Bump version: 0.5.0 → 0.5.1

* Added PCA initializer and component for OmegaMatrix or LinearMappings

* [QA] Add default configuration for pre commit hooks

* [QA] Add more pre commit checks

* [QA] Add more pre commit checks

* test(githooks): Add gitlint to check commit messages on commit

* docs(githooks): Add usage guide for pre-commit  to readme

* fix(githooks): mypy only checks source now

reverts changes on docs conf.py

* docs(githooks): Fix typo

Co-authored-by: staps@hs-mittweida.de <staps@hs-mittweida.de>
Co-authored-by: Alexander Engelsberger <alexanderengelsberger@gmail.com>

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.5.0
+current_version = 0.5.1
 commit = True
 tag = True
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)

.pre-commit-config.yaml

@@ -0,0 +1,54 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.0.1
+    hooks:
+    -   id: trailing-whitespace
+    -   id: end-of-file-fixer
+    -   id: check-yaml
+    -   id: check-added-large-files
+    -   id: check-ast
+    -   id: check-case-conflict
+
+
+- repo: https://github.com/myint/autoflake
+  rev: v1.4
+  hooks:
+  -   id: autoflake
+
+- repo: http://github.com/PyCQA/isort
+  rev: 5.8.0
+  hooks:
+  -   id: isort
+
+-   repo: https://github.com/pre-commit/mirrors-mypy
+    rev: 'v0.902'
+    hooks:
+    -   id: mypy
+        files: prototorch
+        additional_dependencies: [types-pkg_resources]
+
+-   repo: https://github.com/pre-commit/mirrors-yapf
+    rev: 'v0.31.0'  # Use the sha / tag you want to point at
+    hooks:
+    -   id: yapf
+
+-   repo: https://github.com/pre-commit/pygrep-hooks
+    rev: v1.9.0  # Use the ref you want to point at
+    hooks:
+    -   id: python-use-type-annotations
+    -   id: python-no-log-warn
+    -   id: python-check-blanket-noqa
+
+
+-   repo: https://github.com/asottile/pyupgrade
+    rev: v2.19.4
+    hooks:
+    -   id: pyupgrade
+
+-   repo: https://github.com/jorisroovers/gitlint
+    rev: "v0.15.1"
+    hooks:
+    -   id: gitlint
+        args: [--contrib=CT1, --ignore=B6, --msg-filename]

README.md

@@ -48,6 +48,17 @@ pip install -e .[all]
 The documentation is available at <https://www.prototorch.ml/en/latest/>. Should
 that link not work try <https://prototorch.readthedocs.io/en/latest/>.
 
+## Contribution
+
+This repository contains definition for [git hooks](https://githooks.com).
+[Pre-commit](https://pre-commit.com) gets installed as development dependency with prototorch.
+Please install the hooks by running
+```bash
+pre-commit install
+pre-commit install --hook-type commit-msg
+```
+before creating the first commit.
+
 ## Bibtex
 
 If you would like to cite the package, please use this:

docs/source/conf.py

@@ -23,7 +23,7 @@ author = "Jensun Ravichandran"
 
