:py:mod:`python.dgbpy.keras_classes`
====================================
.. py:module:: python.dgbpy.keras_classes
Module Contents
---------------
Classes
~~~~~~~
.. autoapisummary::
python.dgbpy.keras_classes.TrainingSequence
python.dgbpy.keras_classes.DataPredType
python.dgbpy.keras_classes.OutputType
python.dgbpy.keras_classes.DimType
python.dgbpy.keras_classes.UserModel
Attributes
~~~~~~~~~~
.. autoapisummary::
python.dgbpy.keras_classes.mlmodels
.. py:class:: TrainingSequence(trainbatch, forvalidation, model, exfilenm=None, batch_size=1, with_augmentation=True, tempnm=None)
Bases: :py:obj:`tensorflow.keras.utils.Sequence`
.. py:method:: __len__(self)
.. py:method:: set_chunk(self, ichunk)
.. py:method:: on_epoch_end(self)
.. py:method:: __getitem__(self, index)
.. py:method:: __data_generation(self, data_IDs_temp)
.. py:class:: DataPredType
Bases: :py:obj:`enum.Enum`
Generic enumeration.
Derive from this class to define new enumerations.
.. py:attribute:: Continuous
:annotation: = Continuous Data
.. py:attribute:: Classification
:annotation: = Classification Data
.. py:attribute:: Segmentation
:annotation: = Segmentation
.. py:attribute:: Any
:annotation: = Any
.. py:class:: OutputType
Bases: :py:obj:`enum.Enum`
Generic enumeration.
Derive from this class to define new enumerations.
.. py:attribute:: Pixel
:annotation: = 1
.. py:attribute:: Image
:annotation: = 2
.. py:attribute:: Any
:annotation: = 3
.. py:class:: DimType
Bases: :py:obj:`enum.Enum`
Generic enumeration.
Derive from this class to define new enumerations.
.. py:attribute:: D1
:annotation: = 1
.. py:attribute:: D2
:annotation: = 2
.. py:attribute:: D3
:annotation: = 3
.. py:attribute:: Any
:annotation: = 4
.. py:class:: UserModel
Bases: :py:obj:`abc.ABC`
Abstract base class for user defined Keras machine learning models
This module provides support for users to add their own machine learning
models to OpendTect.
It defines an abstract base class. Users derive there own model classes from this base
class and implement the _make_model static method to define the structure of the keras model.
The users model definition should be saved in a file name with "mlmodel_keras" as a prefix and be
at the top level of the module search path so it can be discovered.
The "mlmodel_keras" class should also define some class variables describing the class:
uiname : str - this is the name that will appear in the user interface
uidescription : str - this is a short description which may be displayed to help the user
predtype : DataPredType enum - type of prediction (must be member of DataPredType enum)
outtype: OutputType enum - output shape type (OutputType.Pixel or OutputType.Image)
dimtype : DimType enum - the input dimensions supported by model (must be member of DimType enum)
Examples
--------
from dgbpy.keras_classes import UserModel, DataPredType, OutputType, DimType
class myModel(UserModel):
uiname = 'mymodel'
uidescription = 'short description of model'
predtype = DataPredType.Classification
outtype = OutputType.Pixel
dimtype = DimType.D3
def _make_model(self, input_shape, nroutputs, learnrate, data_format):
inputs = Input(input_shape)
conv1 = Conv3D(2, (3,3,3), activation='relu', padding='same')(inputs)
conv1 = Conv3D(2, (3,3,3), activation='relu', padding='same')(conv1)
pool1 = MaxPooling3D(pool,size=(2,2,2))(conv1)
...
conv8 = Conv3D(1, (1,1,1,), activation='sigmoid')(conv7)
model = Model(inputs=[inputs], outputs=[conv8])
model.compile(optimizer = Adam(lr = 1e-4), loss = cross_entropy_balanced, metrics = ['accuracy'])
return model
.. py:attribute:: mlmodels
:annotation: = []
.. py:method:: findModels()
:staticmethod:
Static method that searches the PYTHONPATH for modules containing user
defined Keras machine learning models (UserModels).
The module name must be prefixed by "mlmodel_keras". All subclasses of the
UserModel base class is each found module will be added to the mlmodels
class variable.
.. py:method:: findName(modname)
:staticmethod:
Static method that searches the found UserModel's for a match with the
uiname class variable
Parameters
----------
modname : str
Name (i.e. uiname) of the UserModel to search for.
Returns
-------
an instance of the class with the first matching name in the mlmodels
list or None if no match is found
.. py:method:: getModelsByType(pred_type, out_type, dim_type)
:staticmethod:
Static method that returns a list of the UserModels filtered by the given
prediction, output and dimension types
Parameters
----------
pred_type: DataPredType enum
The prediction type of the model to filter by
out_type: OutputType enum
The output shape type of the model to filter by
dim_type: DimType enum
The dimensions that the model must support
Returns
-------
a list of matching model or None if no match found
.. py:method:: getNamesByType(pred_type, out_type, dim_type)
:staticmethod:
.. py:method:: isPredType(modelnm, pred_type)
:staticmethod:
.. py:method:: isOutType(modelnm, out_type)
:staticmethod:
.. py:method:: isClassifier(modelnm)
:staticmethod:
.. py:method:: isRegressor(modelnm)
:staticmethod:
.. py:method:: isImg2Img(modelnm)
:staticmethod:
.. py:method:: _make_model(self, input_shape, nroutputs, learnrate, data_format)
:abstractmethod:
Abstract static method that defines a machine learning model.
Must be implemented in the user's derived class
Parameters
----------
input_shape : tuple
Defines input data shape in the Keras default data_format for the current backend.
For the TensorFlow backend the default data_format is 'channels_last'
nroutputs : int (number of discrete classes for a classification)
Number of outputs
learnrate : float
The step size applied at each iteration to move toward a minimum of the loss function
Returns
-------
a compiled keras model
.. py:method:: model(self, input_shape, nroutputs, learnrate, data_format='channels_first')
Creates/returns a compiled keras model instance
Parameters
----------
input_shape : tuple
Defines input data shape arranged as per the data_format setting.
nroutputs : int (number of discrete classes for a classification)
Number of outputs
learnrate : float
The step size applied at each iteration to move toward a minimum of the loss function
data_format: str
The data format used. The machine learning plugin uses 'channels_first' data_format.
Returns
-------
a compiled keras model
.. py:data:: mlmodels