a Sic0@s@dZddlmmZddlmZddlmZddlm Z ddl m Z ddl m Z e dGd d d Ze d d Gd ddeZe ddGdddeZe ddGdddeZe ddGdddeZe ddGdddeZeZeZeZeZeZeZeZeZe dd d!Ze d"d(d#d$Ze d%d&d'ZdS))z@Constraints: functions that impose constraints on weight values.N)backend)deserialize_keras_objectserialize_keras_object) keras_export) doc_controlszkeras.constraints.Constraintc@s eZdZdZddZddZdS) ConstraintaoBase class for weight constraints. A `Constraint` instance works like a stateless function. Users who subclass this class should override the `__call__` method, which takes a single weight parameter and return a projected version of that parameter (e.g. normalized or clipped). Constraints can be used with various Keras layers via the `kernel_constraint` or `bias_constraint` arguments. Here's a simple example of a non-negative weight constraint: >>> class NonNegative(tf.keras.constraints.Constraint): ... ... def __call__(self, w): ... return w * tf.cast(tf.math.greater_equal(w, 0.), w.dtype) >>> weight = tf.constant((-1.0, 1.0)) >>> NonNegative()(weight) >>> tf.keras.layers.Dense(4, kernel_constraint=NonNegative()) cCs|S)agApplies the constraint to the input weight variable. By default, the inputs weight variable is not modified. Users should override this method to implement their own projection function. Args: w: Input weight variable. Returns: Projected variable (by default, returns unmodified inputs). selfwr r M/var/www/html/django/DPS/env/lib/python3.9/site-packages/keras/constraints.py__call__8s zConstraint.__call__cCsiS)aReturns a Python dict of the object config. A constraint config is a Python dictionary (JSON-serializable) that can be used to reinstantiate the same object. Returns: Python dict containing the configuration of the constraint object. r r r r r get_configGs zConstraint.get_configN)__name__ __module__ __qualname____doc__rrr r r r rsrzkeras.constraints.MaxNormzkeras.constraints.max_normc@s6eZdZdZd ddZejddZejdd Zd S) MaxNormaQMaxNorm weight constraint. Constrains the weights incident to each hidden unit to have a norm less than or equal to a desired value. Also available via the shortcut function `tf.keras.constraints.max_norm`. Args: max_value: the maximum norm value for the incoming weights. axis: integer, axis along which to calculate weight norms. For instance, in a `Dense` layer the weight matrix has shape `(input_dim, output_dim)`, set `axis` to `0` to constrain each weight vector of length `(input_dim,)`. In a `Conv2D` layer with `data_format="channels_last"`, the weight tensor has shape `(rows, cols, input_depth, output_depth)`, set `axis` to `[0, 1, 2]` to constrain the weights of each filter tensor of size `(rows, cols, input_depth)`. rcCs||_||_dSN max_valueaxis)r rrr r r __init__lszMaxNorm.__init__cCsBttjt||jdd}t|d|j}||t|S)NTrkeepdimsr) rsqrttf reduce_sumsquarercliprepsilonr r normsdesiredr r r rps zMaxNorm.__call__cCs|j|jdS)Nrrrr r r rxszMaxNorm.get_configN)rr rrrrrrdo_not_generate_docsrrr r r r rSs   rzkeras.constraints.NonNegzkeras.constraints.non_negc@seZdZdZddZdS)NonNegz}Constrains the weights to be non-negative. Also available via the shortcut function `tf.keras.constraints.non_neg`. cCs|tt|dtS)N)rcast greater_equalrfloatxr r r r rszNonNeg.__call__N)rrrrrr r r r r)}sr)zkeras.constraints.UnitNormzkeras.constraints.unit_normc@s6eZdZdZd ddZejddZejddZd S) UnitNormaConstrains the weights incident to each hidden unit to have unit norm. Also available via the shortcut function `tf.keras.constraints.unit_norm`. Args: axis: integer, axis along which to calculate weight norms. For instance, in a `Dense` layer the weight matrix has shape `(input_dim, output_dim)`, set `axis` to `0` to constrain each weight vector of length `(input_dim,)`. In a `Conv2D` layer with `data_format="channels_last"`, the weight tensor has shape `(rows, cols, input_depth, output_depth)`, set `axis` to `[0, 1, 2]` to constrain the weights of each filter tensor of size `(rows, cols, input_depth)`. rcCs ||_dSrr)r rr r r rszUnitNorm.__init__c Cs*|tttjt||jddS)NTr)rr#rrr r!rr r r r rszUnitNorm.