 # The full version, including alpha/beta/rc tags
 #
-release = "0.5.0"
+release = "0.5.1"
 
 # -- General configuration ---------------------------------------------------
 

examples/glvq_iris.py

@@ -1,120 +0,0 @@
-"""ProtoTorch GLVQ example using 2D Iris data."""
-
-import numpy as np
-import torch
-from matplotlib import pyplot as plt
-from prototorch.components import LabeledComponents, StratifiedMeanInitializer
-from prototorch.functions.competitions import wtac
-from prototorch.functions.distances import euclidean_distance
-from prototorch.modules.losses import GLVQLoss
-from sklearn.datasets import load_iris
-from sklearn.preprocessing import StandardScaler
-from torchinfo import summary
-
-# Prepare and preprocess the data
-scaler = StandardScaler()
-x_train, y_train = load_iris(return_X_y=True)
-x_train = x_train[:, [0, 2]]
-scaler.fit(x_train)
-x_train = scaler.transform(x_train)
-
-
-# Define the GLVQ model
-class Model(torch.nn.Module):
-    def __init__(self):
-        """GLVQ model for training on 2D Iris data."""
-        super().__init__()
-        prototype_initializer = StratifiedMeanInitializer([x_train, y_train])
-        prototype_distribution = {"num_classes": 3, "prototypes_per_class": 3}
-        self.proto_layer = LabeledComponents(
-            prototype_distribution,
-            prototype_initializer,
-        )
-
-    def forward(self, x):
-        prototypes, prototype_labels = self.proto_layer()
-        distances = euclidean_distance(x, prototypes)
-        return distances, prototype_labels
-
-
-# Build the GLVQ model
-model = Model()
-
-# Print summary using torchinfo (might be buggy/incorrect)
-print(summary(model))
-
-# Optimize using SGD optimizer from `torch.optim`
-optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
-criterion = GLVQLoss(squashing="sigmoid_beta", beta=10)
-
-x_in = torch.Tensor(x_train)
-y_in = torch.Tensor(y_train)
-
-# Training loop
-TITLE = "Prototype Visualization"
-fig = plt.figure(TITLE)
-for epoch in range(70):
-    # Compute loss
-    distances, prototype_labels = model(x_in)
-    loss = criterion([distances, prototype_labels], y_in)
-
-    # Compute Accuracy
-    with torch.no_grad():
-        predictions = wtac(distances, prototype_labels)
-        correct = predictions.eq(y_in.view_as(predictions)).sum().item()
-    acc = 100.0 * correct / len(x_train)
-
-    print(
-        f"Epoch: {epoch + 1:03d} Loss: {loss.item():05.02f} Acc: {acc:05.02f}%"
-    )
-
-    # Optimizer step
-    optimizer.zero_grad()
-    loss.backward()
-    optimizer.step()
-
-    # Get the prototypes form the model
-    prototypes = model.proto_layer.components.numpy()
-    if np.isnan(np.sum(prototypes)):
-        print("Stopping training because of `nan` in prototypes.")
-        break
-
-    # Visualize the data and the prototypes
-    ax = fig.gca()
-    ax.cla()
-    ax.set_title(TITLE)
-    ax.set_xlabel("Data dimension 1")
-    ax.set_ylabel("Data dimension 2")
-    cmap = "viridis"
-    ax.scatter(x_train[:, 0], x_train[:, 1], c=y_train, edgecolor="k")
-    ax.scatter(
-        prototypes[:, 0],
-        prototypes[:, 1],
-        c=prototype_labels,
-        cmap=cmap,
-        edgecolor="k",
-        marker="D",
-        s=50,
-    )
-
-    # Paint decision regions
-    x = np.vstack((x_train, prototypes))
-    x_min, x_max = x[:, 0].min() - 1, x[:, 0].max() + 1
-    y_min, y_max = x[:, 1].min() - 1, x[:, 1].max() + 1
-    xx, yy = np.meshgrid(np.arange(x_min, x_max, 1 / 50),
-                         np.arange(y_min, y_max, 1 / 50))
-    mesh_input = np.c_[xx.ravel(), yy.ravel()]
-
-    torch_input = torch.Tensor(mesh_input)
-    d = model(torch_input)[0]
-    w_indices = torch.argmin(d, dim=1)
-    y_pred = torch.index_select(prototype_labels, 0, w_indices)
-    y_pred = y_pred.reshape(xx.shape)
-
-    # Plot voronoi regions
-    ax.contourf(xx, yy, y_pred, cmap=cmap, alpha=0.35)
-
-    ax.set_xlim(left=x_min + 0, right=x_max - 0)
-    ax.set_ylim(bottom=y_min + 0, top=y_max - 0)
-
-    plt.pause(0.1)

