a Sicc{ @sdZddlZddlZddlmmZddlmZddl m Z ddl m Z ddl m Z ddl mZddlmZdd lmZdd lmZdd lmZdd lmZdd lmZddlmZedGdddZGdddeZedGdddeZedGdddeZedGdddeZedGdddeZ ed Gd!d"d"eZ!ed#Gd$d%d%eZ"ed&Gd'd(d(eZ#ed)Gd*d+d+eZ$ed,Gd-d.d.eZ%ed/Gd0d1d1eZ&ed2Gd3d4d4eZ'ed5Gd6d7d7eZ(ed8Gd9d:d:eZ)ed;GdGd?d@d@eZ+edAdBdCdDdEdFej,jj-dGdHZ.ddJdKZ/e0e.ej1dLdMZ2edNdOdPdQdRdSej,jj-dTdUZ3e0e3ej1dVdWZ4edXdYdZd[d\d]ej,jj-d^d_Z5e0e5ej1d`daZ6edbdcdddedfdgej,jj-dhdiZ7e0e7ej1djdkZ8dldmZ9edndoej,jj-dpdqZ:edrdsej,jj-dtduZ;edvej,jj-dwdxZeddej,jj-dddZ?e0e?ej1dddZ@eddej,jj-dddZAe0eAej1dddZBeddej,jj-dddZCe0eCej1dddZDeddej,jj-dddZEe0eEej1dddZFeddddddddej,jj-ddZGeddej,jj-ddZHedgddzej,jj-dddZIedGdddeZJeCZKZLe.ZMZNe3ZOZPe5ZQZRe7ZSZTeGZUZVZWe>ZXe=ZYddZZedddZ[eddddZ\edddZ]ejj^j_j`deAdiZadS)zBuilt-in loss functions.N)backend) saving_lib) generic_utils) losses_utils)tf_utils)deserialize_keras_objectserialize_keras_object)ragged_map_ops) ragged_util)dispatch) keras_export) doc_controlszkeras.losses.Lossc@sdeZdZdZejjdfddZddZdddZ e d d Z d d Z e jejd dZddZdS)LossarLoss base class. To be implemented by subclasses: * `call()`: Contains the logic for loss calculation using `y_true`, `y_pred`. Example subclass implementation: ```python class MeanSquaredError(Loss): def call(self, y_true, y_pred): return tf.reduce_mean(tf.math.square(y_pred - y_true), axis=-1) ``` When used with `tf.distribute.Strategy`, outside of built-in training loops such as `tf.keras` `compile` and `fit`, please use 'SUM' or 'NONE' reduction types, and reduce losses explicitly in your training loop. Using 'AUTO' or 'SUM_OVER_BATCH_SIZE' will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details on this. You can implement 'SUM_OVER_BATCH_SIZE' using global batch size like: ```python 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)) ``` NcCs*tj|||_||_d|_|dS)aInitializes `Loss` class. Args: reduction: Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `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`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. name: Optional name for the instance. FN)r ReductionV2validate reductionname_allow_sum_over_batch_size_set_name_scopeselfrrrH/var/www/html/django/DPS/env/lib/python3.9/site-packages/keras/losses.py__init__Ns  z Loss.__init__cCs@|jdur|jjd|_n |jdkr.d|_n|jd|_dS)z"Creates a valid `name_scope` name.N_zlambda)r __class____name__strip _name_scoperrrrrfs   zLoss._set_name_scopec Cst|||}t|j|tr2|j}ntjj |jtjj }|||}t |}|}t ||||}t j|||dWdWdS1s0YWdn1s0YdS)a|Invokes the `Loss` instance. Args: y_true: Ground truth values. shape = `[batch_size, d0, .. dN]`, except sparse loss functions such as sparse categorical crossentropy where shape = `[batch_size, d0, .. dN-1]` y_pred: The predicted values. shape = `[batch_size, d0, .. dN]` sample_weight: Optional `sample_weight` acts as a coefficient for the loss. If a scalar is provided, then the loss is simply scaled by the given value. If `sample_weight` is a tensor of size `[batch_size]`, then the total loss 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 loss element of `y_pred` is scaled by the corresponding value of `sample_weight`. (Note on`dN-1`: all loss functions reduce by 1 dimension, usually axis=-1.) Returns: Weighted loss float `Tensor`. If `reduction` is `NONE`, this has shape `[batch_size, d0, .. dN-1]`; otherwise, it is scalar. (Note `dN-1` because all loss functions reduce by 1 dimension, usually axis=-1.) Raises: ValueError: If the shape of `sample_weight` is invalid. )rN)r"graph_context_for_symbolic_tensorsr name_scoper tfexecuting_eagerlycall __internal__ autograph tf_convertcontrol_status_ctxrget_mask_get_reductionZapply_valid_maskcompute_weighted_loss) ry_truey_pred sample_weight graph_ctxcall_fnlossesmaskrrrr__call__ps$  z Loss.__call__cCs|fi|S)zInstantiates a `Loss` from its config (output of `get_config()`). Args: config: Output of `get_config()`. Returns: A `Loss` instance. r)clsconfigrrr from_configs zLoss.from_configcCs|j|jdS)z4Returns the config dictionary for a `Loss` instance.rrr9r!rrr get_configszLoss.get_configcCs tddS)aInvokes the `Loss` instance. Args: y_true: Ground truth values. shape = `[batch_size, d0, .. dN]`, except sparse loss functions such as sparse categorical crossentropy where shape = `[batch_size, d0, .. dN-1]` y_pred: The predicted values. shape = `[batch_size, d0, .. dN]` Returns: Loss values with the shape `[batch_size, d0, .. dN-1]`. z"Must be implemented in subclasses.N)NotImplementedError)rr.r/rrrr&sz Loss.callcCsP|js4tjr4|jtjjks,|jtjjkr4t d|jtjjkrJtjjS|jS)z?Handles `AUTO` reduction cases and returns the reduction value.aQPlease use `tf.keras.losses.Reduction.SUM` or `tf.keras.losses.Reduction.NONE` for loss reduction when losses are used with `tf.distribute.Strategy` outside of the built-in training loops. You can implement `tf.keras.losses.Reduction.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 https://www.tensorflow.org/tutorials/distribute/custom_training for more details.) rr$ distribute has_strategyrrrAUTOSUM_OVER_BATCH_SIZE ValueErrorr!rrrr,s   zLoss._get_reduction)N)r __module__ __qualname____doc__rrr>rrr5 classmethodr8r:abcabstractmethodrfor_subclass_implementersr&r,rrrrr(s$ 2  rcsJeZdZdZejjdffdd ZddZfddZ e d d Z Z S) LossFunctionWrapperz*Wraps a loss function in the `Loss` class.Nc s tj||d||_||_dS)aInitializes `LossFunctionWrapper` class. Args: fn: The loss function to wrap, with signature `fn(y_true, y_pred, **kwargs)`. reduction: Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `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`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. name: Optional name for the instance. **kwargs: The keyword arguments that are passed on to `fn`. r9N)superrfn _fn_kwargs)rrJrrkwargsrrrrszLossFunctionWrapper.__init__cCsRt|r$t|r$t||\}}tjj|jtjj}|||fi|j S)zInvokes the `LossFunctionWrapper` instance. Args: y_true: Ground truth values. y_pred: The predicted values. Returns: Loss values per sample. ) r$ is_tensorrsqueeze_or_expand_dimensionsr'r(r)rJr*rK)rr.r/ag_fnrrrr&s zLossFunctionWrapper.callcspi}|jD]$\}}t|r*t|n|||<qtjrJt |j |d<t }t t|t|S)NrJ)rKitemsris_tensor_or_variablerevalr_ENABLEDrget_registered_namerJrIr:dictlist)rr7kv base_configrMrrr:s zLossFunctionWrapper.get_configcCs8tjr*|dd}|r*|tur*t||d<|fi|S)zInstantiates a `Loss` from its config (output of `get_config()`). Args: config: Output of `get_config()`. Returns: A `keras.losses.Loss` instance. rJN)rrTpoprHget)r6r7fn_namerrrr8s    zLossFunctionWrapper.from_config) rrArBrCrrr>rr&r:rDr8 __classcell__rrrMrrHs rHzkeras.losses.MeanSquaredErrorcs*eZdZdZejjdffdd ZZS)MeanSquaredErroraComputes the mean of squares of errors between labels and predictions. `loss = square(y_true - y_pred)` Standalone usage: >>> y_true = [[0., 1.], [0., 0.]] >>> y_pred = [[1., 1.], [1., 0.]] >>> # Using 'auto'/'sum_over_batch_size' reduction type. >>> mse = tf.keras.losses.MeanSquaredError() >>> mse(y_true, y_pred).numpy() 0.5 >>> # Calling with 'sample_weight'. >>> mse(y_true, y_pred, sample_weight=[0.7, 0.3]).numpy() 0.25 >>> # Using 'sum' reduction type. >>> mse = tf.keras.losses.MeanSquaredError( ... reduction=tf.keras.losses.Reduction.SUM) >>> mse(y_true, y_pred).numpy() 1.0 >>> # Using 'none' reduction type. >>> mse = tf.keras.losses.MeanSquaredError( ... reduction=tf.keras.losses.Reduction.NONE) >>> mse(y_true, y_pred).numpy() array([0.5, 0.5], dtype=float32) Usage with the `compile()` API: ```python model.compile(optimizer='sgd', loss=tf.keras.losses.MeanSquaredError()) ``` mean_squared_errorcstjt||ddS)a-Initializes `MeanSquaredError` instance. Args: reduction: Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `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`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. name: Optional name for the instance. Defaults to 'mean_squared_error'. rrN)rIrr`rrMrrrVszMeanSquaredError.