B ӻd1@s dZddlZddlmZddlmZddlmZddlmZddl m Z dd Z d d Z e d Gd dde Ze dGdddeZe ddGdddeZe ddGdddeZe dd'ddZeZeZe ddd Ze d!d(d"d#Ze d$d%d&ZdS))zBuilt-in regularizers.N)backend)deserialize_keras_object)serialize_keras_object)math_ops) keras_exportcCsBt|ttfstd|t|s0t|r>td|dS)z>check penalty number availability, raise ValueError if failed.zVValue: {} is not a valid regularization penalty number, expected an int or float valuezsValue: {} is not a valid regularization penalty number, a positive/negative infinity or NaN is not a property valueN) isinstancefloatint ValueErrorformatmathisinfisnan)xrV/var/www/html/venv/lib/python3.7/site-packages/tensorflow/python/keras/regularizers.py_check_penalty_numbersrcCs|dkr |S|S)Nr)inputsdefaultrrr_none_to_default(srzkeras.regularizers.Regularizerc@s,eZdZdZddZeddZddZdS) RegularizeraRegularizer base class. Regularizers allow you to apply penalties on layer parameters or layer activity during optimization. These penalties are summed into the loss function that the network optimizes. Regularization penalties are applied on a per-layer basis. The exact API will depend on the layer, but many layers (e.g. `Dense`, `Conv1D`, `Conv2D` and `Conv3D`) have a unified API. These layers expose 3 keyword arguments: - `kernel_regularizer`: Regularizer to apply a penalty on the layer's kernel - `bias_regularizer`: Regularizer to apply a penalty on the layer's bias - `activity_regularizer`: Regularizer to apply a penalty on the layer's output All layers (including custom layers) expose `activity_regularizer` as a settable property, whether or not it is in the constructor arguments. The value returned by the `activity_regularizer` is divided by the input batch size so that the relative weighting between the weight regularizers and the activity regularizers does not change with the batch size. You can access a layer's regularization penalties by calling `layer.losses` after calling the layer on inputs. ## Example >>> layer = tf.keras.layers.Dense( ... 5, input_dim=5, ... kernel_initializer='ones', ... kernel_regularizer=tf.keras.regularizers.L1(0.01), ... activity_regularizer=tf.keras.regularizers.L2(0.01)) >>> tensor = tf.ones(shape=(5, 5)) * 2.0 >>> out = layer(tensor) >>> # The kernel regularization term is 0.25 >>> # The activity regularization term (after dividing by the batch size) is 5 >>> tf.math.reduce_sum(layer.losses) ## Available penalties ```python tf.keras.regularizers.L1(0.3) # L1 Regularization Penalty tf.keras.regularizers.L2(0.1) # L2 Regularization Penalty tf.keras.regularizers.L1L2(l1=0.01, l2=0.01) # L1 + L2 penalties ``` ## Directly calling a regularizer Compute a regularization loss on a tensor by directly calling a regularizer as if it is a one-argument function. E.g. >>> regularizer = tf.keras.regularizers.L2(2.) >>> tensor = tf.ones(shape=(5, 5)) >>> regularizer(tensor) ## Developing new regularizers Any function that takes in a weight matrix and returns a scalar tensor can be used as a regularizer, e.g.: >>> @tf.keras.utils.register_keras_serializable(package='Custom', name='l1') ... def l1_reg(weight_matrix): ... return 0.01 * tf.math.reduce_sum(tf.math.abs(weight_matrix)) ... >>> layer = tf.keras.layers.Dense(5, input_dim=5, ... kernel_initializer='ones', kernel_regularizer=l1_reg) >>> tensor = tf.ones(shape=(5, 5)) >>> out = layer(tensor) >>> layer.losses [] Alternatively, you can write your custom regularizers in an object-oriented way by extending this regularizer base class, e.g.: >>> @tf.keras.utils.register_keras_serializable(package='Custom', name='l2') ... class L2Regularizer(tf.keras.regularizers.Regularizer): ... def __init__(self, l2=0.): # pylint: disable=redefined-outer-name ... self.l2 = l2 ... ... def __call__(self, x): ... return self.l2 * tf.math.reduce_sum(tf.math.square(x)) ... ... def get_config(self): ... return {'l2': float(self.l2)} ... >>> layer = tf.keras.layers.Dense( ... 5, input_dim=5, kernel_initializer='ones', ... kernel_regularizer=L2Regularizer(l2=0.5)) >>> tensor = tf.ones(shape=(5, 5)) >>> out = layer(tensor) >>> layer.losses [] ### A note on serialization and deserialization: Registering the regularizers as serializable is optional if you are just training and executing models, exporting to and from SavedModels, or saving and loading weight checkpoints. Registration is required for Keras `model_to_estimator`, saving and loading models to HDF5 formats, Keras model cloning, some visualization utilities, and exporting models to and from JSON. If using this functionality, you must make sure any python process running your model has also defined and registered your custom regularizer. `tf.keras.utils.register_keras_serializable` is only available in TF 2.1 and beyond. In earlier versions of TensorFlow you must pass your custom regularizer to the `custom_objects` argument of methods that expect custom regularizers to be registered as serializable. cCsdS)z6Compute a regularization penalty from an input tensor.gr)selfrrrr__call__szRegularizer.__call__cCs |f|S)aCreates a regularizer from its config. This method is the reverse of `get_config`, capable of instantiating the same regularizer from the config dictionary. This method is used by Keras `model_to_estimator`, saving and loading models to HDF5 formats, Keras model cloning, some visualization utilities, and exporting models to and from JSON. Args: config: A Python dictionary, typically the output of get_config. Returns: A regularizer instance. r)clsconfigrrr from_configszRegularizer.from_configcCstt|ddS)aReturns the config of the regularizer. An regularizer config is a Python dictionary (serializable) containing all configuration parameters of the regularizer. The same regularizer can be reinstantiated later (without any saved state) from this configuration. This method is optional if you are just training and executing models, exporting to and from SavedModels, or using weight checkpoints. This method is required for Keras `model_to_estimator`, saving and loading models to HDF5 formats, Keras model cloning, some visualization utilities, and exporting models to and from JSON. Returns: Python dictionary. z does not implement get_config()N)NotImplementedErrorstr)rrrr get_configszRegularizer.get_configN)__name__ __module__ __qualname____doc__r classmethodrrrrrrr,sv rzkeras.regularizers.L1L2c@s*eZdZdZd ddZddZddZd S) L1L2aA regularizer that applies both L1 and L2 regularization penalties. The L1 regularization penalty is computed as: `loss = l1 * reduce_sum(abs(x))` The L2 regularization penalty is computed as `loss = l2 * reduce_sum(square(x))` L1L2 may be passed to a layer as a string identifier: >>> dense = tf.keras.layers.Dense(3, kernel_regularizer='l1_l2') In this case, the default values used are `l1=0.01` and `l2=0.01`. Attributes: l1: Float; L1 regularization factor. l2: Float; L2 regularization factor. cCsL|dkr dn|}|dkrdn|}t|t|t||_t||_dS)Ng)rrcast_to_floatxl1l2)rr'r(rrr__init__s  z L1L2.__init__cCsTtjd|jd}|jr0||jtt|7}|jrP||jtt|7}|S)Ng)dtype) rZconstantr*r'r reduce_sumabsr(square)rrZregularizationrrrrs z L1L2.__call__cCst|jt|jdS)N)r'r()rr'r()rrrrrszL1L2.get_configN)r%r%)rr r!r"r)rrrrrrr$s r$zkeras.regularizers.L1zkeras.regularizers.l1c@s*eZdZdZd ddZddZddZd S) L1avA regularizer that applies a L1 regularization penalty. The L1 regularization penalty is computed as: `loss = l1 * reduce_sum(abs(x))` L1 may be passed to a layer as a string identifier: >>> dense = tf.keras.layers.Dense(3, kernel_regularizer='l1') In this case, the default value used is `l1=0.01`. Attributes: l1: Float; L1 regularization factor. {Gz?cKsF|d|}|rtd|f|dkr*dn|}t|t||_dS)NlzArgument(s) not recognized: %sg{Gz?)pop TypeErrorrrr&r')rr'kwargsrrrr)s  z L1.__init__cCs|jtt|S)N)r'rr+r,)rrrrrrsz L1.__call__cCsdt|jiS)Nr')rr')rrrrrsz L1.get_configN)r/)rr r!r"r)rrrrrrr.s r.zkeras.regularizers.L2zkeras.regularizers.l2c@s*eZdZdZd ddZddZddZd S) L2ayA regularizer that applies a L2 regularization penalty. The L2 regularization penalty is computed as: `loss = l2 * reduce_sum(square(x))` L2 may be passed to a layer as a string identifier: >>> dense = tf.keras.layers.Dense(3, kernel_regularizer='l2') In this case, the default value used is `l2=0.01`. Attributes: l2: Float; L2 regularization factor. {Gz?cKsF|d|}|rtd|f|dkr*dn|}t|t||_dS)Nr0zArgument(s) not recognized: %sg{Gz?)r1r2rrr&r()rr(r3rrrr)1s  z L2.__init__cCs|jtt|S)N)r(rr+r-)rrrrrr;sz L2.__call__cCsdt|jiS)Nr()rr()rrrrr>sz L2.get_configN)r5)rr r!r"r)rrrrrrr4 s r4zkeras.regularizers.l1_l2{Gz?cCs t||dS)aCreate a regularizer that applies both L1 and L2 penalties. The L1 regularization penalty is computed as: `loss = l1 * reduce_sum(abs(x))` The L2 regularization penalty is computed as: `loss = l2 * reduce_sum(square(x))` Args: l1: Float; L1 regularization factor. l2: Float; L2 regularization factor. Returns: An L1L2 Regularizer with the given regularization factors. )r'r()r$)r'r(rrrl1_l2Bsr7zkeras.regularizers.serializecCst|S)N)r) regularizerrrr serialize[sr9zkeras.regularizers.deserializecCs&|dkrtdddSt|t|ddS)Nr7g{Gz?)r'r(r8)Zmodule_objectscustom_objectsZprintable_module_name)r$rglobals)rr:rrr deserialize`s r<zkeras.regularizers.getcCsR|dkr dSt|trt|St|tr4tt|St|r@|Std|dS)zs2      %,!!