&VfnddlmZddlmZddlmZedGddZeddgGd d eZed d gGd deZeddgGddeZeddgGddeZ dS))backend)ops) keras_exportzkeras.constraints.Constraintc4eZdZdZdZdZedZdS) ConstraintaGBase 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(keras.constraints.Constraint): ... ... def __call__(self, w): ... return w * ops.cast(ops.greater_equal(w, 0.), dtype=w.dtype) >>> weight = ops.convert_to_tensor((-1.0, 1.0)) >>> NonNegative()(weight) [0., 1.] Usage in a layer: >>> keras.layers.Dense(4, kernel_constraint=NonNegative()) c|S)akApplies 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). selfws ^/var/www/html/software/conda/lib/python3.11/site-packages/keras/src/constraints/constraints.py__call__zConstraint.__call__!s ciS)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 s r get_configzConstraint.get_config0s  rc|di|S)aInstantiates a weight constraint from a configuration dictionary. Example: ```python constraint = UnitNorm() config = constraint.get_config() constraint = UnitNorm.from_config(config) ``` Args: config: A Python dictionary, the output of `get_config()`. Returns: A `keras.constraints.Constraint` instance. r r )clsconfigs r from_configzConstraint.from_config;s$s}}V}}rN)__name__ __module__ __qualname____doc__rr classmethodrr rr rrsW2      [rrzkeras.constraints.MaxNormzkeras.constraints.max_normc&eZdZdZddZdZdZdS) MaxNormazMaxNorm weight constraint. Constrains the weights incident to each hidden unit to have a norm less than or equal to a desired value. Also available via the shortcut function `keras.constraints.max_norm`. Args: max_value: the maximum norm value for the incoming weights. axis: integer, axis along which to calculate weight norms. For instance, in a `Dense` layer the weight matrix has shape `(input_dim, output_dim)`, set `axis` to `0` to constrain each weight vector of length `(input_dim,)`. In a `Conv2D` layer with `data_format="channels_last"`, the weight tensor has shape `(rows, cols, input_depth, output_depth)`, set `axis` to `[0, 1, 2]` to constrain the weights of each filter tensor of size `(rows, cols, input_depth)`. rc"||_||_dSN max_valueaxis)r r"r#s r __init__zMaxNorm.__init__is" rctj|}tjtjtj||jd}tj|d|j}||tj |zz zS)NTr#keepdimsr) rconvert_to_tensorrsqrtsumsquarer#clipr"epsilonr r normsdesireds r rzMaxNorm.__call__msn  %a ( (ATYNNNOO(5!T^44Gw00589::rc |j|jdS)Nr!r!rs r rzMaxNorm.get_configss!^TY???rN)rrrrrrr$rrr rr rrPsU.;;; @@@@@rrzkeras.constraints.NonNegzkeras.constraints.non_negceZdZdZdZdS)NonNegz*Constrains the weights to be non-negative.ctj|}|tjtj|d|jzS)N)dtype)rr(rcast greater_equalr7r s r rzNonNeg.__call__{s;  %a ( (38C-a55QWEEEEErN)rrrrrr rr r4r4ws.44FFFFFrr4zkeras.constraints.UnitNormzkeras.constraints.unit_normc&eZdZdZddZdZdZdS)UnitNormaConstrains the weights incident to each hidden unit to have 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)`. rc||_dSr r#)r r#s r r$zUnitNorm.__init__s  rc tj|}|tjtjtjtj||jdzz S)NTr&)rr(r-rr)r*r+r#r s r rzUnitNorm.__call__sX  %a ( ( O  hswsz!}}49tLLLMM N  rcd|jiS)Nr#r=rs r rzUnitNorm.get_configs ""rN)rr2r rr r;r;sP    #####rr;zkeras.constraints.MinMaxNormzkeras.constraints.min_max_normc&eZdZdZd dZdZdZdS) MinMaxNormaMinMaxNorm weight constraint. Constrains the weights incident to each hidden unit to have the norm between a lower bound and an upper bound. Args: min_value: the minimum norm for the incoming weights. max_value: the maximum norm for the incoming weights. rate: rate for enforcing the constraint: weights will be rescaled to yield `(1 - rate) * norm + rate * norm.clip(min_value, max_value)`. Effectively, this means that rate=1.0 stands for strict enforcement of the constraint, while rate<1.0 means that weights will be rescaled at each step to slowly move towards a value inside the desired interval. axis: integer, axis along which to calculate weight norms. For instance, in a `Dense` layer the weight matrix has shape `(input_dim, output_dim)`, set `axis` to `0` to constrain each weight vector of length `(input_dim,)`. In a `Conv2D` layer with `data_format="channels_last"`, the weight tensor has shape `(rows, cols, input_depth, output_depth)`, set `axis` to `[0, 1, 2]` to constrain the weights of each filter tensor of size `(rows, cols, input_depth)`. r6?rc>||_||_||_||_dSr  min_valuer"rater#)r rEr"rFr#s r r$zMinMaxNorm.__init__s"""  rcNtj|}tjtjtj||jd}|jtj||j |j zd|jz |zz}||tj |zz zS)NTr&) rr(rr)r*r+r#rFr,rEr"r-r.s r rzMinMaxNorm.__call__s  %a ( (ATYNNNOO IGG G49}% & Gw00589::rc8|j|j|j|jdS)NrDrDrs r rzMinMaxNorm.get_configs%II    rN)r6rBrBrr2r rr rArAsP8 ;;;     rrAN) keras.srcrrkeras.src.api_exportrrrr4r;rAr rr rLs------,--FFFFFFF.-FR*,HIJJ#@#@#@#@#@j#@#@KJ#@L)+FGHHFFFFFZFFIHF+-JKLL#####z##ML#>#%EF2 2 2 2 2 2 2 2 2 2 r