__init__ rrArBrCrrr>rr^rrrMrr_0s%r_zkeras.losses.MeanAbsoluteErrorcs*eZdZdZejjdffdd ZZS)MeanAbsoluteErroraComputes the mean of absolute difference between labels and predictions. `loss = abs(y_true - y_pred)` Standalone usage: >>> y_true = [[0., 1.], [0., 0.]] >>> y_pred = [[1., 1.], [1., 0.]] >>> # Using 'auto'/'sum_over_batch_size' reduction type. >>> mae = tf.keras.losses.MeanAbsoluteError() >>> mae(y_true, y_pred).numpy() 0.5 >>> # Calling with 'sample_weight'. >>> mae(y_true, y_pred, sample_weight=[0.7, 0.3]).numpy() 0.25 >>> # Using 'sum' reduction type. >>> mae = tf.keras.losses.MeanAbsoluteError( ... reduction=tf.keras.losses.Reduction.SUM) >>> mae(y_true, y_pred).numpy() 1.0 >>> # Using 'none' reduction type. >>> mae = tf.keras.losses.MeanAbsoluteError( ... reduction=tf.keras.losses.Reduction.NONE) >>> mae(y_true, y_pred).numpy() array([0.5, 0.5], dtype=float32) Usage with the `compile()` API: ```python model.compile(optimizer='sgd', loss=tf.keras.losses.MeanAbsoluteError()) ``` mean_absolute_errorcstjt||ddS)a/Initializes `MeanAbsoluteError` instance. Args: reduction: Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `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`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. name: Optional name for the instance. Defaults to 'mean_absolute_error'. raN)rIrrdrrMrrrszMeanAbsoluteError.__init__rbrrrMrrcls&rcz(keras.losses.MeanAbsolutePercentageErrorcs*eZdZdZejjdffdd ZZS)MeanAbsolutePercentageErroraComputes the mean absolute percentage error between `y_true` and `y_pred`. Formula: `loss = 100 * abs((y_true - y_pred) / y_true)` Note that to avoid dividing by zero, a small epsilon value is added to the denominator. Standalone usage: >>> y_true = [[2., 1.], [2., 3.]] >>> y_pred = [[1., 1.], [1., 0.]] >>> # Using 'auto'/'sum_over_batch_size' reduction type. >>> mape = tf.keras.losses.MeanAbsolutePercentageError() >>> mape(y_true, y_pred).numpy() 50. >>> # Calling with 'sample_weight'. >>> mape(y_true, y_pred, sample_weight=[0.7, 0.3]).numpy() 20. >>> # Using 'sum' reduction type. >>> mape = tf.keras.losses.MeanAbsolutePercentageError( ... reduction=tf.keras.losses.Reduction.SUM) >>> mape(y_true, y_pred).numpy() 100. >>> # Using 'none' reduction type. >>> mape = tf.keras.losses.MeanAbsolutePercentageError( ... reduction=tf.keras.losses.Reduction.NONE) >>> mape(y_true, y_pred).numpy() array([25., 75.], dtype=float32) Usage with the `compile()` API: ```python model.compile(optimizer='sgd', loss=tf.keras.losses.MeanAbsolutePercentageError()) ``` mean_absolute_percentage_errorcstjt||ddS)aDInitializes `MeanAbsolutePercentageError` instance. Args: reduction: Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `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`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. name: Optional name for the instance. Defaults to 'mean_absolute_percentage_error'. raN)rIrrfrrMrrrsz$MeanAbsolutePercentageError.__init__rbrrrMrres,rez(keras.losses.MeanSquaredLogarithmicErrorcs*eZdZdZejjdffdd ZZS)MeanSquaredLogarithmicErrora\Computes the mean squared logarithmic error between `y_true` and `y_pred`. `loss = square(log(y_true + 1.) - log(y_pred + 1.))` Standalone usage: >>> y_true = [[0., 1.], [0., 0.]] >>> y_pred = [[1., 1.], [1., 0.]] >>> # Using 'auto'/'sum_over_batch_size' reduction type. >>> msle = tf.keras.losses.MeanSquaredLogarithmicError() >>> msle(y_true, y_pred).numpy() 0.240 >>> # Calling with 'sample_weight'. >>> msle(y_true, y_pred, sample_weight=[0.7, 0.3]).numpy() 0.120 >>> # Using 'sum' reduction type. >>> msle = tf.keras.losses.MeanSquaredLogarithmicError( ... reduction=tf.keras.losses.Reduction.SUM) >>> msle(y_true, y_pred).numpy() 0.480 >>> # Using 'none' reduction type. >>> msle = tf.keras.losses.MeanSquaredLogarithmicError( ... reduction=tf.keras.losses.Reduction.NONE) >>> msle(y_true, y_pred).numpy() array([0.240, 0.240], dtype=float32) Usage with the `compile()` API: ```python model.compile(optimizer='sgd', loss=tf.keras.losses.MeanSquaredLogarithmicError()) ``` mean_squared_logarithmic_errorcstjt||ddS)aDInitializes `MeanSquaredLogarithmicError` instance. Args: reduction: Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `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`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. name: Optional name for the instance. Defaults to 'mean_squared_logarithmic_error'. raN)rIrrhrrMrrrsz$MeanSquaredLogarithmicError.__init__rbrrrMrrgs'rgzkeras.losses.BinaryCrossentropycs0eZdZdZdddejjdffdd ZZS)BinaryCrossentropya Computes the cross-entropy loss between true labels and predicted labels. Use this cross-entropy loss for binary (0 or 1) classification applications. The loss function requires the following inputs: - `y_true` (true label): This is either 0 or 1. - `y_pred` (predicted value): This is the model's prediction, i.e, a single floating-point value which either represents a [logit](https://en.wikipedia.org/wiki/Logit), (i.e, value in [-inf, inf] when `from_logits=True`) or a probability (i.e, value in [0., 1.] when `from_logits=False`). **Recommended Usage:** (set `from_logits=True`) With `tf.keras` API: ```python model.compile( loss=tf.keras.losses.BinaryCrossentropy(from_logits=True), .... ) ``` As a standalone function: >>> # Example 1: (batch_size = 1, number of samples = 4) >>> y_true = [0, 1, 0, 0] >>> y_pred = [-18.6, 0.51, 2.94, -12.8] >>> bce = tf.keras.losses.BinaryCrossentropy(from_logits=True) >>> bce(y_true, y_pred).numpy() 0.865 >>> # Example 2: (batch_size = 2, number of samples = 4) >>> y_true = [[0, 1], [0, 0]] >>> y_pred = [[-18.6, 0.51], [2.94, -12.8]] >>> # Using default 'auto'/'sum_over_batch_size' reduction type. >>> bce = tf.keras.losses.BinaryCrossentropy(from_logits=True) >>> bce(y_true, y_pred).numpy() 0.865 >>> # Using 'sample_weight' attribute >>> bce(y_true, y_pred, sample_weight=[0.8, 0.2]).numpy() 0.243 >>> # Using 'sum' reduction` type. >>> bce = tf.keras.losses.BinaryCrossentropy(from_logits=True, ... reduction=tf.keras.losses.Reduction.SUM) >>> bce(y_true, y_pred).numpy() 1.730 >>> # Using 'none' reduction type. >>> bce = tf.keras.losses.BinaryCrossentropy(from_logits=True, ... reduction=tf.keras.losses.Reduction.NONE) >>> bce(y_true, y_pred).numpy() array([0.235, 1.496], dtype=float32) **Default Usage:** (set `from_logits=False`) >>> # Make the following updates to the above "Recommended Usage" section >>> # 1. Set `from_logits=False` >>> tf.keras.losses.BinaryCrossentropy() # OR ...('from_logits=False') >>> # 2. Update `y_pred` to use probabilities instead of logits >>> y_pred = [0.6, 0.3, 0.2, 0.8] # OR [[0.6, 0.3], [0.2, 0.8]] Fbinary_crossentropycs"tjt|||||d||_dS)aInitializes `BinaryCrossentropy` instance. Args: from_logits: Whether to interpret `y_pred` as a tensor of [logit](https://en.wikipedia.org/wiki/Logit) values. By default, we assume that `y_pred` contains probabilities (i.e., values in [0, 1]). label_smoothing: Float in [0, 1]. When 0, no smoothing occurs. When > 0, we compute the loss between the predicted labels and a smoothed version of the true labels, where the smoothing squeezes the labels towards 0.5. Larger values of `label_smoothing` correspond to heavier smoothing. axis: The axis along which to compute crossentropy (the features axis). Defaults to -1. reduction: Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `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`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. name: Name for the op. Defaults to 'binary_crossentropy'. rr from_logitslabel_smoothingaxisN)rIrrlrnrrnrorprrrMrrrqs"zBinaryCrossentropy.__init__rbrrrMrri1s@riz$keras.losses.BinaryFocalCrossentropycsBeZdZdZddddddejjdffdd Zfd d ZZ S) BinaryFocalCrossentropyaComputes the focal cross-entropy loss between true labels and predictions. Binary cross-entropy loss is often used for binary (0 or 1) classification tasks. The loss function requires the following inputs: - `y_true` (true label): This is either 0 or 1. - `y_pred` (predicted value): This is the model's prediction, i.e, a single floating-point value which either represents a [logit](https://en.wikipedia.org/wiki/Logit), (i.e, value in [-inf, inf] when `from_logits=True`) or a probability (i.e, value in `[0., 1.]