d|_dS)N)fnnamedtypedown)super__init__r _directionselfrr __class__s a/var/www/html/software/conda/lib/python3.11/site-packages/keras/src/metrics/regression_metrics.pyrzMeanSquaredError.__init__&s. .TGGG c |j|jdSNrrrrs r get_configzMeanSquaredError.get_config+ DJ777r)r N__name__ __module__ __qualname____doc__rr! __classcell__rs@rrrsV(!!!!!! 8888888rrzkeras.metrics.MeanAbsoluteErrorc*eZdZdZdfd ZdZxZS)MeanAbsoluteErroraComputes the mean absolute error between the labels and predictions. Formula: ```python loss = mean(abs(y_true - y_pred)) ``` Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Examples: >>> m = keras.metrics.MeanAbsoluteError() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result() 0.25 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]], ... sample_weight=[1, 0]) >>> m.result() 0.5 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[keras.metrics.MeanAbsoluteError()]) ``` rNchtt||d|_dSNrr)rrrrrs rrzMeanAbsoluteError.__init__Ss. ,d%@@@ rc |j|jdSrrr s rr!zMeanAbsoluteError.get_configXr"r)rNr#r)s@rr+r+/sW  D!!!!!! 8888888rr+z)keras.metrics.MeanAbsolutePercentageErrorc*eZdZdZdfd ZdZxZS)MeanAbsolutePercentageErrora6Computes mean absolute percentage error between `y_true` and `y_pred`. Formula: ```python loss = 100 * mean(abs((y_true - y_pred) / y_true)) ``` Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Example: Example: >>> m = keras.metrics.MeanAbsolutePercentageError() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result() 250000000.0 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]], ... sample_weight=[1, 0]) >>> m.result() 500000000.0 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[keras.metrics.MeanAbsolutePercentageError()]) ``` r Nchtt||d|_dSr-)rrr rrs rrz$MeanAbsolutePercentageError.__init__. 7UKKK rc |j|jdSrrr s rr!z&MeanAbsolutePercentageError.get_configr"r)r Nr#r)s@rr1r1\W""H!!!!!! 8888888rr1z)keras.metrics.MeanSquaredLogarithmicErrorc*eZdZdZdfd ZdZxZS)MeanSquaredLogarithmicErrora8Computes mean squared logarithmic error between `y_true` and `y_pred`. Formula: ```python loss = mean(square(log(y_true + 1) - log(y_pred + 1))) ``` Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Example: Example: >>> m = keras.metrics.MeanSquaredLogarithmicError() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result() 0.12011322 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]], ... sample_weight=[1, 0]) >>> m.result() 0.24022643 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[keras.metrics.MeanSquaredLogarithmicError()]) ``` r Nchtt||d|_dSr-)rrr rrs rrz$MeanSquaredLogarithmicError.__init__r3rc |j|jdSrrr s rr!z&MeanSquaredLogarithmicError.get_configr"r)r Nr#r)s@rr7r7r5rr7z"keras.metrics.RootMeanSquaredErrorc:eZdZdZdfd Zdfd ZfdZxZS) RootMeanSquaredErroraComputes root mean squared error metric between `y_true` and `y_pred`. Formula: ```python loss = sqrt(mean((y_pred - y_true) ** 2)) ``` Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Example: Example: >>> m = keras.metrics.RootMeanSquaredError() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result() 0.5 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]], ... sample_weight=[1, 0]) >>> m.result() 0.70710677 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[keras.metrics.RootMeanSquaredError()]) ``` root_mean_squared_errorNc\t||d|_dSr-)rrrrs rrzRootMeanSquaredError.