examples/gmlvq_tecator.py

@@ -1,103 +0,0 @@
-"""ProtoTorch "siamese" GMLVQ example using Tecator."""
-
-import matplotlib.pyplot as plt
-import torch
-from prototorch.components import LabeledComponents, StratifiedMeanInitializer
-from prototorch.datasets.tecator import Tecator
-from prototorch.functions.distances import sed
-from prototorch.modules.losses import GLVQLoss
-from prototorch.utils.colors import get_legend_handles
-from torch.utils.data import DataLoader
-
-# Prepare the dataset and dataloader
-train_data = Tecator(root="./artifacts", train=True)
-train_loader = DataLoader(train_data, batch_size=128, shuffle=True)
-
-
-class Model(torch.nn.Module):
-    def __init__(self, **kwargs):
-        """GMLVQ model as a siamese network."""
-        super().__init__()
-        prototype_initializer = StratifiedMeanInitializer(train_loader)
-        prototype_distribution = {"num_classes": 2, "prototypes_per_class": 2}
-
-        self.proto_layer = LabeledComponents(
-            prototype_distribution,
-            prototype_initializer,
-        )
-
-        self.omega = torch.nn.Linear(in_features=100,
-                                     out_features=100,
-                                     bias=False)
-        torch.nn.init.eye_(self.omega.weight)
-
-    def forward(self, x):
-        protos = self.proto_layer.components
-        plabels = self.proto_layer.component_labels
-
-        # Process `x` and `protos` through `omega`
-        x_map = self.omega(x)
-        protos_map = self.omega(protos)
-
-        # Compute distances and output
-        dis = sed(x_map, protos_map)
-        return dis, plabels
-
-
-# Build the GLVQ model
-model = Model()
-
-# Print a summary of the model
-print(model)
-
-# Optimize using Adam optimizer from `torch.optim`
-optimizer = torch.optim.Adam(model.parameters(), lr=0.001_0)
-scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=75, gamma=0.1)
-criterion = GLVQLoss(squashing="identity", beta=10)
-
-# Training loop
-for epoch in range(150):
-    epoch_loss = 0.0  # zero-out epoch loss
-    optimizer.zero_grad()  # zero-out gradients
-    for xb, yb in train_loader:
-        # Compute loss
-        distances, plabels = model(xb)
-        loss = criterion([distances, plabels], yb)
-        epoch_loss += loss.item()
-        # Backprop
-        loss.backward()
-    # Take a gradient descent step
-    optimizer.step()
-    scheduler.step()
-
-    lr = optimizer.param_groups[0]["lr"]
-    print(f"Epoch: {epoch + 1:03d} Loss: {epoch_loss:06.02f} lr: {lr:07.06f}")
-
-# Get the omega matrix form the model
-omega = model.omega.weight.data.numpy().T
-
-# Visualize the lambda matrix
-title = "Lambda Matrix Visualization"
-fig = plt.figure(title)
-ax = fig.gca()
-ax.set_title(title)
-im = ax.imshow(omega.dot(omega.T), cmap="viridis")
-plt.show()
-
-# Get the prototypes form the model
-protos = model.proto_layer.components.numpy()
-plabels = model.proto_layer.component_labels.numpy()
-
-# Visualize the prototypes
-title = "Tecator Prototypes"
-fig = plt.figure(title)
-ax = fig.gca()
-ax.set_title(title)
-ax.set_xlabel("Spectral frequencies")
-ax.set_ylabel("Absorption")
-clabels = ["Class 0 - Low fat", "Class 1 - High fat"]
-handles, colors = get_legend_handles(clabels, marker="line", zero_indexed=True)
-for x, y in zip(protos, plabels):
-    ax.plot(x, c=colors[int(y)])
-ax.legend(handles, clabels)
-plt.show()