` when `from_logits=False`). According to [Lin et al., 2018](https://arxiv.org/pdf/1708.02002.pdf), it helps to apply a "focal factor" to down-weight easy examples and focus more on hard examples. By default, the focal tensor is computed as follows: `focal_factor = (1 - output) ** gamma` for class 1 `focal_factor = output ** gamma` for class 0 where `gamma` is a focusing parameter. When `gamma=0`, this function is equivalent to the binary crossentropy loss. With the `compile()` API: ```python model.compile( loss=tf.keras.losses.BinaryFocalCrossentropy(gamma=2.0, from_logits=True), .... ) ``` As a standalone function: >>> # Example 1: (batch_size = 1, number of samples = 4) >>> y_true = [0, 1, 0, 0] >>> y_pred = [-18.6, 0.51, 2.94, -12.8] >>> loss = tf.keras.losses.BinaryFocalCrossentropy(gamma=2, ... from_logits=True) >>> loss(y_true, y_pred).numpy() 0.691 >>> # Apply class weight >>> loss = tf.keras.losses.BinaryFocalCrossentropy( ... apply_class_balancing=True, gamma=2, from_logits=True) >>> loss(y_true, y_pred).numpy() 0.51 >>> # Example 2: (batch_size = 2, number of samples = 4) >>> y_true = [[0, 1], [0, 0]] >>> y_pred = [[-18.6, 0.51], [2.94, -12.8]] >>> # Using default 'auto'/'sum_over_batch_size' reduction type. >>> loss = tf.keras.losses.BinaryFocalCrossentropy(gamma=3, ... from_logits=True) >>> loss(y_true, y_pred).numpy() 0.647 >>> # Apply class weight >>> loss = tf.keras.losses.BinaryFocalCrossentropy( ... apply_class_balancing=True, gamma=3, from_logits=True) >>> loss(y_true, y_pred).numpy() 0.482 >>> # Using 'sample_weight' attribute with focal effect >>> loss = tf.keras.losses.BinaryFocalCrossentropy(gamma=3, ... from_logits=True) >>> loss(y_true, y_pred, sample_weight=[0.8, 0.2]).numpy() 0.133 >>> # Apply class weight >>> loss = tf.keras.losses.BinaryFocalCrossentropy( ... apply_class_balancing=True, gamma=3, from_logits=True) >>> loss(y_true, y_pred, sample_weight=[0.8, 0.2]).numpy() 0.097 >>> # Using 'sum' reduction` type. >>> loss = tf.keras.losses.BinaryFocalCrossentropy(gamma=4, ... from_logits=True, ... reduction=tf.keras.losses.Reduction.SUM) >>> loss(y_true, y_pred).numpy() 1.222 >>> # Apply class weight >>> loss = tf.keras.losses.BinaryFocalCrossentropy( ... apply_class_balancing=True, gamma=4, from_logits=True, ... reduction=tf.keras.losses.Reduction.SUM) >>> loss(y_true, y_pred).numpy() 0.914 >>> # Using 'none' reduction type. >>> loss = tf.keras.losses.BinaryFocalCrossentropy( ... gamma=5, from_logits=True, ... reduction=tf.keras.losses.Reduction.NONE) >>> loss(y_true, y_pred).numpy() array([0.0017 1.1561], dtype=float32) >>> # Apply class weight >>> loss = tf.keras.losses.BinaryFocalCrossentropy( ... apply_class_balancing=True, gamma=5, from_logits=True, ... reduction=tf.keras.losses.Reduction.NONE) >>> loss(y_true, y_pred).numpy() array([0.0004 0.8670], dtype=float32) Args: apply_class_balancing: A bool, whether to apply weight balancing on the binary classes 0 and 1. alpha: A weight balancing factor for class 1, default is `0.25` as mentioned in reference [Lin et al., 2018]( https://arxiv.org/pdf/1708.02002.pdf). The weight for class 0 is `1.0 - alpha`. gamma: A focusing parameter used to compute the focal factor, default is `2.0` as mentioned in the reference [Lin et al., 2018](https://arxiv.org/pdf/1708.02002.pdf). from_logits: Whether to interpret `y_pred` as a tensor of [logit](https://en.wikipedia.org/wiki/Logit) values. By default, we assume that `y_pred` are probabilities (i.e., values in `[0, 1]`). label_smoothing: Float in `[0, 1]`. When `0`, no smoothing occurs. When > `0`, we compute the loss between the predicted labels and a smoothed version of the true labels, where the smoothing squeezes the labels towards `0.5`. Larger values of `label_smoothing` correspond to heavier smoothing. axis: The axis along which to compute crossentropy (the features axis). Defaults to `-1`. reduction: Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `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()`, using `SUM_OVER_BATCH_SIZE` or `AUTO` will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. name: Name for the op. Defaults to 'binary_focal_crossentropy'. F?@rjrkbinary_focal_crossentropyc s:tjt||||||||d ||_||_||_||_dS)z/Initializes `BinaryFocalCrossentropy` instance.)apply_class_balancingalphagammarrrnrorpN)rIrrurnrvrwrx) rrvrwrxrnrorprrrMrrr&s  z BinaryFocalCrossentropy.__init__cs8|j|j|jd}t}tt|t|S)N)rvrwrx)rvrwrxrIr:rVrWrQ)rr7rZrMrrr:Bs  z"BinaryFocalCrossentropy.get_config) rrArBrCrrr>rr:r^rrrMrrrs rrz$keras.losses.CategoricalCrossentropycs0eZdZdZdddejjdffdd ZZS)CategoricalCrossentropyaComputes the crossentropy loss between the labels and predictions. Use this crossentropy loss function when there are two or more label classes. We expect labels to be provided in a `one_hot` representation. If you want to provide labels as integers, please use `SparseCategoricalCrossentropy` loss. There should be `# classes` floating point values per feature. In the snippet below, there is `# classes` floating pointing values per example. The shape of both `y_pred` and `y_true` are `[batch_size, num_classes]`. Standalone usage: >>> y_true = [[0, 1, 0], [0, 0, 1]] >>> y_pred = [[0.05, 0.95, 0], [0.1, 0.8, 0.1]] >>> # Using 'auto'/'sum_over_batch_size' reduction type. >>> cce = tf.keras.losses.CategoricalCrossentropy() >>> cce(y_true, y_pred).numpy() 1.177 >>> # Calling with 'sample_weight'. >>> cce(y_true, y_pred, sample_weight=tf.constant([0.3, 0.7])).numpy() 0.814 >>> # Using 'sum' reduction type. >>> cce = tf.keras.losses.CategoricalCrossentropy( ... reduction=tf.keras.losses.Reduction.SUM) >>> cce(y_true, y_pred).numpy() 2.354 >>> # Using 'none' reduction type. >>> cce = tf.keras.losses.CategoricalCrossentropy( ... reduction=tf.keras.losses.Reduction.NONE) >>> cce(y_true, y_pred).numpy() array([0.0513, 2.303], dtype=float32) Usage with the `compile()` API: ```python model.compile(optimizer='sgd', loss=tf.keras.losses.CategoricalCrossentropy()) ``` Frjrkcategorical_crossentropycstjt|||||ddS)afInitializes `CategoricalCrossentropy` instance. Args: from_logits: Whether `y_pred` is expected to be a logits tensor. By default, we assume that `y_pred` encodes a probability distribution. label_smoothing: Float in [0, 1]. When > 0, label values are smoothed, meaning the confidence on label values are relaxed. For example, if `0.1`, use `0.1 / num_classes` for non-target labels and `0.9 + 0.1 / num_classes` for target labels. axis: The axis along which to compute crossentropy (the features axis). Defaults to -1. reduction: Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `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`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. name: Optional name for the instance. Defaults to 'categorical_crossentropy'. rmN)rIrrzrqrMrrr{s z CategoricalCrossentropy.