Skip to content
Snippets Groups Projects
Commit 9a771123 authored by lukas leufen's avatar lukas leufen
Browse files

split is now included

parent cc612677
No related branches found
No related tags found
3 merge requests!146Develop,!145Resolve "new release v0.12.0",!138Resolve "Advanced Documentation"
Pipeline #43809 passed
Stage: test
Stage: docs
Stage: pages
Stage: deploy
Hide whitespace changes
Inline Side-by-side
docs/_source/customise.rst 0 → 100644
+ 244
− 0
View file @ 9a771123
Default Workflow
----------------
.. role:: py(code)
:language: python
MLAir is constituted of so-called :py:`run_modules` which are executed in a distinct order called :py:`workflow`. MLAir
provides a :py:`default_workflow`. This workflow runs the run modules :py:`ExperimentSetup`, :py:`PreProcessing`,
:py:`ModelSetup`, :py:`Training`, and :py:`PostProcessing` one by one.
.. figure:: ./_plots/run_modules_schedule.png
Sketch of the default workflow.
.. code-block:: python
import mlair
# create your custom MLAir workflow
DefaultWorkflow = mlair.DefaultWorkflow()
# execute default workflow
DefaultWorkflow.run()
The output of running this default workflow will be structured like the following.
.. code-block::
INFO: mlair started
INFO: ExperimentSetup started
...
INFO: ExperimentSetup finished after 00:00:01 (hh:mm:ss)
INFO: PreProcessing started
...
INFO: PreProcessing finished after 00:00:11 (hh:mm:ss)
INFO: ModelSetup started
...
INFO: ModelSetup finished after 00:00:01 (hh:mm:ss)
INFO: Training started
...
INFO: Training finished after 00:02:15 (hh:mm:ss)
INFO: PostProcessing started
...
INFO: PostProcessing finished after 00:01:37 (hh:mm:ss)
INFO: mlair finished after 00:04:05 (hh:mm:ss)
Customised Run Module and Workflow
----------------------------------
It is possible to create new custom run modules. A custom run module is required to inherit from the base class
:py:`RunEnvironment` and to hold the constructor method :py:`__init__()`. This method has to execute the module on call.
In the following example, this is done by using the :py:`_run()` method that is called by the initialiser. It is
possible to parse arguments to the custom run module as shown.
.. code-block:: python
import mlair
import logging
class CustomStage(mlair.RunEnvironment):
"""A custom MLAir stage for demonstration."""
def __init__(self, test_string):
super().__init__() # always call super init method
self._run(test_string) # call a class method
def _run(self, test_string):
logging.info("Just running a custom stage.")
logging.info("test_string = " + test_string)
epochs = self.data_store.get("epochs")
logging.info("epochs = " + str(epochs))
If a custom run module is defined, it is required to adjust the workflow. For this, you need to load the empty
:py:`Workflow` class and add each run module that is required. The order of adding modules defines the order of
execution if running the workflow.
.. code-block:: python
# create your custom MLAir workflow
CustomWorkflow = mlair.Workflow()
# provide stages without initialisation
CustomWorkflow.add(mlair.ExperimentSetup, epochs=128)
# add also keyword arguments for a specific stage
CustomWorkflow.add(CustomStage, test_string="Hello World")
# finally execute custom workflow in order of adding
CustomWorkflow.run()
The output will look like:
.. code-block::
INFO: mlair started
...
INFO: ExperimentSetup finished after 00:00:12 (hh:mm:ss)
INFO: CustomStage started
INFO: Just running a custom stage.
INFO: test_string = Hello World
INFO: epochs = 128
INFO: CustomStage finished after 00:00:01 (hh:mm:ss)
INFO: mlair finished after 00:00:13 (hh:mm:ss)
Custom Model
------------
Create your own model to run your personal experiment. To guarantee a proper integration in the MLAir workflow, models
are restricted to inherit from the :py:`AbstractModelClass`. This will ensure a smooth training and evaluation
behaviour.
How to create a customised model?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
* Create a new model class inheriting from :py:`AbstractModelClass`
.. code-block:: python
from mlair import AbstractModelClass
class MyCustomisedModel(AbstractModelClass):
def __init__(self, shape_inputs: list, shape_outputs: list):
super().__init__(shape_inputs[0], shape_outputs[0])
# settings
self.dropout_rate = 0.1
self.activation = keras.layers.PReLU
# apply to model
self.set_model()
self.set_compile_options()
self.set_custom_objects(loss=self.compile_options['loss'])
* Make sure to add the :py:`super().__init__()` and at least :py:`set_model()` and :py:`set_compile_options()` to your
custom init method.
* The shown model expects a single input and output branch provided in a list. Therefore shapes of input and output are
extracted and then provided to the super class initialiser.
* Some general settings like the dropout rate are set in the init method additionally.
* If you have custom objects in your model, that are not part of the keras or tensorflow frameworks, you need to add
them to custom objects. To do this, call :py:`set_custom_objects` with arbitrarily kwargs. In the shown example, the
loss has been added for demonstration only, because we use a build-in loss function. Nonetheless, we always encourage
you to add the loss as custom object, to prevent potential errors when loading an already created model instead of
training a new one.