examples/gtlvq_mnist.py

@@ -1,183 +0,0 @@
-"""
-ProtoTorch GTLVQ example using MNIST data.
-The GTLVQ is placed as an classification model on
-top of a CNN, considered as featurer extractor.
-Initialization of subpsace and prototypes in
-Siamnese fashion
-For more info about GTLVQ see:
-DOI:10.1109/IJCNN.2016.7727534
-"""
-
-import numpy as np
-import torch
-import torch.nn as nn
-import torchvision
-from prototorch.functions.helper import calculate_prototype_accuracy
-from prototorch.modules.losses import GLVQLoss
-from prototorch.modules.models import GTLVQ
-from torchvision import transforms
-
-# Parameters and options
-num_epochs = 50
-batch_size_train = 64
-batch_size_test = 1000
-learning_rate = 0.1
-momentum = 0.5
-log_interval = 10
-cuda = "cuda:0"
-random_seed = 1
-device = torch.device(cuda if torch.cuda.is_available() else "cpu")
-
-# Configures reproducability
-torch.manual_seed(random_seed)
-np.random.seed(random_seed)
-
-# Prepare and preprocess the data
-train_loader = torch.utils.data.DataLoader(
-    torchvision.datasets.MNIST(
-        "./files/",
-        train=True,
-        download=True,
-        transform=torchvision.transforms.Compose([
-            transforms.ToTensor(),
-            transforms.Normalize((0.1307, ), (0.3081, ))
-        ]),
-    ),
-    batch_size=batch_size_train,
-    shuffle=True,
-)
-
-test_loader = torch.utils.data.DataLoader(
-    torchvision.datasets.MNIST(
-        "./files/",
-        train=False,
-        download=True,
-        transform=torchvision.transforms.Compose([
-            transforms.ToTensor(),
-            transforms.Normalize((0.1307, ), (0.3081, ))
-        ]),
-    ),
-    batch_size=batch_size_test,
-    shuffle=True,
-)
-
-
-# Define the GLVQ model plus appropriate feature extractor
-class CNNGTLVQ(torch.nn.Module):
-    def __init__(
-        self,
-        num_classes,
-        subspace_data,
-        prototype_data,
-        tangent_projection_type="local",
-        prototypes_per_class=2,
-        bottleneck_dim=128,
-    ):
-        super(CNNGTLVQ, self).__init__()
-
-        # Feature Extractor - Simple CNN
-        self.fe = nn.Sequential(
-            nn.Conv2d(1, 32, 3, 1),
-            nn.ReLU(),
-            nn.Conv2d(32, 64, 3, 1),
-            nn.ReLU(),
-            nn.MaxPool2d(2),
-            nn.Dropout(0.25),
-            nn.Flatten(),
-            nn.Linear(9216, bottleneck_dim),
-            nn.Dropout(0.5),
-            nn.LeakyReLU(),
-            nn.LayerNorm(bottleneck_dim),
-        )
-
-        # Forward pass of subspace and prototype initialization data through feature extractor
-        subspace_data = self.fe(subspace_data)
-        prototype_data[0] = self.fe(prototype_data[0])
-
-        # Initialization of GTLVQ
-        self.gtlvq = GTLVQ(
-            num_classes,
-            subspace_data,
-            prototype_data,
-            tangent_projection_type=tangent_projection_type,
-            feature_dim=bottleneck_dim,
-            prototypes_per_class=prototypes_per_class,
-        )
-
-    def forward(self, x):
-        # Feature Extraction
-        x = self.fe(x)
-
-        # GTLVQ Forward pass
-        dis = self.gtlvq(x)
-        return dis
-
-
-# Get init data
-subspace_data = torch.cat(
-    [next(iter(train_loader))[0],
-     next(iter(test_loader))[0]])
-prototype_data = next(iter(train_loader))
-
-# Build the CNN GTLVQ  model
-model = CNNGTLVQ(
-    10,
-    subspace_data,
-    prototype_data,
-    tangent_projection_type="local",
-    bottleneck_dim=128,
-).to(device)
-
-# Optimize using SGD optimizer from `torch.optim`
-optimizer = torch.optim.Adam(
-    [{
-        "params": model.fe.parameters()
-    }, {
-        "params": model.gtlvq.parameters()
-    }],
-    lr=learning_rate,
-)
-criterion = GLVQLoss(squashing="sigmoid_beta", beta=10)
-
-# Training loop
-for epoch in range(num_epochs):
-    for batch_idx, (x_train, y_train) in enumerate(train_loader):
-        model.train()
-        x_train, y_train = x_train.to(device), y_train.to(device)
-        optimizer.zero_grad()
-
-        distances = model(x_train)
-        plabels = model.gtlvq.cls.component_labels.to(device)
-
-        # Compute loss.
-        loss = criterion([distances, plabels], y_train)
-        loss.backward()
-        optimizer.step()
-
-        # GTLVQ uses projected SGD, which means to orthogonalize the subspaces after every gradient update.
-        model.gtlvq.orthogonalize_subspace()
-
-        if batch_idx % log_interval == 0:
-            acc = calculate_prototype_accuracy(distances, y_train, plabels)
-            print(
-                f"Epoch: {epoch + 1:02d}/{num_epochs:02d} Epoch Progress: {100. * batch_idx / len(train_loader):02.02f} % Loss: {loss.item():02.02f} \
-              Train Acc: {acc.item():02.02f}")
-
-    # Test
-    with torch.no_grad():
-        model.eval()
-        correct = 0
-        total = 0
-        for x_test, y_test in test_loader:
-            x_test, y_test = x_test.to(device), y_test.to(device)
-            test_distances = model(torch.tensor(x_test))
-            test_plabels = model.gtlvq.cls.prototype_labels.to(device)
-            i = torch.argmin(test_distances, 1)
-            correct += torch.sum(y_test == test_plabels[i])
-            total += y_test.size(0)
-        print("Accuracy of the network on the test images: %d %%" %
-              (torch.true_divide(correct, total) * 100))
-
-# Save the model
-PATH = "./glvq_mnist_model.pth"
-torch.save(model.state_dict(), PATH)