__init__rbrrrMrryLs/ryz*keras.losses.SparseCategoricalCrossentropycs.eZdZdZddejjdffdd ZZS)SparseCategoricalCrossentropyaComputes the crossentropy loss between the labels and predictions. Use this crossentropy loss function when there are two or more label classes. We expect labels to be provided as integers. If you want to provide labels using `one-hot` representation, please use `CategoricalCrossentropy` loss. There should be `# classes` floating point values per feature for `y_pred` and a single floating point value per feature for `y_true`. In the snippet below, there is a single floating point value per example for `y_true` and `# classes` floating pointing values per example for `y_pred`. The shape of `y_true` is `[batch_size]` and the shape of `y_pred` is `[batch_size, num_classes]`. Standalone usage: >>> y_true = [1, 2] >>> y_pred = [[0.05, 0.95, 0], [0.1, 0.8, 0.1]] >>> # Using 'auto'/'sum_over_batch_size' reduction type. >>> scce = tf.keras.losses.SparseCategoricalCrossentropy() >>> scce(y_true, y_pred).numpy() 1.177 >>> # Calling with 'sample_weight'. >>> scce(y_true, y_pred, sample_weight=tf.constant([0.3, 0.7])).numpy() 0.814 >>> # Using 'sum' reduction type. >>> scce = tf.keras.losses.SparseCategoricalCrossentropy( ... reduction=tf.keras.losses.Reduction.SUM) >>> scce(y_true, y_pred).numpy() 2.354 >>> # Using 'none' reduction type. >>> scce = tf.keras.losses.SparseCategoricalCrossentropy( ... reduction=tf.keras.losses.Reduction.NONE) >>> scce(y_true, y_pred).numpy() array([0.0513, 2.303], dtype=float32) Usage with the `compile()` API: ```python model.compile(optimizer='sgd', loss=tf.keras.losses.SparseCategoricalCrossentropy()) ``` FNsparse_categorical_crossentropycstjt||||ddS)a1Initializes `SparseCategoricalCrossentropy` instance. Args: from_logits: Whether `y_pred` is expected to be a logits tensor. By default, we assume that `y_pred` encodes a probability distribution. ignore_class: Optional integer. The ID of a class to be ignored during loss computation. This is useful, for example, in segmentation problems featuring a "void" class (commonly -1 or 255) in segmentation maps. By default (`ignore_class=None`), all classes are considered. reduction: Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `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`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. name: Optional name for the instance. Defaults to 'sparse_categorical_crossentropy'. )rrrn ignore_classN)rIrr|)rrnr}rrrMrrrsz&SparseCategoricalCrossentropy.__init__rbrrrMrr{s 1r{zkeras.losses.Hingecs*eZdZdZejjdffdd ZZS)Hingea1Computes the hinge loss between `y_true` and `y_pred`. `loss = maximum(1 - y_true * y_pred, 0)` `y_true` values are expected to be -1 or 1. If binary (0 or 1) labels are provided we will convert them to -1 or 1. Standalone usage: >>> y_true = [[0., 1.], [0., 0.]] >>> y_pred = [[0.6, 0.4], [0.4, 0.6]] >>> # Using 'auto'/'sum_over_batch_size' reduction type. >>> h = tf.keras.losses.Hinge() >>> h(y_true, y_pred).numpy() 1.3 >>> # Calling with 'sample_weight'. >>> h(y_true, y_pred, sample_weight=[1, 0]).numpy() 0.55 >>> # Using 'sum' reduction type. >>> h = tf.keras.losses.Hinge( ... reduction=tf.keras.losses.Reduction.SUM) >>> h(y_true, y_pred).numpy() 2.6 >>> # Using 'none' reduction type. >>> h = tf.keras.losses.Hinge( ... reduction=tf.keras.losses.Reduction.NONE) >>> h(y_true, y_pred).numpy() array([1.1, 1.5], dtype=float32) Usage with the `compile()` API: ```python model.compile(optimizer='sgd', loss=tf.keras.losses.Hinge()) ``` hingecstjt||ddS)a Initializes `Hinge` instance. Args: reduction: Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `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`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. name: Optional name for the instance. Defaults to 'hinge'. raN)rIrrrrMrrr&szHinge.__init__rbrrrMrr~s'r~zkeras.losses.SquaredHingecs*eZdZdZejjdffdd ZZS) SquaredHingeaaComputes the squared hinge loss between `y_true` and `y_pred`. `loss = square(maximum(1 - y_true * y_pred, 0))` `y_true` values are expected to be -1 or 1. If binary (0 or 1) labels are provided we will convert them to -1 or 1. Standalone usage: >>> y_true = [[0., 1.], [0., 0.]] >>> y_pred = [[0.6, 0.4], [0.4, 0.6]] >>> # Using 'auto'/'sum_over_batch_size' reduction type. >>> h = tf.keras.losses.SquaredHinge() >>> h(y_true, y_pred).numpy() 1.86 >>> # Calling with 'sample_weight'. >>> h(y_true, y_pred, sample_weight=[1, 0]).numpy() 0.73 >>> # Using 'sum' reduction type. >>> h = tf.keras.losses.SquaredHinge( ... reduction=tf.keras.losses.Reduction.SUM) >>> h(y_true, y_pred).numpy() 3.72 >>> # Using 'none' reduction type. >>> h = tf.keras.losses.SquaredHinge( ... reduction=tf.keras.losses.Reduction.NONE) >>> h(y_true, y_pred).numpy() array([1.46, 2.26], dtype=float32) Usage with the `compile()` API: ```python model.compile(optimizer='sgd', loss=tf.keras.losses.SquaredHinge()) ``` squared_hingecstjt||ddS)aInitializes `SquaredHinge` instance. Args: reduction: Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `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`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. name: Optional name for the instance. Defaults to 'squared_hinge'. raN)rIrrrrMrrrbszSquaredHinge.__init__rbrrrMrr9s(rzkeras.losses.CategoricalHingecs*eZdZdZejjdffdd ZZS)CategoricalHingea'Computes the categorical hinge loss between `y_true` and `y_pred`. `loss = maximum(neg - pos + 1, 0)` where `neg=maximum((1-y_true)*y_pred) and pos=sum(y_true*y_pred)` Standalone usage: >>> y_true = [[0, 1], [0, 0]] >>> y_pred = [[0.6, 0.4], [0.4, 0.6]] >>> # Using 'auto'/'sum_over_batch_size' reduction type. >>> h = tf.keras.losses.CategoricalHinge() >>> h(y_true, y_pred).numpy() 1.4 >>> # Calling with 'sample_weight'. >>> h(y_true, y_pred, sample_weight=[1, 0]).numpy() 0.6 >>> # Using 'sum' reduction type. >>> h = tf.keras.losses.CategoricalHinge( ... reduction=tf.keras.losses.Reduction.SUM) >>> h(y_true, y_pred).numpy() 2.8 >>> # Using 'none' reduction type. >>> h = tf.keras.losses.CategoricalHinge( ... reduction=tf.keras.losses.Reduction.NONE) >>> h(y_true, y_pred).numpy() array([1.2, 1.6], dtype=float32) Usage with the `compile()` API: ```python model.compile(optimizer='sgd', loss=tf.keras.losses.CategoricalHinge()) ``` categorical_hingecstjt||ddS)a Initializes `CategoricalHinge` instance. Args: reduction: Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `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`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. name: Optional name for the instance. Defaults to 'categorical_hinge'. raN)rIrrrrMrrrszCategoricalHinge.__init__rbrrrMrrws&rzkeras.losses.Poissoncs*eZdZdZejjdffdd ZZS)PoissonaComputes the Poisson loss between `y_true` and `y_pred`. `loss = y_pred - y_true * log(y_pred)` Standalone usage: >>> y_true = [[0., 1.], [0., 0.]] >>> y_pred = [[1., 1.], [0., 0.]] >>> # Using 'auto'/'sum_over_batch_size' reduction type. >>> p = tf.keras.losses.Poisson() >>> p(y_true, y_pred).numpy() 0.5 >>> # Calling with 'sample_weight'. >>> p(y_true, y_pred, sample_weight=[0.8, 0.2]).numpy() 0.4 >>> # Using 'sum' reduction type. >>> p = tf.keras.losses.Poisson( ... reduction=tf.keras.losses.Reduction.SUM) >>> p(y_true, y_pred).numpy() 0.999 >>> # Using 'none' reduction type. >>> p = tf.keras.losses.Poisson( ... reduction=tf.keras.losses.Reduction.NONE) >>> p(y_true, y_pred).numpy() array([0.999, 0.], dtype=float32) Usage with the `compile()` API: ```python model.compile(optimizer='sgd', loss=tf.keras.losses.Poisson()) ``` poissoncstjt||ddS)a Initializes `Poisson` instance. Args: reduction: Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `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`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. name: Optional name for the instance. Defaults to 'poisson'. raN)rIrrrrMrrrszPoisson.__init__rbrrrMrrs$rzkeras.losses.LogCoshcs*eZdZdZejjdffdd ZZS)LogCoshaComputes the logarithm of the hyperbolic cosine of the prediction error. `logcosh = log((exp(x) + exp(-x))/2)`, where x is the error `y_pred - y_true`. Standalone usage: >>> y_true = [[0., 1.], [0., 0.]] >>> y_pred = [[1., 1.], [0., 0.]] >>> # Using 'auto'/'sum_over_batch_size' reduction type. >>> l = tf.keras.losses.LogCosh() >>> l(y_true, y_pred).numpy() 0.108 >>> # Calling with 'sample_weight'. >>> l(y_true, y_pred, sample_weight=[0.8, 0.2]).numpy() 0.087 >>> # Using 'sum' reduction type. >>> l = tf.keras.losses.LogCosh( ... reduction=tf.keras.losses.Reduction.SUM) >>> l(y_true, y_pred).numpy() 0.217 >>> # Using 'none' reduction type. >>> l = tf.keras.losses.LogCosh( ... reduction=tf.keras.losses.Reduction.NONE) >>> l(y_true, y_pred).numpy() array([0.217, 0.], dtype=float32) Usage with the `compile()` API: ```python model.compile(optimizer='sgd', loss=tf.keras.losses.LogCosh()) ``` log_coshcstjt||ddS)aInitializes `LogCosh` instance. Args: reduction: Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `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`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. name: Optional name for the instance. Defaults to 'log_cosh'. raN)rIrrrrMrrrszLogCosh.