__init__s+ U+++ rctj||j}tj||j}t||\}}tj||z }t ||S)Accumulates root mean squared error statistics. Args: y_true: The ground truth values. y_pred: The predicted values. sample_weight: Optional weighting of each example. Can be a `Tensor` whose rank is either 0, or the same rank as `y_true`, and must be broadcastable to `y_true`. Defaults to `1`. Returns: Update op. ) sample_weight)rconvert_to_tensor_dtypersquarer update_state)ry_truey_predr@error_sqrs rrDz!RootMeanSquaredError.update_statesp&vt{;;&vt{;;7GG:fvo..ww##HM#JJJrchtjtSN)rsqrtrresult)rrs rrKzRootMeanSquaredError.results!x(()))r)r<NrI)r$r%r&r'rrDrKr(r)s@rr;r;s##J!!!!!! KKKKKK(*********rr;zkeras.metrics.CosineSimilarityc*eZdZdZdfd ZdZxZS)CosineSimilarityaComputes the cosine similarity between the labels and predictions. Formula: ```python loss = sum(l2_norm(y_true) * l2_norm(y_pred)) ``` See: [Cosine Similarity](https://en.wikipedia.org/wiki/Cosine_similarity). This metric keeps the average cosine similarity between `predictions` and `labels` over a stream of data. Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. axis: (Optional) Defaults to `-1`. The dimension along which the cosine similarity is computed. Example: Example: >>> # l2_norm(y_true) = [[0., 1.], [1./1.414, 1./1.414]] >>> # l2_norm(y_pred) = [[1., 0.], [1./1.414, 1./1.414]] >>> # l2_norm(y_true) . l2_norm(y_pred) = [[0., 0.], [0.5, 0.5]] >>> # result = mean(sum(l2_norm(y_true) . l2_norm(y_pred), axis=1)) >>> # = ((0. + 0.) + (0.5 + 0.5)) / 2 >>> m = keras.metrics.CosineSimilarity(axis=1) >>> m.update_state([[0., 1.], [1., 1.]], [[1., 0.], [1., 1.]]) >>> m.result() 0.49999997 >>> m.reset_state() >>> m.update_state([[0., 1.], [1., 1.]], [[1., 0.], [1., 1.]], ... sample_weight=[0.3, 0.7]) >>> m.result() 0.6999999 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[keras.metrics.CosineSimilarity(axis=1)]) ``` cosine_similarityNcjtt|||d|_dS)N)raxisup)rrrNr)rrrrQrs rrzCosineSimilarity.__init__.s0 *DDIIIrc |j|jdSrrr s rr!zCosineSimilarity.get_config3r"r)rNNrOr#r)s@rrMrMsW,,\ 8888888rrMzkeras.metrics.LogCoshErrorc*eZdZdZdfd ZdZxZS) LogCoshErroraGComputes the logarithm of the hyperbolic cosine of the prediction error. Formula: ```python error = y_pred - y_true logcosh = mean(log((exp(error) + exp(-error))/2), axis=-1) ``` Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Example: Example: >>> m = keras.metrics.LogCoshError() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result() 0.10844523 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]], ... sample_weight=[1, 0]) >>> m.result() 0.21689045 Usage with `compile()` API: ```python model.compile(optimizer='sgd', loss='mse', metrics=[keras.metrics.LogCoshError()]) ``` logcoshNchtt||d|_dSr-)rrrrrs rrzLogCoshError.__init__]s- 4u555 rc |j|jdSrrr s rr!zLogCoshError.get_configbr"r)rVNr#r)s@rrUrU7r5rrUzkeras.metrics.R2ScorecPeZdZdZ d fd ZdZd dZd Zd Zfd Z xZ S)R2ScoreaComputes R2 score. Formula: ```python sum_squares_residuals = sum((y_true - y_pred) ** 2) sum_squares = sum((y_true - mean(y_true)) ** 2) R2 = 1 - sum_squares_residuals / sum_squares ``` This is also called the [coefficient of determination]( https://en.wikipedia.org/wiki/Coefficient_of_determination). It indicates how close the fitted regression line is to ground-truth data. - The highest score possible is 1.0. It indicates that the predictors perfectly accounts for variation in the target. - A score of 0.0 indicates that the predictors do not account for variation in the target. - It can also be negative if the model is worse than random. This metric can also compute the "Adjusted R2" score. Args: class_aggregation: Specifies how to aggregate scores corresponding to different output classes (or target dimensions), i.e. different dimensions on the last axis of the predictions. Equivalent to `multioutput` argument in Scikit-Learn. Should be one of `None` (no aggregation), `"uniform_average"`, `"variance_weighted_average"`. num_regressors: Number of independent regressors used ("Adjusted R2" score). 