examples/lgmlvq_iris.py

@@ -1,108 +0,0 @@
-"""ProtoTorch LGMLVQ example using 2D Iris data."""
-
-import numpy as np
-import torch
-from matplotlib import pyplot as plt
-from prototorch.components import LabeledComponents, StratifiedMeanInitializer
-from prototorch.functions.competitions import stratified_min
-from prototorch.functions.distances import lomega_distance
-from prototorch.modules.losses import GLVQLoss
-from sklearn.datasets import load_iris
-from sklearn.metrics import accuracy_score
-
-# Prepare training data
-x_train, y_train = load_iris(True)
-x_train = x_train[:, [0, 2]]
-
-
-# Define the model
-class Model(torch.nn.Module):
-    def __init__(self):
-        """Local-GMLVQ model."""
-        super().__init__()
-
-        prototype_initializer = StratifiedMeanInitializer([x_train, y_train])
-        prototype_distribution = [1, 2, 2]
-        self.proto_layer = LabeledComponents(
-            prototype_distribution,
-            prototype_initializer,
-        )
-
-        omegas = torch.eye(2, 2).repeat(5, 1, 1)
-        self.omegas = torch.nn.Parameter(omegas)
-
-    def forward(self, x):
-        protos, plabels = self.proto_layer()
-        omegas = self.omegas
-        dis = lomega_distance(x, protos, omegas)
-        return dis, plabels
-
-
-# Build the model
-model = Model()
-
-# Optimize using Adam optimizer from `torch.optim`
-optimizer = torch.optim.Adam(model.parameters(), lr=0.01)
-criterion = GLVQLoss(squashing="sigmoid_beta", beta=10)
-
-x_in = torch.Tensor(x_train)
-y_in = torch.Tensor(y_train)
-
-# Training loop
-title = "Prototype Visualization"
-fig = plt.figure(title)
-for epoch in range(100):
-    # Compute loss
-    dis, plabels = model(x_in)
-    loss = criterion([dis, plabels], y_in)
-    y_pred = np.argmin(stratified_min(dis, plabels).detach().numpy(), axis=1)
-    acc = accuracy_score(y_train, y_pred)
-    log_string = f"Epoch: {epoch + 1:03d} Loss: {loss.item():05.02f} "
-    log_string += f"Acc: {acc * 100:05.02f}%"
-    print(log_string)
-
-    # Take a gradient descent step
-    optimizer.zero_grad()
-    loss.backward()
-    optimizer.step()
-
-    # Get the prototypes form the model
-    protos = model.proto_layer.components.numpy()
-
-    # Visualize the data and the prototypes
-    ax = fig.gca()
-    ax.cla()
-    ax.set_title(title)
-    ax.set_xlabel("Data dimension 1")
-    ax.set_ylabel("Data dimension 2")
-    cmap = "viridis"
-    ax.scatter(x_train[:, 0], x_train[:, 1], c=y_train, edgecolor="k")
-    ax.scatter(
-        protos[:, 0],
-        protos[:, 1],
-        c=plabels,
-        cmap=cmap,
-        edgecolor="k",
-        marker="D",
-        s=50,
-    )
-
-    # Paint decision regions
-    x = np.vstack((x_train, protos))
-    x_min, x_max = x[:, 0].min() - 1, x[:, 0].max() + 1
-    y_min, y_max = x[:, 1].min() - 1, x[:, 1].max() + 1
-    xx, yy = np.meshgrid(np.arange(x_min, x_max, 1 / 50),
-                         np.arange(y_min, y_max, 1 / 50))
-    mesh_input = np.c_[xx.ravel(), yy.ravel()]
-
-    d, plabels = model(torch.Tensor(mesh_input))
-    y_pred = np.argmin(stratified_min(d, plabels).detach().numpy(), axis=1)
-    y_pred = y_pred.reshape(xx.shape)
-
-    # Plot voronoi regions
-    ax.contourf(xx, yy, y_pred, cmap=cmap, alpha=0.35)
-
-    ax.set_xlim(left=x_min + 0, right=x_max - 0)
-    ax.set_ylim(bottom=y_min + 0, top=y_max - 0)
-
-    plt.pause(0.1)