* Now build your model inside :py:`set_model()` by using the instance attributes :py:`self.shape_inputs` and
:py:`self.shape_outputs` and storing the model as :py:`self.model`.
.. code-block:: python
import keras
class MyCustomisedModel(AbstractModelClass):
def set_model(self):
x_input = keras.layers.Input(shape=self.shape_inputs)
x_in = keras.layers.Conv2D(32, (1, 1), padding='same', name='{}_Conv_1x1'.format("major"))(x_input)
x_in = self.activation(name='{}_conv_act'.format("major"))(x_in)
x_in = keras.layers.Flatten(name='{}'.format("major"))(x_in)
x_in = keras.layers.Dropout(self.dropout_rate, name='{}_Dropout_1'.format("major"))(x_in)
x_in = keras.layers.Dense(16, name='{}_Dense_16'.format("major"))(x_in)
x_in = self.activation()(x_in)
x_in = keras.layers.Dense(self.shape_outputs, name='{}_Dense'.format("major"))(x_in)
out_main = self.activation()(x_in)
self.model = keras.Model(inputs=x_input, outputs=[out_main])
* Your are free how to design your model. Just make sure to save it in the class attribute model.
* Additionally, set your custom compile options including the loss definition.
.. code-block:: python
class MyCustomisedModel(AbstractModelClass):
def set_compile_options(self):
self.initial_lr = 1e-2
self.optimizer = keras.optimizers.SGD(lr=self.initial_lr, momentum=0.9)
self.lr_decay = mlair.model_modules.keras_extensions.LearningRateDecay(base_lr=self.initial_lr,
drop=.94,
epochs_drop=10)
self.loss = keras.losses.mean_squared_error
self.compile_options = {"metrics": ["mse", "mae"]}
* The allocation of the instance parameters :py:`initial_lr`, :py:`optimizer`, and :py:`lr_decay` could be also part of
the model class' initialiser. The same applies to :py:`self.loss` and :py:`compile_options`, but we recommend to use
the :py:`set_compile_options` method for the definition of parameters, that are related to the compile options.
* More important is that the compile options are actually saved. There are three ways to achieve this.
* (1): Set all compile options by parsing a dictionary with all options to :py:`self.compile_options`.
* (2): Set all compile options as instance attributes. MLAir will search for these attributes and store them.
* (3): Define your compile options partly as dictionary and instance attributes (as shown in this example).
* If using (3) and defining the same compile option with different values, MLAir will raise an error.
Incorrect: (Will raise an error because of a mismatch for the :py:`optimizer` parameter.)
.. code-block:: python
def set_compile_options(self):
self.optimizer = keras.optimizers.SGD()
self.loss = keras.losses.mean_squared_error
self.compile_options = {"optimizer" = keras.optimizers.Adam()}
Specials for Branched Models
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
* If you have a branched model with multiple outputs, you need either set only a single loss for all branch outputs or
provide the same number of loss functions considering the right order.
.. code-block:: python
class MyCustomisedModel(AbstractModelClass):
def set_model(self):
...
self.model = keras.Model(inputs=x_input, outputs=[out_minor_1, out_minor_2, out_main])
def set_compile_options(self):
self.loss = [keras.losses.mean_absolute_error] + # for out_minor_1
[keras.losses.mean_squared_error] + # for out_minor_2
[keras.losses.mean_squared_error] # for out_main
How to access my customised model?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
If the customised model is created, you can easily access the model with
>>> MyCustomisedModel().model
<your custom model>
The loss is accessible via
>>> MyCustomisedModel().loss
<your custom loss>
You can treat the instance of your model as instance but also as the model itself. If you call a method, that refers to
the model instead of the model instance, you can directly apply the command on the instance instead of adding the model
parameter call.
>>> MyCustomisedModel().model.compile(**kwargs) == MyCustomisedModel().compile(**kwargs)
True
Custom Data Handler
-------------------
docs/_source/get-started.rst
+ 25
− 117
View file @ 9a771123
Get started with MLAir
======================
Getting started with MLAir
==========================
.. role:: py(code)
:language: python
Install MLAir
-------------
MLAir is based on several python frameworks. To work properly, you have to install all packages from the
`requirements.txt` file. Additionally to support the geographical plotting part it is required to install geo
:py:`requirements.txt` file. Additionally to support the geographical plotting part it is required to install geo
packages built for your operating system. Name names of these package may differ for different systems, we refer
here to the opensuse / leap OS. The geo plot can be removed from the `plot_list`, in this case there is no need to
here to the opensuse / leap OS. The geo plot can be removed from the :py:`plot_list`, in this case there is no need to
install the geo packages.
* (geo) Install **proj** on your machine using the console. E.g. for opensuse / leap `zypper install proj`
Pre-requirements
~~~~~~~~~~~~~~~~
* (geo) Install **proj** on your machine using the console. E.g. for opensuse / leap :py:`zypper install proj`
* (geo) A c++ compiler is required for the installation of the program **cartopy**
* Install all requirements from [`requirements.txt`](https://gitlab.version.fz-juelich.de/toar/machinelearningtools/-/blob/master/requirements.txt)
preferably in a virtual environment
* (tf) Currently, TensorFlow-1.13 is mentioned in the requirements. We already tested the TensorFlow-1.15 version and couldn't
find any compatibility errors. Please note, that tf-1.13 and 1.15 have two distinct branches each, the default branch
for CPU support, and the "-gpu" branch for GPU support. If the GPU version is installed, MLAir will make use of the GPU
device.