__init__rbrrrMrrs&rzkeras.losses.KLDivergencecs*eZdZdZejjdffdd ZZS) KLDivergencea@Computes Kullback-Leibler divergence loss between `y_true` and `y_pred`. `loss = y_true * log(y_true / y_pred)` See: https://en.wikipedia.org/wiki/Kullback%E2%80%93Leibler_divergence Standalone usage: >>> y_true = [[0, 1], [0, 0]] >>> y_pred = [[0.6, 0.4], [0.4, 0.6]] >>> # Using 'auto'/'sum_over_batch_size' reduction type. >>> kl = tf.keras.losses.KLDivergence() >>> kl(y_true, y_pred).numpy() 0.458 >>> # Calling with 'sample_weight'. >>> kl(y_true, y_pred, sample_weight=[0.8, 0.2]).numpy() 0.366 >>> # Using 'sum' reduction type. >>> kl = tf.keras.losses.KLDivergence( ... reduction=tf.keras.losses.Reduction.SUM) >>> kl(y_true, y_pred).numpy() 0.916 >>> # Using 'none' reduction type. >>> kl = tf.keras.losses.KLDivergence( ... reduction=tf.keras.losses.Reduction.NONE) >>> kl(y_true, y_pred).numpy() array([0.916, -3.08e-06], dtype=float32) Usage with the `compile()` API: ```python model.compile(optimizer='sgd', loss=tf.keras.losses.KLDivergence()) ``` kl_divergencecstjt||ddS)aInitializes `KLDivergence` instance. Args: reduction: Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `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`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. name: Optional name for the instance. Defaults to 'kl_divergence'. raN)rIrrrrMrrrPszKLDivergence.__init__rbrrrMrr(s'rzkeras.losses.Hubercs,eZdZdZdejjdffdd ZZS)HuberauComputes the Huber loss between `y_true` and `y_pred`. For each value x in `error = y_true - y_pred`: ``` loss = 0.5 * x^2 if |x| <= d loss = 0.5 * d^2 + d * (|x| - d) if |x| > d ``` where d is `delta`. See: https://en.wikipedia.org/wiki/Huber_loss Standalone usage: >>> y_true = [[0, 1], [0, 0]] >>> y_pred = [[0.6, 0.4], [0.4, 0.6]] >>> # Using 'auto'/'sum_over_batch_size' reduction type. >>> h = tf.keras.losses.Huber() >>> h(y_true, y_pred).numpy() 0.155 >>> # Calling with 'sample_weight'. >>> h(y_true, y_pred, sample_weight=[1, 0]).numpy() 0.09 >>> # Using 'sum' reduction type. >>> h = tf.keras.losses.Huber( ... reduction=tf.keras.losses.Reduction.SUM) >>> h(y_true, y_pred).numpy() 0.31 >>> # Using 'none' reduction type. >>> h = tf.keras.losses.Huber( ... reduction=tf.keras.losses.Reduction.NONE) >>> h(y_true, y_pred).numpy() array([0.18, 0.13], dtype=float32) Usage with the `compile()` API: ```python model.compile(optimizer='sgd', loss=tf.keras.losses.Huber()) ``` ? huber_losscstjt|||ddS)aInitializes `Huber` instance. Args: delta: A float, the point where the Huber loss function changes from a quadratic to linear. reduction: Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `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`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. name: Optional name for the instance. Defaults to 'huber_loss'. )rrdeltaN)rIrhuber)rrrrrMrrrszHuber.__init__rbrrrMrres ,rz keras.metrics.mean_squared_errorzkeras.metrics.msezkeras.metrics.MSEzkeras.losses.mean_squared_errorzkeras.losses.msezkeras.losses.MSEcCs0t|}t||j}tjtj||ddS)a#Computes the mean squared error between labels and predictions. After computing the squared distance between the inputs, the mean value over the last dimension is returned. `loss = mean(square(y_true - y_pred), axis=-1)` Standalone usage: >>> y_true = np.random.randint(0, 2, size=(2, 3)) >>> y_pred = np.random.random(size=(2, 3)) >>> loss = tf.keras.losses.mean_squared_error(y_true, y_pred) >>> assert loss.shape == (2,) >>> assert np.array_equal( ... loss.numpy(), np.mean(np.square(y_true - y_pred), axis=-1)) Args: y_true: Ground truth values. shape = `[batch_size, d0, .. dN]`. y_pred: The predicted values. shape = `[batch_size, d0, .. dN]`. Returns: Mean squared error values. shape = `[batch_size, d0, .. dN-1]`. rkrp)r$convert_to_tensorcastdtypermeanmathsquared_differencer.r/rrrr`s! r`Fc s8ddddfddfdd}t|tjsH||S|jd d }t|d krxtj||jd }ntj g|jd }d d||fD}|rdd|D}|d |d d kr|d dd |d <t j |t|d kd} t |} t| $tj| ||f|dWdS1s*0YdS)aApply a loss function on a per batch basis. Args: loss_fn: The loss function y_true: truth values (RaggedTensor) y_pred: predicted values (RaggedTensor) y_pred_extra_dim: whether y_pred has an additional dimension compared to y_true Returns: Loss-function result. A dense tensor if the output has a single dimension (per-batch loss value); a ragged tensor otherwise. cSstdd|DS)zReturns true if this RaggedTensor has the same row_lenghts across all ragged dimensions and thus can be converted to a dense tensor without loss of information. Args: rt: RaggedTensor. c Ss4g|],}ttjt|ttdgqS)rj)r$equalrreduce_variancerrfloatxconstant).0row_lensrrr s zH_ragged_tensor_apply_loss..rt_is_equiv_dense..)r$ reduce_allnested_row_lengths)rtrrrrt_is_equiv_denses z4_ragged_tensor_apply_loss..rt_is_equiv_densecSstdd|DS)Ncss&|]}t|tjr|n|VqdSN) isinstancer$ RaggedTensor to_tensorrrrrr szG_ragged_tensor_apply_loss.._convert_to_dense..)tuple)inputsrrr_convert_to_densesz4_ragged_tensor_apply_loss.._convert_to_densecsB|}|r&t|tjs&tj|}n|s>t|tjr>|}|S)zAdapt the result to ragged or dense tensor according to the expected output type. This is done so that all the return values of the map operation have the same type. )rr$r from_tensorr)r ragged_outputr)loss_fnrr _call_losss z-_ragged_tensor_apply_loss.._call_losscsH\}}t|tjr@t|fddfddSS)NcsSrrr)rrrrrr z=_ragged_tensor_apply_loss.._wrapper..cs Srrr)rrrrrrr)rr$rcond)rrrr/rrrr)rrr_wrappers z+_ragged_tensor_apply_loss.._wrapperrkr)shapercSsg|] }|jqSr)nested_row_splitsrrrrrrz-_ragged_tensor_apply_loss..cSsg|] }t|qSr)len)rslistrrrrrN)r)elemsr)rr$rrras_listrRaggedTensorSpecr TensorSpec functoolspartialr assert_splits_matchcontrol_dependenciesr map_fn) rr.r/y_pred_extra_dimrlshapespecnested_splits_listrdimsrassertion_listrrr_ragged_tensor_apply_losss&     rcCs tt||S)aImplements support for handling RaggedTensors. Args: y_true: RaggedTensor truth values. shape = `[batch_size, d0, .. dN]`. y_pred: RaggedTensor predicted values. shape = `[batch_size, d0, .. dN]`. Returns: Mean squared error values. shape = `[batch_size, d0, .. dN-1]`. When the number of dimensions of the batch feature vector [d0, .. dN] is greater than one the return value is a RaggedTensor. Otherwise a Dense tensor with dimensions [batch_size] is returned. )rr`rrrr_ragged_tensor_mse*srz!keras.metrics.mean_absolute_errorzkeras.metrics.maezkeras.metrics.MAEz keras.losses.mean_absolute_errorzkeras.losses.maezkeras.losses.MAEcCs0t|}t||j}tjt||ddS)aComputes the mean absolute error between labels and predictions. `loss = mean(abs(y_true - y_pred), axis=-1)` Standalone usage: >>> y_true = np.random.randint(0, 2, size=(2, 3)) >>> y_pred = np.random.random(size=(2, 3)) >>> loss = tf.keras.losses.mean_absolute_error(y_true, y_pred) >>> assert loss.shape == (2,) >>> assert np.array_equal( ... loss.numpy(), np.mean(np.abs(y_true - y_pred), axis=-1)) Args: y_true: Ground truth values. shape = `[batch_size, d0, .. dN]`. y_pred: The predicted values. shape = `[batch_size, d0, .. dN]`. Returns: Mean absolute error values. shape = `[batch_size, d0, .. dN-1]`. rkr)r$rrrrrabsrrrrrd;s rdcCs tt||S)z-RaggedTensor adapter for mean_absolute_error.)rrdrrrr_ragged_tensor_mae^srz,keras.metrics.mean_absolute_percentage_errorzkeras.metrics.mapezkeras.metrics.MAPEz+keras.losses.mean_absolute_percentage_errorzkeras.losses.mapezkeras.losses.MAPEcCsNt|}t||j}t||tt|t}dtj|ddS)a>Computes the mean absolute percentage error between `y_true` and `y_pred`. `loss = 100 * mean(abs((y_true - y_pred) / y_true), axis=-1)` Standalone usage: >>> y_true = np.random.random(size=(2, 3)) >>> y_true = np.maximum(y_true, 1e-7) # Prevent division by zero >>> y_pred = np.random.random(size=(2, 3)) >>> loss = tf.keras.losses.mean_absolute_percentage_error(y_true, y_pred) >>> assert loss.shape == (2,) >>> assert np.array_equal( ... loss.numpy(), ... 