Author: Awais Farooq
-
KerasNLP Models
KerasNLP contains end-to-end implementations of popular model architectures. These models can be created in two ways: Below, we list all presets available in the library. For more detailed usage, browse the docstring for a particular class. For an in depth introduction to our API, see the getting started guide. Backbone presets The following preset names correspond…
-
Errors
FailedTrialError class Raise this error to mark a Trial as failed. When this error is raised in a Trial, the Tuner would not retry the Trial but directly mark it as “FAILED”. Example FatalError class A fatal error during search to terminate the program. It is used to terminate the KerasTuner program for errors that need users immediate attention. When this error is raised in…
-
KerasTuner HyperModels
The HyperModel base class makes the search space better encapsulated for sharing and reuse. A HyperModel subclass only needs to implement a build(self, hp) method, which creates a keras.Model using the hp argument to define the hyperparameters and returns the model instance. A simple code example is shown as follows. You can pass a HyperModel instance to the Tuner as the search space. There are also some built-in HyperModel subclasses (e.g. HyperResNet, HyperXception)…
-
KerasTuner Oracles
The Oracle class is the base class for all the search algorithms in KerasTuner. An Oracle object receives evaluation results for a model (from a Tuner class) and generates new hyperparameter values. The built-in Oracle classes are RandomSearchOracle, BayesianOptimizationOracle, and HyperbandOracle. You can also write your own tuning algorithm by subclassing the Oracle class.
-
The Tuner classes in KerasTuner
The base Tuner class is the class that manages the hyperparameter search process, including model creation, training, and evaluation. For each trial, a Tuner receives new hyperparameter values from an Oracle instance. After calling model.fit(…), it sends the evaluation results back to the Oracle instance and it retrieves the next set of hyperparameters to try. There are a few built-in Tuner subclasses available for widely-used tuning…
-
HyperParameters
HyperParameters class Container for both a hyperparameter space, and current values. A HyperParameters instance can be pass to HyperModel.build(hp) as an argument to build a model. To prevent the users from depending on inactive hyperparameter values, only active hyperparameters should have values in HyperParameters.values. Attributes Boolean method Choice between True and False. Arguments Returns The value of the hyperparameter, or None if…
-
Keras configuration utilities
version function clear_session function Resets all state generated by Keras. Keras manages a global state, which it uses to implement the Functional model-building API and to uniquify autogenerated layer names. If you are creating many models in a loop, this global state will consume an increasing amount of memory over time, and you may want to clear…
-
Python & NumPy utilities
set_random_seed function Sets all random seeds (Python, NumPy, and backend framework, e.g. TF). You can use this utility to make almost any Keras program fully deterministic. Some limitations apply in cases where network communications are involved (e.g. parameter server distribution), which creates additional sources of randomness, or when certain non-deterministic cuDNN ops are involved. Calling this…
-
Tensor utilities
get_source_inputs function Returns the list of input tensors necessary to compute tensor. Output will always be a list of tensors (potentially with 1 element). Arguments Returns List of input tensors. is_keras_tensor function Returns whether x is a Keras tensor. A “Keras tensor” is a symbolic tensor, such as a tensor that was created via Input(). A “symbolic tensor” can be understood as…
-
Structured data preprocessing utilities
FeatureSpace class One-stop utility for preprocessing and encoding structured data. Arguments Available feature types: Note that all features can be referred to by their string name, e.g. “integer_categorical”. When using the string name, the default argument values are used. Examples Basic usage with a dict of input data: Basic usage with tf.data: Basic usage with the Keras Functional…