0 is the standard R2 score. Defaults to `0`. name: Optional. string name of the metric instance. dtype: Optional. data type of the metric result. Example: >>> y_true = np.array([[1], [4], [3]], dtype=np.float32) >>> y_pred = np.array([[2], [4], [4]], dtype=np.float32) >>> metric = keras.metrics.R2Score() >>> metric.update_state(y_true, y_pred) >>> result = metric.result() >>> result 0.57142854 uniform_averagerr2_scoreNcHt||d|_d}||vrtd|d||dkrtd|||_||_|dtjd |_ d |_ dS) NrrR)Nr[variance_weighted_averagez@Invalid value for argument `class_aggregation`. Expected one of z. Received: class_aggregation=rz]Invalid value for argument `num_regressors`. Expected a value >= 0. Received: num_regressors= num_samples)shape initializerrF) rrr ValueErrorclass_aggregationnum_regressors add_variablerZerosr`_built)rrdrerrvalid_class_aggregation_valuesrs rrzR2Score.__init__s d%000* & $B B BC8CC/@CC  A  =,:==  "3,,,$*,,-    rc`t|dkst|dkrtd|d|d|d|dtd|d|d|d}|d|gtj|_|d |gtj|_|d |gtj|_|d |gtj|_d |_ dS) NzcR2Score expects 2D inputs with shape (batch_size, output_dim). Received input shapes: y_pred.shape=z and y_true.shape=.rOzR2Score expects 2D inputs with shape (batch_size, output_dim), with output_dim fully defined (not None). Received input shapes: y_pred.shape= squared_sum)rrarbsumresidualcountT) lenrcrfrrgrmrn total_mserprh)r y_true_shape y_pred_shape num_classess r_buildzR2Score._builds |   ! !S%6%6!%;%;0(400!-000    #|B'7'?0)500!- 000 #2& ,,-$*,,-   $$-$*,,%   **-$*,,+   &&-$*,,'    rc htj||j}tj||j}t||\}}|js ||j|j|d}tj||j}t|jdkrtj |d}tj |tj|}|tj ||jz}|j |j tj |dz|j |jtj ||zdz|j |jtj ||z dztj ||jzdz|j |jtj |dz|j |jtj|zdS)r?r.NrQrrk)rrArBrrhrvrarrq expand_dims broadcast_tocastrnassignrmrrrpr`size)rrErFr@weighted_y_trues rrDzR2Score.update_states&vT[AAA&vT[AAA7GG{ 4 KK fl 3 3 3  M-m4:NNN }" # #q ( (OMBBBM( &8I8IJJ  38M6<#H#HH 37?#C#C#CCDDD   swv'?aHHH H     Ng&Q&-)N)NN     $*sw}1'E'E'EEFFF  038F3C3C CDDDDDrc|j|jz }|j|j|zz }d|j|z z }t jt j|d|}|jdkrt j|}n>|jdkr1t j||z}t j|}||z }n|}|j dkr|j |j dz krtj ddn|j |j dz krtj d dnt j |j d }t j |j d }t jt jd |t j|d } t jt j||d } t jd t j| | }|S) Nrxgr[r^rzdMore independent predictors than datapoints in adjusted R2 score. Falling back to standard R2 score.rk) stacklevelzIDivision by zero in Adjusted R2 score. Falling back to standard R2 score.float32r.g?)rnrprmrrrwhereisinfrdmeanrer`warningswarnrAmultiplysubtractdivide) rrtotal raw_scoresr\ weighted_sumsum_of_weightsnpnumdens rrKzR2Score.resultsx$*$ 48d?2$.501 Ysy44c:FF  !%6 6 6x ++HH  #'B B B75:#566L WU^^N#n4HH!H  ! # #"T%5%999 O  $(81(<<< 9  )$*:)LLL)$*=YOOOlLh//a1E1El3<1#5#5s;;<SZS-A-ABBrc|jD]5}|tj|j|j6dS)Nr.) variablesr}rzerosrar)rvs r reset_statezR2Score.reset_state;sE 8 8A HHSYqwag666 7 7 7 7 8 8rc|j|j|j|jd}t }i||S)N)rrrdre)rrrdrerr!)rconfig base_configrs rr!zR2Score.get_config?sLIZ!%!7"1    gg((** (+(((r)r[rr\NrI) r$r%r&r'rrvrDrKrr!r(r)s@rrZrZgs00h,  ######J%%%N,E,E,E,E\$$$L888)))))))))rrZrOctj|}tj||j}t||\}}t ||}t ||}tj||z|S)aNComputes the cosine similarity between labels and predictions. Formula: ```python loss = sum(l2_norm(y_true) * l2_norm(y_pred)) ``` Args: y_true: Tensor of true targets. y_pred: Tensor of predicted targets. axis: Axis along which to determine similarity. Defaults to `-1`. Returns: Cosine similarity tensor. Example: >>> y_true = [[0., 1.], [1., 1.], [1., 1.]] >>> y_pred = [[1., 0.], [1., 1.], [-1., -1.]] >>> loss = keras.losses.cosine_similarity(y_true, y_pred, axis=-1) [0., 0.99999994, -0.99999994] r.ry)rrArrr rn)rErFrQs rrNrNJs{0 "6 * *F  "6 > > >F3FFCCNFF vD ) ) )F vD ) ) )F 76F? . . ..r)rO)r keras.srcrrkeras.src.api_exportrkeras.src.losses.lossrkeras.src.losses.lossesrrr r r keras.src.metricsr keras.src.utils.numerical_utilsr MeanMetricWrapperrr+r1r7Meanr;rMrUMetricrZrNr_rrrs9""""""------@@@@@@,,,,,,777777BBBBBB666666BBBBBB//////555555.//88888(:880/8</00)8)8)8)8)8);)8)810)8X9::+8+8+8+8+8"3"E+8+8;:+8\9::+8+8+8+8+8"3"E+8+8;:+8\233@*@*@*@*@*,1@*@*43@*F.//5858585858(:58580/58p*+++8+8+8+8+8$6+8+8,++8^%&&_)_)_)_)_)&_)_)'&_)D//////r