prototorch/__init__.py

@@ -1,6 +1,7 @@
 """ProtoTorch package."""
 
 import pkgutil
+from typing import List
 
 import pkg_resources
 
@@ -8,7 +9,7 @@ from . import components, datasets, functions, modules, utils
 from .datasets import *
 
 # Core Setup
-__version__ = "0.5.0"
+__version__ = "0.5.1"
 
 __all_core__ = [
     "datasets",
@@ -19,7 +20,7 @@ __all_core__ = [
 ]
 
 # Plugin Loader
-__path__ = pkgutil.extend_path(__path__, __name__)
+__path__: List[str] = pkgutil.extend_path(__path__, __name__)
 
 
 def discover_plugins():

prototorch/components/components.py

@@ -3,13 +3,13 @@
 import warnings
 
 import torch
+from torch.nn.parameter import Parameter
+
 from prototorch.components.initializers import (ClassAwareInitializer,
                                                 ComponentsInitializer,
-                                                CustomLabelsInitializer,
                                                 EqualLabelsInitializer,
                                                 UnequalLabelsInitializer,
                                                 ZeroReasoningsInitializer)
-from torch.nn.parameter import Parameter
 
 from .initializers import parse_data_arg
 
@@ -21,7 +21,9 @@ def get_labels_object(distribution):
                 distribution["num_classes"],
                 distribution["prototypes_per_class"])
         else:
-            labels = CustomLabelsInitializer(distribution)
+            clabels = list(distribution.keys())
+            dist = list(distribution.values())
+            labels = UnequalLabelsInitializer(dist, clabels)
     elif isinstance(distribution, tuple):
         num_classes, prototypes_per_class = distribution
         labels = EqualLabelsInitializer(num_classes, prototypes_per_class)
@@ -42,6 +44,45 @@ def _precheck_initializer(initializer):
         raise TypeError(emsg)
 
 
+class LinearMapping(torch.nn.Module):
+    """LinearMapping is a learnable Mapping Matrix."""
+    def __init__(self,
+                 mapping_shape=None,
+                 initializer=None,
+                 *,
+                 initialized_linearmapping=None):
+        super().__init__()
+
+        # Ignore all initialization settings if initialized_components is given.
+        if initialized_linearmapping is not None:
+            self._register_mapping(initialized_linearmapping)
+            if num_components is not None or initializer is not None:
+                wmsg = "Arguments ignored while initializing Components"
+                warnings.warn(wmsg)
+        else:
+            self._initialize_mapping(mapping_shape, initializer)
+
+    @property
+    def mapping_shape(self):
+        return self._omega.shape
+
+    def _register_mapping(self, components):
+        self.register_parameter("_omega", Parameter(components))
+
+    def _initialize_mapping(self, mapping_shape, initializer):
+        _precheck_initializer(initializer)
+        _mapping = initializer.generate(mapping_shape)
+        self._register_mapping(_mapping)
+
+    @property
+    def mapping(self):
+        """Tensor containing the component tensors."""
+        return self._omega.detach()
+
+    def forward(self):
+        return self._omega
+
+
 class Components(torch.nn.Module):
     """Components is a set of learnable Tensors."""
     def __init__(self,
@@ -118,7 +159,7 @@ class LabeledComponents(Components):
             components, component_labels = parse_data_arg(
                 initialized_components)
             super().__init__(initialized_components=components)
-            self._labels = component_labels
+            self._register_labels(component_labels)
         else:
             labels = get_labels_object(distribution)
             self.initial_distribution = labels.distribution
@@ -156,7 +197,7 @@ class LabeledComponents(Components):
 