* Installation of **MLAir**:
* Either clone MLAir from the [gitlab repository](https://gitlab.version.fz-juelich.de/toar/machinelearningtools.git)
and use it without installation (beside the requirements)
* or download the distribution file (?? .whl) and install it via `pip install <??>`. In this case, you can simply
import MLAir in any python script inside your virtual environment using `import mlair`.
Installation of MLAir
~~~~~~~~~~~~~~~~~~~~~
* Install all requirements from `requirements.txt <https://gitlab.version.fz-juelich.de/toar/machinelearningtools/-/blob/master/requirements.txt>`_
preferably in a virtual environment
* Either clone MLAir from the `gitlab repository <https://gitlab.version.fz-juelich.de/toar/machinelearningtools.git>`_
* or download the distribution file (?? .whl) and install it via :py:`pip install <??>`. In this case, you can simply
import MLAir in any python script inside your virtual environment using :py:`import mlair`.
How to start with MLAir
-----------------------
In this section, we show three examples how to work with MLAir.
In this section, we show three examples how to work with MLAir. Note, that for these examples MLAir was installed using
the distribution file. In case you are using the git clone it is required to adjust the import path if not directly
executed inside the source directory of MLAir.
Example 1
~~~~~~~~~
......@@ -126,107 +138,3 @@ We can see from the terminal that no training was performed. Analysis is now mad
...
INFO: mlair finished after 00:00:06 (hh:mm:ss)
Customised workflows and models
-------------------------------
Custom Workflow
~~~~~~~~~~~~~~~
MLAir provides a default workflow. If additional steps are to be performed, you have to append custom run modules to
the workflow.
.. code-block:: python
import mlair
import logging
class CustomStage(mlair.RunEnvironment):
"""A custom MLAir stage for demonstration."""
def __init__(self, test_string):
super().__init__() # always call super init method
self._run(test_string) # call a class method
def _run(self, test_string):
logging.info("Just running a custom stage.")
logging.info("test_string = " + test_string)
epochs = self.data_store.get("epochs")
logging.info("epochs = " + str(epochs))
# create your custom MLAir workflow
CustomWorkflow = mlair.Workflow()
# provide stages without initialisation
CustomWorkflow.add(mlair.ExperimentSetup, epochs=128)
# add also keyword arguments for a specific stage
CustomWorkflow.add(CustomStage, test_string="Hello World")
# finally execute custom workflow in order of adding
CustomWorkflow.run()
.. code-block::
INFO: mlair started
...
INFO: ExperimentSetup finished after 00:00:12 (hh:mm:ss)
INFO: CustomStage started
INFO: Just running a custom stage.
INFO: test_string = Hello World
INFO: epochs = 128
INFO: CustomStage finished after 00:00:01 (hh:mm:ss)
INFO: mlair finished after 00:00:13 (hh:mm:ss)
Custom Model
~~~~~~~~~~~~
Each model has to inherit from the abstract model class to ensure a smooth training and evaluation behaviour. It is
required to implement the set model and set compile options methods. The later has to set the loss at least.
.. code-block:: python
import keras
from keras.losses import mean_squared_error as mse
from keras.optimizers import SGD
from mlair.model_modules import AbstractModelClass
class MyLittleModel(AbstractModelClass):
"""
A customised model with a 1x1 Conv, and 3 Dense layers (32, 16
window_lead_time). Dropout is used after Conv layer.
"""
def __init__(self, window_history_size, window_lead_time, channels):
super().__init__()
# settings
self.window_history_size = window_history_size
self.window_lead_time = window_lead_time
self.channels = channels
self.dropout_rate = 0.1
self.activation = keras.layers.PReLU
self.lr = 1e-2
# apply to model
self.set_model()
self.set_compile_options()
self.set_custom_objects(loss=self.compile_options['loss'])
def set_model(self):
# add 1 to window_size to include current time step t0
shape = (self.window_history_size + 1, 1, self.channels)
x_input = keras.layers.Input(shape=shape)
x_in = keras.layers.Conv2D(32, (1, 1), padding='same')(x_input)
x_in = self.activation()(x_in)
x_in = keras.layers.Flatten()(x_in)
x_in = keras.layers.Dropout(self.dropout_rate)(x_in)
x_in = keras.layers.Dense(32)(x_in)
x_in = self.activation()(x_in)
x_in = keras.layers.Dense(16)(x_in)
x_in = self.activation()(x_in)
x_in = keras.layers.Dense(self.window_lead_time)(x_in)
out = self.activation()(x_in)
self.model = keras.Model(inputs=x_input, outputs=[out])
def set_compile_options(self):
self.compile_options = {"optimizer": SGD(lr=self.lr),
"loss": mse,
"metrics": ["mse"]}
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment