2VhddlmZddlmZddlmZedGddZeddgGd d eZed d gGd deZeddgGddeZeddgGddeZ y))backend)ops) keras_exportzkeras.constraints.Constraintc,eZdZdZdZdZedZy) 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 Q/home/dcms/DCMS/lib/python3.12/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$}V}rN)__name__ __module__ __qualname____doc__rr classmethodrr rr rrs%2  rrzkeras.constraints.MaxNormzkeras.constraints.max_normc$eZdZdZddZdZdZy)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)`. c ||_||_yN max_valueaxis)r r!r"s r __init__zMaxNorm.__init__is" rc8tj|}tjtjtj ||j d}tj|d|j}||tj|zz zS)NTr"keepdimsr) rconvert_to_tensorrsqrtsumsquarer"clipr!epsilonr r normsdesireds r rzMaxNorm.__call__msk  % %a (ATYYNO((5!T^^4Gw0589::rc4|j|jdS)Nr r rs r rzMaxNorm.get_configss!^^TYY??rN)rrrrrr#rrr rr rrPs.; @rrzkeras.constraints.NonNegzkeras.constraints.non_negceZdZdZdZy)NonNegz*Constrains the weights to be non-negative.ctj|}|tjtj|d|j zS)N)dtype)rr'rcast greater_equalr7r s r rzNonNeg.__call__{s9  % %a (388C--a5QWWEEErN)rrrrrr rr r4r4ws 4Frr4zkeras.constraints.UnitNormzkeras.constraints.unit_normc$eZdZdZddZdZdZy)UnitNormaConstrains the weights incident to each hidden unit to have unit norm. Args: axis: integer, axis along which to calculate weight norms. For instance, in a `Dense` layer the weight matrix has shape `(input_dim, output_dim)`, set `axis` to `0` to constrain each weight vector of length `(input_dim,)`. In a `Conv2D` layer with `data_format="channels_last"`, the weight tensor has shape `(rows, cols, input_depth, output_depth)`, set `axis` to `[0, 1, 2]` to constrain the weights of each filter tensor of size `(rows, cols, input_depth)`. c||_yrr")r r"s r r#zUnitNorm.__init__s  rc tj|}|tjtjtj tj ||jdzz S)NTr%)rr'r,rr(r)r*r"r s r rzUnitNorm.__call__sT  % %a ( OO hhswwszz!}499tLM N  rcd|jiS)Nr"r=rs r rzUnitNorm.get_configs ""rN)rr2r rr r;r;s  #rr;zkeras.constraints.MinMaxNormzkeras.constraints.min_max_normc$eZdZdZddZdZdZy) 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)`. c<||_||_||_||_yr min_valuer!rater")r rDr!rEr"s r r#zMinMaxNorm.__init__s""  rctj|}tjtjtj ||j d}|jtj||j|jzd|jz |zz}||tj|zz zS)NTr%) rr'rr(r)r*r"rEr+rDr!r,r-s r rzMinMaxNorm.__call__s  % %a (ATYYNO IIG G499}% & Gw0589::rc`|j|j|j|jdS)NrCrCrs r rzMinMaxNorm.get_configs(IIII   rN)r6?rIrr2r rr rArAs8 ; rrAN) keras.srcrrkeras.src.api_exportrrrr4r;rAr rr rLs-,-FF.FR*,HIJ#@j#@K#@L)+FGHFZFIF+-JKL#z#M#>#%EF2 2 2 r