100. * np.mean(np.abs((y_true - y_pred) / y_true), axis=-1)) Args: y_true: Ground truth values. shape = `[batch_size, d0, .. dN]`. y_pred: The predicted values. shape = `[batch_size, d0, .. dN]`. Returns: Mean absolute percentage error values. shape = `[batch_size, d0, .. dN-1]`. gY@rkr) r$rrrrrmaximumepsilonr)r.r/diffrrrrfds ! rfcCs tt||S)zSupport RaggedTensors.)rrfrrrr_ragged_tensor_mapesrz,keras.metrics.mean_squared_logarithmic_errorzkeras.metrics.mslezkeras.metrics.MSLEz+keras.losses.mean_squared_logarithmic_errorzkeras.losses.mslezkeras.losses.MSLEcCsht|}t||j}tjt|td}tjt|td}tj tj ||ddS)apComputes the mean squared logarithmic error between `y_true` and `y_pred`. `loss = mean(square(log(y_true + 1) - log(y_pred + 1)), axis=-1)` Standalone usage: >>> y_true = np.random.randint(0, 2, size=(2, 3)) >>> y_pred = np.random.random(size=(2, 3)) >>> loss = tf.keras.losses.mean_squared_logarithmic_error(y_true, y_pred) >>> assert loss.shape == (2,) >>> y_true = np.maximum(y_true, 1e-7) >>> y_pred = np.maximum(y_pred, 1e-7) >>> assert np.allclose( ... loss.numpy(), ... np.mean( ... np.square(np.log(y_true + 1.) - np.log(y_pred + 1.)), axis=-1)) Args: y_true: Ground truth values. shape = `[batch_size, d0, .. dN]`. y_pred: The predicted values. shape = `[batch_size, d0, .. dN]`. Returns: Mean squared logarithmic error values. shape = `[batch_size, d0, .. dN-1]`. rrkr) r$rrrrlogrrrrr)r.r/ first_log second_logrrrrhs# rhcCs tt||S)z.Implements support for handling RaggedTensors.)rrhrrrr_ragged_tensor_mslesrcsTtd}td}tt||}fdd}tjj||fdd}|S)z!Converts binary labels into -1/1.rrcs ddS)Nrtrrrr.rr_convert_binary_labelssz5_maybe_convert_labels.._convert_binary_labelscsSrrrrrrrrz'_maybe_convert_labels..)r$rr logical_orr' smart_cond)r. are_zerosare_ones is_binaryrupdated_y_truerrr_maybe_convert_labelss   rzkeras.metrics.squared_hingezkeras.losses.squared_hingecCsDt|}t||j}t|}tjttd||dddS)acComputes the squared hinge loss between `y_true` and `y_pred`. `loss = mean(square(maximum(1 - y_true * y_pred, 0)), axis=-1)` Standalone usage: >>> y_true = np.random.choice([-1, 1], size=(2, 3)) >>> y_pred = np.random.random(size=(2, 3)) >>> loss = tf.keras.losses.squared_hinge(y_true, y_pred) >>> assert loss.shape == (2,) >>> assert np.array_equal( ... loss.numpy(), ... np.mean(np.square(np.maximum(1. - y_true * y_pred, 0.)), axis=-1)) Args: y_true: The ground truth values. `y_true` values are expected to be -1 or 1. If binary (0 or 1) labels are provided we will convert them to -1 or 1. shape = `[batch_size, d0, .. dN]`. y_pred: The predicted values. shape = `[batch_size, d0, .. dN]`. Returns: Squared hinge loss values. shape = `[batch_size, d0, .. dN-1]`. rrjrkr) r$rrrrrrsquarerrrrrrs  rzkeras.metrics.hingezkeras.losses.hingecCs>t|}t||j}t|}tjtd||dddS)a9Computes the hinge loss between `y_true` and `y_pred`. `loss = mean(maximum(1 - y_true * y_pred, 0), axis=-1)` Standalone usage: >>> y_true = np.random.choice([-1, 1], size=(2, 3)) >>> y_pred = np.random.random(size=(2, 3)) >>> loss = tf.keras.losses.hinge(y_true, y_pred) >>> assert loss.shape == (2,) >>> assert np.array_equal( ... loss.numpy(), ... np.mean(np.maximum(1. - y_true * y_pred, 0.), axis=-1)) Args: y_true: The ground truth values. `y_true` values are expected to be -1 or 1. If binary (0 or 1) labels are provided they will be converted to -1 or 1. shape = `[batch_size, d0, .. dN]`. y_pred: The predicted values. shape = `[batch_size, d0, .. dN]`. Returns: Hinge loss values. shape = `[batch_size, d0, .. dN-1]`. rrjrkr)r$rrrrrrrrrrrrs rzkeras.losses.categorical_hingecCsbt|}t||j}tj||dd}tjd||dd}td|j}t||d|S)a|Computes the categorical hinge loss between `y_true` and `y_pred`. `loss = maximum(neg - pos + 1, 0)` where `neg=maximum((1-y_true)*y_pred) and pos=sum(y_true*y_pred)` Standalone usage: >>> y_true = np.random.randint(0, 3, size=(2,)) >>> y_true = tf.keras.utils.to_categorical(y_true, num_classes=3) >>> y_pred = np.random.random(size=(2, 3)) >>> loss = tf.keras.losses.categorical_hinge(y_true, y_pred) >>> assert loss.shape == (2,) >>> pos = np.sum(y_true * y_pred, axis=-1) >>> neg = np.amax((1. - y_true) * y_pred, axis=-1) >>> assert np.array_equal(loss.numpy(), np.maximum(0., neg - pos + 1.)) Args: y_true: The ground truth values. `y_true` values are expected to be either `{-1, +1}` or `{0, 1}` (i.e. a one-hot-encoded tensor). y_pred: The predicted values. Returns: Categorical hinge loss values. rkrrrj)r$rrr reduce_sum reduce_maxr)r.r/posnegzerorrrrs  rzkeras.losses.huber)v1rc Cstj|td}tj|td}tj|td}t||}t|}tjd|jd}tjt ||k|t ||||t |ddS)aComputes Huber loss value. For each value x in `error = y_true - y_pred`: ``` loss = 0.5 * x^2 if |x| <= d loss = d * |x| - 0.5 * d^2 if |x| > d ``` where d is `delta`. See: https://en.wikipedia.org/wiki/Huber_loss Args: y_true: tensor of true targets. y_pred: tensor of predicted targets. delta: A float, the point where the Huber loss function changes from a quadratic to linear. Returns: Tensor with one scalar loss entry per sample. r?rkr) r$rrrsubtractrrrrwherer)r.r/rerror abs_errorhalfrrrr>s   rzkeras.losses.log_coshzkeras.losses.logcoshzkeras.metrics.log_coshzkeras.metrics.logcoshcCs6t|}t||j}dd}tj|||ddS)aLogarithm of the hyperbolic cosine of the prediction error. `log(cosh(x))` is approximately equal to `(x ** 2) / 2` for small `x` and to `abs(x) - log(2)` for large `x`. This means that 'logcosh' works mostly like the mean squared error, but will not be so strongly affected by the occasional wildly incorrect prediction. Standalone usage: >>> y_true = np.random.random(size=(2, 3)) >>> y_pred = np.random.random(size=(2, 3)) >>> loss = tf.keras.losses.logcosh(y_true, y_pred) >>> assert loss.shape == (2,) >>> x = y_pred - y_true >>> assert np.allclose( ... loss.numpy(), ... np.mean(x + np.log(np.exp(-2. * x) + 1.) - tf.math.log(2.), ... axis=-1), ... atol=1e-5) Args: y_true: Ground truth values. shape = `[batch_size, d0, .. dN]`. y_pred: The predicted values. shape = `[batch_size, d0, .. dN]`. Returns: Logcosh error values. shape = `[batch_size, d0, .. dN-1]`. cSs*|tjd|ttjd|jS)Ngrt)r$rsoftplusrrr)xrrr_logcoshs(zlog_cosh.._logcoshrkr)r$rrrrr)r.r/rrrrrds# rz&keras.metrics.categorical_crossentropyz%keras.losses.categorical_crossentropyrjrkcst|tr"td|dt|ttjtjjdfdd}tjj |fddt j ||dS) aComputes the categorical crossentropy loss. Standalone usage: >>> y_true = [[0, 1, 0], [0, 0, 1]] >>> y_pred = [[0.05, 0.95, 0], [0.1, 0.8, 0.1]] >>> loss = tf.keras.losses.categorical_crossentropy(y_true, y_pred) >>> assert loss.shape == (2,) >>> loss.numpy() array([0.0513, 2.303], dtype=float32) Args: y_true: Tensor of one-hot true targets. y_pred: Tensor of predicted targets. from_logits: Whether `y_pred` is expected to be a logits tensor. By default, we assume that `y_pred` encodes a probability distribution. label_smoothing: Float in [0, 1]. If > `0` then smooth the labels. For example, if `0.1`, use `0.1 / num_classes` for non-target labels and `0.9 + 0.1 / num_classes` for target labels. axis: Defaults to -1. The dimension along which the entropy is computed. Returns: Categorical crossentropy loss value. z-`axis` must be of type `int`. Received: axis=z of type rcs,ttdj}d|S)Nrkr)r$rrr) num_classesror/r.rr_smooth_labelss z0categorical_crossentropy.._smooth_labelscsSrrrrrrrrz*categorical_crossentropy..)rnrp) rboolr@typer$rrrr'rrrzr.r/rnrorprrrrrzs$!  