         # Components
         if isinstance(initializer, ClassAwareInitializer):
-            _new = initializer.generate(len(new_labels), labels.distribution)
+            _new = initializer.generate(len(new_labels), distribution)
         else:
             _new = initializer.generate(len(new_labels))
         _components = torch.cat([self._components, _new])
@@ -180,7 +221,7 @@ class LabeledComponents(Components):
 
 
 class ReasoningComponents(Components):
-    """ReasoningComponents generate a set of components and a set of reasoning matrices.
+    r"""ReasoningComponents generate a set of components and a set of reasoning matrices.
 
     Every Component has a reasoning matrix assigned.
 

prototorch/components/initializers.py

@@ -1,5 +1,4 @@
-"""ProtoTroch Component and Label Initializers."""
+"""ProtoTroch Initializers."""
-
 import warnings
 from collections.abc import Iterable
 from itertools import chain
@@ -168,6 +167,14 @@ class StratifiedSelectionInitializer(ClassAwareInitializer):
         return samples
 
 
+# Omega matrix
+class PcaInitializer(DataAwareInitializer):
+    def generate(self, shape):
+        (input_dim, latent_dim) = shape
+        (_, eigVal, eigVec) = torch.pca_lowrank(self.data, q=latent_dim)
+        return eigVec
+
+
 # Labels
 class LabelsInitializer:
     def generate(self):
@@ -175,19 +182,17 @@ class LabelsInitializer:
 
 
 class UnequalLabelsInitializer(LabelsInitializer):
-    def __init__(self, dist):
+    def __init__(self, dist, clabels=None):
         self.dist = dist
+        self.clabels = clabels or range(len(self.dist))
 
     @property
     def distribution(self):
         return self.dist
 
-    def generate(self, clabels=None, dist=None):
+    def generate(self):
-        if not clabels:
+        targets = list(
-            clabels = range(len(self.dist))
+            chain(*[[i] * n for i, n in zip(self.clabels, self.dist)]))
-        if not dist:
-            dist = self.dist
-        targets = list(chain(*[[i] * n for i, n in zip(clabels, dist)]))
         return torch.LongTensor(targets)
 
 
@@ -204,13 +209,6 @@ class EqualLabelsInitializer(LabelsInitializer):
         return torch.arange(self.classes).repeat(self.per_class, 1).T.flatten()
 
 
-class CustomLabelsInitializer(UnequalLabelsInitializer):
-    def generate(self):
-        clabels = list(self.dist.keys())
-        dist = list(self.dist.values())
-        return super().generate(clabels, dist)
-
-
 # Reasonings
 class ReasoningsInitializer:
     def generate(self, length):
@@ -232,3 +230,4 @@ SMI = StratifiedMeanInitializer
 Random = RandomInitializer = UniformInitializer
 Zeros = ZerosInitializer
 Ones = OnesInitializer
+PCA = PcaInitializer

prototorch/datasets/sklearn.py

@@ -8,11 +8,11 @@ URL:
 import warnings
 from typing import Sequence, Union
 
-from prototorch.datasets.abstract import NumpyDataset
-
 from sklearn.datasets import (load_iris, make_blobs, make_circles,
                               make_classification, make_moons)
 
+from prototorch.datasets.abstract import NumpyDataset
+
 
 class Iris(NumpyDataset):
     """Iris Dataset by Ronald Fisher introduced in 1936.

