feat: metrics can be assigned to the different phases

docs/source/index.rst

@@ -23,6 +23,13 @@ ProtoTorch Models Plugins
 
    custom
 
+.. toctree::
+   :hidden:
+   :maxdepth: 3
+   :caption: Proto Y Architecture
+
+   y-architecture
+
 About
 -----------------------------------------
 `Prototorch Models <https://github.com/si-cim/prototorch_models>`_ is a Plugin
@@ -33,8 +40,10 @@ prototype-based Machine Learning algorithms using `PyTorch-Lightning
 Library
 -----------------------------------------
 Prototorch Models delivers many application ready models.
-These models have been published in the past and have been adapted to the Prototorch library.
+These models have been published in the past and have been adapted to the
+Prototorch library.
 
 Customizable
 -----------------------------------------
-Prototorch Models also contains the building blocks to build own models with PyTorch-Lightning and Prototorch.
+Prototorch Models also contains the building blocks to build own models with
+PyTorch-Lightning and Prototorch.

docs/source/library.rst

@@ -71,7 +71,7 @@ Probabilistic Models
 Probabilistic variants assume, that the prototypes generate a probability distribution over the classes.
 For a test sample they return a distribution instead of a class assignment.
 
-The following two algorihms were presented by :cite:t:`seo2003` .
+The following two algorithms were presented by :cite:t:`seo2003` .
 Every prototypes is a center of a gaussian distribution of its class, generating a mixture model.
 
 .. autoclass:: prototorch.models.probabilistic.SLVQ
@@ -80,7 +80,7 @@ Every prototypes is a center of a gaussian distribution of its class, generating
 .. autoclass:: prototorch.models.probabilistic.RSLVQ
    :members:
 
-:cite:t:`villmann2018` proposed two changes to RSLVQ: First incooperate the winning rank into the prior probability calculation.
+:cite:t:`villmann2018` proposed two changes to RSLVQ: First incorporate the winning rank into the prior probability calculation.
 And second use divergence as loss function.
 
 .. autoclass:: prototorch.models.probabilistic.PLVQ
@@ -106,7 +106,7 @@ Visualization
 Visualization is very specific to its application.
 PrototorchModels delivers visualization for two dimensional data and image data.
 
-The visulizations can be shown in a seperate window and inside a tensorboard.
+The visualizations can be shown in a separate window and inside a tensorboard.
 
 .. automodule:: prototorch.models.vis
    :members:

docs/source/y-architecture.rst

@@ -0,0 +1,71 @@
+.. Documentation of the updated Architecture.
+
+Proto Y Architecture
+========================================
+
+Overview
+****************************************
+
+The Proto Y Architecture is a framework for abstract prototype learning methods.
+
+It divides the problem into multiple steps:
+
+    * **Components** : Recalling the position and metadata of the components/prototypes.
+    * **Backbone** : Apply a mapping function to data and prototypes.
+    * **Comparison** : Calculate a dissimilarity based on the latent positions.
+    * **Competition** : Calculate competition values based on the comparison and the metadata.
+    * **Loss** : Calculate the loss based on the competition values
+    * **Inference** : Predict the output based on the competition values.
+
+Depending on the phase (Training or Testing) Loss or Inference is used.
+
+Inheritance Structure
+****************************************
+
+The Proto Y Architecture has a single base class that defines all steps and hooks
+of the architecture.
+
+.. autoclass:: prototorch.y.architectures.base.BaseYArchitecture
+
+    **Steps**
+
+    Components
+
+    .. automethod:: init_components
+    .. automethod:: components
+
+    Backbone
+
+    .. automethod:: init_backbone
+    .. automethod:: backbone
+
+    Comparison
+
+    .. automethod:: init_comparison
+    .. automethod:: comparison
+
+    Competition
+
+    .. automethod:: init_competition
+    .. automethod:: competition
+
+    Loss
+
+    .. automethod:: init_loss
+    .. automethod:: loss
+
+    Inference
+
+    .. automethod:: init_inference
+    .. automethod:: inference
+
+    **Hooks**
+
+    Torchmetric
+
+    .. automethod:: register_torchmetric
+
+Hyperparameters
+****************************************
+Every model implemented with the Proto Y Architecture has a set of hyperparameters,
+which is stored in the ``HyperParameters`` attribute of the architecture.