rzcCstjt|||d}t|||S)aImplements support for handling RaggedTensors. Args: y_true: Tensor of one-hot true targets. y_pred: Tensor of predicted targets. from_logits: Whether `y_pred` is expected to be a logits tensor. By default, we assume that `y_pred` encodes a probability distribution. label_smoothing: Float in [0, 1]. If > `0` then smooth the labels. For example, if `0.1`, use `0.1 / num_classes` for non-target labels and `0.9 + 0.1 / num_classes` for target labels. axis: The axis along which to compute crossentropy (the features axis). Defaults to -1. Returns: Categorical crossentropy loss value. Expected shape: (batch, sequence_len, n_classes) with sequence_len being variable per batch. Return shape: (batch, sequence_len). When used by CategoricalCrossentropy() with the default reduction (SUM_OVER_BATCH_SIZE), the reduction averages the loss over the number of elements independent of the batch. E.g. if the RaggedTensor has 2 batches with [2, 1] values respectively the resulting loss is the sum of the individual loss values divided by 3. rnrorp)rrrzrr.r/rnrorprJrrr'_ragged_tensor_categorical_crossentropysrz-keras.metrics.sparse_categorical_crossentropyz,keras.losses.sparse_categorical_crossentropycCstj|||||dS)aComputes the sparse categorical crossentropy loss. Standalone usage: >>> y_true = [1, 2] >>> y_pred = [[0.05, 0.95, 0], [0.1, 0.8, 0.1]] >>> loss = tf.keras.losses.sparse_categorical_crossentropy(y_true, y_pred) >>> assert loss.shape == (2,) >>> loss.numpy() array([0.0513, 2.303], dtype=float32) >>> y_true = [[[ 0, 2], ... [-1, -1]], ... [[ 0, 2], ... [-1, -1]]] >>> y_pred = [[[[1.0, 0.0, 0.0], [0.0, 0.0, 1.0]], ... [[0.2, 0.5, 0.3], [0.0, 1.0, 0.0]]], ... [[[1.0, 0.0, 0.0], [0.0, 0.5, 0.5]], ... [[0.2, 0.5, 0.3], [0.0, 1.0, 0.0]]]] >>> loss = tf.keras.losses.sparse_categorical_crossentropy( ... y_true, y_pred, ignore_class=-1) >>> loss.numpy() array([[[2.3841855e-07, 2.3841855e-07], [0.0000000e+00, 0.0000000e+00]], [[2.3841855e-07, 6.9314730e-01], [0.0000000e+00, 0.0000000e+00]]], dtype=float32) Args: y_true: Ground truth values. y_pred: The predicted values. from_logits: Whether `y_pred` is expected to be a logits tensor. By default, we assume that `y_pred` encodes a probability distribution. axis: Defaults to -1. The dimension along which the entropy is computed. ignore_class: Optional integer. The ID of a class to be ignored during loss computation. This is useful, for example, in segmentation problems featuring a "void" class (commonly -1 or 255) in segmentation maps. By default (`ignore_class=None`), all classes are considered. Returns: Sparse categorical crossentropy loss value. rnr}rp)rr|)r.r/rnrpr}rrrr|s2r|cCs"tjt|||d}t|||ddS)a%Implements support for handling RaggedTensors. Expected y_pred shape: (batch, sequence_len, n_classes) with sequence_len being variable per batch. Return shape: (batch, sequence_len). When used by SparseCategoricalCrossentropy() with the default reduction (SUM_OVER_BATCH_SIZE), the reduction averages the loss over the number of elements independent of the batch. E.g. if the RaggedTensor has 2 batches with [2, 1] values respectively, the resulting loss is the sum of the individual loss values divided by 3. rT)r)rrr|r)r.r/rnrpr}rJrrr._ragged_tensor_sparse_categorical_crossentropy-srz!keras.metrics.binary_crossentropyz keras.losses.binary_crossentropycsjt|}t|jtj|jdfdd}tjj|fddtjtj||d|dS)aComputes the binary crossentropy loss. Standalone usage: >>> y_true = [[0, 1], [0, 0]] >>> y_pred = [[0.6, 0.4], [0.4, 0.6]] >>> loss = tf.keras.losses.binary_crossentropy(y_true, y_pred) >>> assert loss.shape == (2,) >>> loss.numpy() array([0.916 , 0.714], dtype=float32) Args: y_true: Ground truth values. shape = `[batch_size, d0, .. dN]`. y_pred: The predicted values. shape = `[batch_size, d0, .. dN]`. from_logits: Whether `y_pred` is expected to be a logits tensor. By default, we assume that `y_pred` encodes a probability distribution. label_smoothing: Float in [0, 1]. If > `0` then smooth the labels by squeezing them towards 0.5 That is, using `1. - 0.5 * label_smoothing` for the target class and `0.5 * label_smoothing` for the non-target class. axis: The axis along which the mean is computed. Defaults to -1. Returns: Binary crossentropy loss value. shape = `[batch_size, d0, .. dN-1]`. rcsddSNrrrrror.rrrjsz+binary_crossentropy.._smooth_labelscsSrrrrrrrnrz%binary_crossentropy..)rnr) r$rrrr'rrrrlrrrrrlFs rlcCstjt|||d}t|||S)aImplements support for handling RaggedTensors. Args: y_true: Tensor of one-hot true targets. y_pred: Tensor of predicted targets. from_logits: Whether `y_pred` is expected to be a logits tensor. By default, we assume that `y_pred` encodes a probability distribution. label_smoothing: Float in [0, 1]. If > `0` then smooth the labels. For example, if `0.1`, use `0.1 / num_classes` for non-target labels and `0.9 + 0.1 / num_classes` for target labels. axis: Axis along which to compute crossentropy. Returns: Binary crossentropy loss value. Expected shape: (batch, sequence_len) with sequence_len being variable per batch. Return shape: (batch,); returns the per batch mean of the loss values. When used by BinaryCrossentropy() with the default reduction (SUM_OVER_BATCH_SIZE), the reduction averages the per batch losses over the number of batches. r)rrrlrrrrr"_ragged_tensor_binary_crossentropywsrz'keras.metrics.binary_focal_crossentropyz&keras.losses.binary_focal_crossentropyrsrtc spt|}t|jtj|jdfdd}tjj|fddtjtj|||||d|dS)aComputes the binary focal crossentropy loss. According to [Lin et al., 2018](https://arxiv.org/pdf/1708.02002.pdf), it helps to apply a focal factor to down-weight easy examples and focus more on hard examples. By default, the focal tensor is computed as follows: `focal_factor = (1 - output)**gamma` for class 1 `focal_factor = output**gamma` for class 0 where `gamma` is a focusing parameter. When `gamma` = 0, there is no focal effect on the binary crossentropy loss. If `apply_class_balancing == True`, this function also takes into account a weight balancing factor for the binary classes 0 and 1 as follows: `weight = alpha` for class 1 (`target == 1`) `weight = 1 - alpha` for class 0 where `alpha` is a float in the range of `[0, 1]`. Standalone usage: >>> y_true = [[0, 1], [0, 0]] >>> y_pred = [[0.6, 0.4], [0.4, 0.6]] >>> loss = tf.keras.losses.binary_focal_crossentropy(y_true, y_pred, ... gamma=2) >>> assert loss.shape == (2,) >>> loss.numpy() array([0.330, 0.206], dtype=float32) Args: y_true: Ground truth values, of shape `(batch_size, d0, .. dN)`. y_pred: The predicted values, of shape `(batch_size, d0, .. dN)`. apply_class_balancing: A bool, whether to apply weight balancing on the binary classes 0 and 1. alpha: A weight balancing factor for class 1, default is `0.25` as mentioned in the reference. The weight for class 0 is `1.0 - alpha`. gamma: A focusing parameter, default is `2.0` as mentioned in the reference. from_logits: Whether `y_pred` is expected to be a logits tensor. By default, we assume that `y_pred` encodes a probability distribution. label_smoothing: Float in `[0, 1]`. If higher than 0 then smooth the labels by squeezing them towards `0.5`, i.e., using `1. - 0.5 * label_smoothing` for the target class and `0.5 * label_smoothing` for the non-target class. axis: The axis along which the mean is computed. Defaults to `-1`. Returns: Binary focal crossentropy loss value. shape = `[batch_size, d0, .. dN-1]`. rcsddSrrrrrrrsz1binary_focal_crossentropy.._smooth_labelscsSrrrrrrrrz+binary_focal_crossentropy..)targetoutputrvrwrxrnr) r$rrrr'rrrru) r.r/rvrwrxrnrorprrrrrus$? ruc Cs$tjt||||||d}t|||S)apImplements support for handling RaggedTensors. Expected shape: `(batch, sequence_len)` with sequence_len being variable per batch. Return shape: `(batch,)`; returns the per batch mean of the loss values. When used by BinaryFocalCrossentropy() with the default reduction (SUM_OVER_BATCH_SIZE), the reduction averages the per batch losses over the number of batches. Args: y_true: Tensor of one-hot true targets. y_pred: Tensor of predicted targets. apply_class_balancing: A bool, whether to apply weight balancing on the binary classes 0 and 1. alpha: A weight balancing factor for class 1, default is `0.25` as mentioned in the reference [Lin et al., 2018]( https://arxiv.org/pdf/1708.02002.pdf). The weight for class 0 is `1.0 - alpha`. gamma: A focusing parameter, default is `2.0` as mentioned in the reference. from_logits: Whether `y_pred` is expected to be a logits tensor. By default, we assume that `y_pred` encodes a probability distribution. label_smoothing: Float in `[0, 1]`. If > `0` then smooth the labels. For example, if `0.1`, use `0.1 / num_classes` for non-target labels and `0.9 + 0.1 / num_classes` for target labels. axis: Axis along which to compute crossentropy. Returns: Binary focal crossentropy loss value. )rvrwrxrnrorp)rrrur) r.r/rvrwrxrnrorprJrrr(_ragged_tensor_binary_focal_crossentropys* rzkeras.metrics.kl_divergencez)keras.metrics.kullback_leibler_divergencezkeras.metrics.kldzkeras.metrics.KLDzkeras.losses.kl_divergencez(keras.losses.kullback_leibler_divergencezkeras.losses.kldzkeras.losses.KLDcCsZt|}t||j}t|td}t|td}tj|tj ||ddS)atComputes Kullback-Leibler divergence loss between `y_true` and `y_pred`. `loss = y_true * log(y_true / y_pred)` See: https://en.wikipedia.org/wiki/Kullback%E2%80%93Leibler_divergence Standalone usage: >>> y_true = np.random.randint(0, 2, size=(2, 3)).astype(np.float64) >>> y_pred = np.random.random(size=(2, 3)) >>> loss = tf.keras.losses.kullback_leibler_divergence(y_true, y_pred) >>> assert loss.shape == (2,) >>> y_true = tf.keras.backend.clip(y_true, 1e-7, 1) >>> y_pred = tf.keras.backend.clip(y_pred, 1e-7, 1) >>> assert np.array_equal( ... loss.numpy(), np.sum(y_true * np.log(y_true / y_pred), axis=-1)) Args: y_true: Tensor of true targets. y_pred: Tensor of predicted targets. Returns: A `Tensor` with loss. Raises: TypeError: If `y_true` cannot be cast to the `y_pred.dtype`. rrkr) r$rrrrcliprrrrrrrrr( s ' rzkeras.metrics.poissonzkeras.losses.poissoncCs>t|}t||j}tj||tj|tddS)aXComputes the Poisson loss between y_true and y_pred. The Poisson loss is the mean of the elements of the `Tensor` `y_pred - y_true * log(y_pred)`. Standalone usage: >>> y_true = np.random.randint(0, 2, size=(2, 3)) >>> y_pred = np.random.random(size=(2, 3)) >>> loss = tf.keras.losses.poisson(y_true, y_pred) >>> assert loss.shape == (2,) >>> y_pred = y_pred + 1e-7 >>> assert np.allclose( ... loss.numpy(), np.mean(y_pred - y_true * np.log(y_pred), axis=-1), ... atol=1e-5) Args: y_true: Ground truth values. shape = `[batch_size, d0, .. dN]`. y_pred: The predicted values. shape = `[batch_size, d0, .. dN]`. Returns: Poisson loss value. shape = `[batch_size, d0, .. dN-1]`. Raises: InvalidArgumentError: If `y_true` and `y_pred` have incompatible shapes. rkr) r$rrrrrrrrrrrrrV s  rkeras.losses.cosine_similarity)zkeras.metrics.cosine_proximityzkeras.metrics.cosinezkeras.losses.cosine_proximityzkeras.losses.cosinercCs4tjj||d}tjj||d}tj|||d S)aIComputes the cosine similarity between labels and predictions. Note that it is a number between -1 and 1. When it is a negative number between -1 and 0, 0 indicates orthogonality and values closer to -1 indicate greater similarity. The values closer to 1 indicate greater dissimilarity. This makes it usable as a loss function in a setting where you try to maximize the proximity between predictions and targets. If either `y_true` or `y_pred` is a zero vector, cosine similarity will be 0 regardless of the proximity between predictions and targets. `loss = -sum(l2_norm(y_true) * l2_norm(y_pred))` Standalone usage: >>> y_true = [[0., 1.], [1., 1.], [1., 1.]] >>> y_pred = [[1., 0.], [1., 1.], [-1., -1.]] >>> loss = tf.keras.losses.cosine_similarity(y_true, y_pred, axis=1) >>> loss.numpy() array([-0., -0.999, 0.999], dtype=float32) Args: y_true: Tensor of true targets. y_pred: Tensor of predicted targets. axis: Axis along which to determine similarity. Returns: Cosine similarity tensor. r)r$linalg l2_normalizer)r.r/rprrrcosine_similarityz s)rzkeras.losses.CosineSimilaritycs,eZdZdZdejjdffdd ZZS)CosineSimilaritya Computes the cosine similarity between labels and predictions. Note that it is a number between -1 and 1. When it is a negative number between -1 and 0, 0 indicates orthogonality and values closer to -1 indicate greater similarity. The values closer to 1 indicate greater dissimilarity. This makes it usable as a loss function in a setting where you try to maximize the proximity between predictions and targets. If either `y_true` or `y_pred` is a zero vector, cosine similarity will be 0 regardless of the proximity between predictions and targets. `loss = -sum(l2_norm(y_true) * l2_norm(y_pred))` Standalone usage: >>> y_true = [[0., 1.], [1., 1.]] >>> y_pred = [[1., 0.], [1., 1.]] >>> # Using 'auto'/'sum_over_batch_size' reduction type. >>> cosine_loss = tf.keras.losses.CosineSimilarity(axis=1) >>> # 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]] >>> # loss = mean(sum(l2_norm(y_true) . l2_norm(y_pred), axis=1)) >>> # = -((0. + 0.) + (0.5 + 0.5)) / 2 >>> cosine_loss(y_true, y_pred).numpy() -0.5 >>> # Calling with 'sample_weight'. >>> cosine_loss(y_true, y_pred, sample_weight=[0.8, 0.2]).numpy() -0.0999 >>> # Using 'sum' reduction type. >>> cosine_loss = tf.keras.losses.CosineSimilarity(axis=1, ... reduction=tf.keras.losses.Reduction.SUM) >>> cosine_loss(y_true, y_pred).numpy() -0.999 >>> # Using 'none' reduction type. >>> cosine_loss = tf.keras.losses.CosineSimilarity(axis=1, ... reduction=tf.keras.losses.Reduction.NONE) >>> cosine_loss(y_true, y_pred).numpy() array([-0., -0.999], dtype=float32) Usage with the `compile()` API: ```python model.compile(optimizer='sgd', loss=tf.keras.losses.CosineSimilarity(axis=1)) ``` Args: axis: The axis along which the cosine similarity is computed (the features axis). Defaults to -1. reduction: Type of `tf.keras.losses.Reduction` to apply to loss. Default value is `AUTO`. `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`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial]( https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. name: Optional name for the instance. rkrcstjt|||ddS)N)rrrp)rIrr)rrprrrMrrr szCosineSimilarity.__init__rbrrrMrr s BrcCs>t|tp8t|tr|jtkp8t|dr2|jdkp8|dk}|S)Nrrz)rryrHrJrzhasattrr)lossresultrrris_categorical_crossentropy s     r zkeras.losses.serializecCst|S)zSerializes loss function or `Loss` instance. Args: loss: A Keras `Loss` instance or a loss function. Returns: Loss configuration dictionary. r)rrrr serialize s r zkeras.losses.deserializecCst|t|ddS)aVDeserializes a serialized loss class/function instance. Args: name: Loss configuration. custom_objects: Optional dictionary mapping names (strings) to custom objects (classes and functions) to be considered during deserialization. Returns: A Keras `Loss` instance or a loss function. z loss function)module_objectscustom_objectsprintable_module_name)rglobals)rr rrr deserialize s rzkeras.losses.getcCsV|dur dSt|tr&t|}t|St|tr8t|St|rD|Std|dS)aRetrieves a Keras loss as a `function`/`Loss` class instance. The `identifier` may be the string name of a loss function or `Loss` class. >>> loss = tf.keras.losses.get("categorical_crossentropy") >>> type(loss) >>> loss = tf.keras.losses.get("CategoricalCrossentropy") >>> type(loss) You can also specify `config` of the loss to this function by passing dict containing `class_name` and `config` as an identifier. Also note that the `class_name` must map to a `Loss` class >>> identifier = {"class_name": "CategoricalCrossentropy", ... "config": {"from_logits": True}} >>> loss = tf.keras.losses.get(identifier) >>> type(loss) Args: identifier: A loss identifier. One of None or string name of a loss function/class or loss configuration dictionary or a loss function or a loss class instance. Returns: A Keras loss as a `function`/ `Loss` class instance. Raises: ValueError: If `identifier` cannot be interpreted. Nz.Could not interpret loss function identifier: )rstrrrVcallabler@) identifierrrrr\3 s"  r\int32)F)r)Frjrk)Frjrk)FrkN)FrkN)Frjrk)Frjrk)FrsrtFrjrk)FrsrtFrjrk)rk)N)brCrErtensorflow.compat.v2compatv2r$kerasrZkeras.saving.experimentalr keras.utilsrrrkeras.utils.generic_utilsrr tensorflow.python.ops.raggedr r tensorflow.python.utilr tensorflow.python.util.tf_exportr tensorflow.tools.docsrrrHr_rcrergrirrryr{r~rrrrrrr'add_dispatch_supportr`rdispatch_for_typesrrrdrrfrrhrrrrrrrrzrr|rrlrrurrrrrbceBCEmseMSEmaeMAEmapeMAPEmsleMSLEkldKLDkullback_leibler_divergencelogcoshrr r rr\rr3sparse_softmax_cross_entropyLABEL_DTYPES_FOR_LOSSESrrrrs            :N;=E@l.XW;=;8;<E  Y        #     ! $ '4  &6  -  #R  5  # " #N    0