__call__cCs d|jiS)Nrr/rr r r rszUnitNorm.get_configN)rr'r r r r r.s   r.zkeras.constraints.MinMaxNormzkeras.constraints.min_max_normc@s6eZdZdZd ddZejddZejd d Zd S) MinMaxNorma(MinMaxNorm weight constraint. Constrains the weights incident to each hidden unit to have the norm between a lower bound and an upper bound. Also available via the shortcut function `tf.keras.constraints.min_max_norm`. Args: min_value: the minimum norm for the incoming weights. max_value: the maximum norm for the incoming weights. rate: rate for enforcing the constraint: weights will be rescaled to yield `(1 - rate) * norm + rate * norm.clip(min_value, max_value)`. Effectively, this means that rate=1.0 stands for strict enforcement of the constraint, while rate<1.0 means that weights will be rescaled at each step to slowly move towards a value inside the desired interval. axis: integer, axis along which to calculate weight norms. For instance, in a `Dense` layer the weight matrix has shape `(input_dim, output_dim)`, set `axis` to `0` to constrain each weight vector of length `(input_dim,)`. In a `Conv2D` layer with `data_format="channels_last"`, the weight tensor has shape `(rows, cols, input_depth, output_depth)`, set `axis` to `[0, 1, 2]` to constrain the weights of each filter tensor of size `(rows, cols, input_depth)`. r*?rcCs||_||_||_||_dSr min_valuerrater)r r3rr4rr r r rszMinMaxNorm.__init__cCsXttjt||jdd}|jt||j|j d|j|}||t |S)NTr) rrrr r!rr4r"r3rr#r$r r r rs zMinMaxNorm.__call__cCs|j|j|j|jdS)Nr2r2rr r r rs zMinMaxNorm.get_configN)r*r1r1rr'r r r r r0s   r0z"keras.constraints.RadialConstraintz#keras.constraints.radial_constraintc@s&eZdZdZejddZddZdS)RadialConstraintaConstrains `Conv2D` kernel weights to be the same for each radius. Also available via the shortcut function `tf.keras.constraints.radial_constraint`. For example, the desired output for the following 4-by-4 kernel: ``` kernel = [[v_00, v_01, v_02, v_03], [v_10, v_11, v_12, v_13], [v_20, v_21, v_22, v_23], [v_30, v_31, v_32, v_33]] ``` is this:: ``` kernel = [[v_11, v_11, v_11, v_11], [v_11, v_33, v_33, v_11], [v_11, v_33, v_33, v_11], [v_11, v_11, v_11, v_11]] ``` This constraint can be applied to any `Conv2D` layer version, including `Conv2DTranspose` and `SeparableConv2D`, and with either `"channels_last"` or `"channels_first"` data format. The method assumes the weight tensor is of shape `(rows, cols, input_depth, output_depth)`. cCs|j}|jdus|jdkr(td||\}}}}t|||||f}t|jtjtj |dddd}ttjtj |dddd||||fS)NzGThe weight tensor must have rank 4. Received weight tensor with shape: r/r) shaperank ValueErrorrreshapemap_fn_kernel_constraintstackrunstack)r r w_shapeheightwidthchannelskernelsr r r r s"  zRadialConstraint.__call__c stjddgddggddtd}t|ddtttj|ddfddfd d}tttj|ddd dd d}fd d}fd d}tjj j ||||g| t ddggd\}}|S)zKRadially constraints a kernel with shape (height, width, channels).r5int32dtyperrboolcsddfS)Nr5r r kernelstartr r *z5RadialConstraint._kernel_constraint..cs,ddftjdjdS)Nr5)rrrG)rzerosrHr rJr r rM+scSstjdddS)NrrFrGrconstantr r r r rM0rNcSstjdddS)Nr5rFrGrPr r r r rM1rNcs t|Sr)rless)indexargs)rLr r rM3rNcs(|dtj|||fdfS)Nr5)constant_values)rpad)iarrayrKpaddingrLr r body_fn5s z4RadialConstraint._kernel_constraint..body_fnN)shape_invariants) rrQr9r+switchrmathfloormodcompatv1 while_loop get_shape TensorShape)r rK kernel_shape kernel_newrSwhile_conditionr[_r rYr r> s,    z#RadialConstraint._kernel_constraintN)rrrrrr(rr>r r r r r6s r6zkeras.constraints.serializecCst|Srr) constraintr r r serializeQsrjzkeras.constraints.deserializecCst|t|ddS)Nri)module_objectscustom_objectsprintable_module_name)rglobals)configrlr r r deserializeVs rpzkeras.constraints.getcCs\|dur dSt|trt|St|tr>t|id}t|St|rJ|Std|dS)z&Retrieves a Keras constraint function.N) class_nameroz4Could not interpret constraint function identifier: ) isinstancedictrpstrcallabler;) identifierror r r get`s  rw)N)rtensorflow.compat.v2r`v2rkerasrkeras.utils.generic_utilsrr tensorflow.python.util.tf_exportrtensorflow.tools.docsrrrr)r.r0r6max_normnon_neg unit_norm min_max_normradial_constraintmaxnormnonnegunitnormrjrprwr r r r sD     4) $;Y