o 2h@sddlmZddlmZddlmZedGdddZeddgGd d d eZed d gGd ddeZeddgGdddeZeddgGdddeZ dS))backend)ops) keras_exportzkeras.constraints.Constraintc@s,eZdZdZddZddZeddZdS) 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()) cCs|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). selfwrr\/var/www/html/chatgem/venv/lib/python3.10/site-packages/keras/src/constraints/constraints.py__call__!s 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. rrrrr get_config0s zConstraint.get_configcCs|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. Nrr)clsconfigrrr from_config;szConstraint.from_configN)__name__ __module__ __qualname____doc__r r classmethodrrrrr rs  rzkeras.constraints.MaxNormzkeras.constraints.max_normc@s*eZdZdZd ddZddZdd Zd S) 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)`. rcCs||_||_dSN max_valueaxis)rrrrrr __init__is zMaxNorm.__init__cCsLt|}ttjt||jdd}t|d|j}||t |S)NTrkeepdimsr) rconvert_to_tensorrsqrtsumsquarercliprepsilonrr normsdesiredrrr r ms zMaxNorm.__call__cCs|j|jdS)Nrrr rrr r sszMaxNorm.get_configN)rrrrrrrr r rrrr rPs   rzkeras.constraints.NonNegzkeras.constraints.non_negc@seZdZdZddZdS)NonNegz*Constrains the weights to be non-negative.cCs&t|}|tjt|d|jdS)N)dtype)rrrcast greater_equalr+rrrr r {s zNonNeg.__call__N)rrrrr rrrr r)ws r)zkeras.constraints.UnitNormzkeras.constraints.unit_normc@s*eZdZdZd ddZddZddZd S) 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)`. rcCs ||_dSrr)rrrrr r zUnitNorm.__init__c Cs4t|}|tttjt||jddS)NTr)rrr$rr r!r"rrrrr r s zUnitNorm.__call__cCs d|jiS)Nrr/r rrr r r0zUnitNorm.get_configN)rr(rrrr r.s   r.zkeras.constraints.MinMaxNormzkeras.constraints.min_max_normc@s*eZdZdZd ddZddZd d Zd S) MinMaxNormaMinMaxNorm weight constraint. Constrains the weights incident to each hidden unit to have the norm between a lower bound and an upper bound. Args: min_value: the minimum norm for the incoming weights. max_value: the maximum norm for the incoming weights. rate: rate for enforcing the constraint: weights will be rescaled to yield `(1 - rate) * norm + rate * norm.clip(min_value, max_value)`. Effectively, this means that rate=1.0 stands for strict enforcement of the constraint, while rate<1.0 means that weights will be rescaled at each step to slowly move towards a value inside the desired interval. axis: integer, axis along which to calculate weight norms. For instance, in a `Dense` layer the weight matrix has shape `(input_dim, output_dim)`, set `axis` to `0` to constrain each weight vector of length `(input_dim,)`. In a `Conv2D` layer with `data_format="channels_last"`, the weight tensor has shape `(rows, cols, input_depth, output_depth)`, set `axis` to `[0, 1, 2]` to constrain the weights of each filter tensor of size `(rows, cols, input_depth)`. r*?rcCs||_||_||_||_dSr min_valuerrater)rr4rr5rrrr rs zMinMaxNorm.__init__cCsbt|}ttjt||jdd}|jt||j |j d|j|}||t |S)NTr) rrrr r!r"rr5r#r4rr$r%rrr r s  zMinMaxNorm.__call__cCs|j|j|j|jdS)Nr3r3r rrr r s zMinMaxNorm.get_configN)r*r2r2rr(rrrr r1s   r1N) keras.srcrrkeras.src.api_exportrrrr)r.r1rrrr s   I &