prototorch/datasets/tecator.py

@@ -40,9 +40,10 @@ import os
 
 import numpy as np
 import torch
-from prototorch.datasets.abstract import ProtoDataset
 from torchvision.datasets.utils import download_file_from_google_drive
 
+from prototorch.datasets.abstract import ProtoDataset
+
 
 class Tecator(ProtoDataset):
     """

prototorch/functions/distances.py

@@ -2,6 +2,7 @@
 
 import numpy as np
 import torch
+
 from prototorch.functions.helper import (_check_shapes, _int_and_mixed_shape,
                                          equal_int_shape, get_flat)
 

prototorch/functions/helper.py

@@ -89,6 +89,6 @@ def _check_shapes(signal_int_shape, proto_int_shape):
 
 def _int_and_mixed_shape(tensor):
     shape = mixed_shape(tensor)
-    int_shape = tuple([i if isinstance(i, int) else None for i in shape])
+    int_shape = tuple(i if isinstance(i, int) else None for i in shape)
 
     return shape, int_shape

prototorch/functions/transforms.py

@@ -1,5 +1,32 @@
 import torch
 
 
-def gaussian(distance, variance):
+# Functions
-    return torch.exp(-(distance * distance) / (2 * variance))
+def gaussian(distances, variance):
+    return torch.exp(-(distances * distances) / (2 * variance))
+
+
+def rank_scaled_gaussian(distances, lambd):
+    order = torch.argsort(distances, dim=1)
+    ranks = torch.argsort(order, dim=1)
+
+    return torch.exp(-torch.exp(-ranks / lambd) * distances)
+
+
+# Modules
+class GaussianPrior(torch.nn.Module):
+    def __init__(self, variance):
+        super().__init__()
+        self.variance = variance
+
+    def forward(self, distances):
+        return gaussian(distances, self.variance)
+
+
+class RankScaledGaussianPrior(torch.nn.Module):
+    def __init__(self, lambd):
+        super().__init__()
+        self.lambd = lambd
+
+    def forward(self, distances):
+        return rank_scaled_gaussian(distances, self.lambd)

prototorch/modules/__init__.py

@@ -1,7 +1,5 @@
 """ProtoTorch modules."""
 
 from .competitions import *
-from .initializers import *
 from .pooling import *
-from .transformations import *
 from .wrappers import LambdaLayer, LossLayer

prototorch/modules/competitions.py

@@ -1,6 +1,7 @@
 """ProtoTorch Competition Modules."""
 
 import torch
+
 from prototorch.functions.competitions import knnc, wtac
 
 

prototorch/modules/initializers.py

@@ -1,61 +0,0 @@
-"""ProtoTroch Module Initializers."""
-
-import torch
-
-
-# Transformations
-class MatrixInitializer(object):
-    def __init__(self, *args, **kwargs):
-        ...
-
-    def generate(self, shape):
-        raise NotImplementedError("Subclasses should implement this!")
-
-
-class ZerosInitializer(MatrixInitializer):
-    def generate(self, shape):
-        return torch.zeros(shape)
-
-
-class OnesInitializer(MatrixInitializer):
-    def __init__(self, scale=1.0):
-        super().__init__()
-        self.scale = scale
-
-    def generate(self, shape):
-        return torch.ones(shape) * self.scale
-
-
-class UniformInitializer(MatrixInitializer):
-    def __init__(self, minimum=0.0, maximum=1.0, scale=1.0):
-        super().__init__()
-        self.minimum = minimum
-        self.maximum = maximum
-        self.scale = scale
-
-    def generate(self, shape):
-        return torch.ones(shape).uniform_(self.minimum,
-                                          self.maximum) * self.scale
-
-
-class DataAwareInitializer(MatrixInitializer):
-    def __init__(self, data, transform=torch.nn.Identity()):
-        super().__init__()
-        self.data = data
-        self.transform = transform
-
-    def __del__(self):
-        del self.data
-
-
-class EigenVectorInitializer(DataAwareInitializer):
-    def generate(self, shape):
-        # TODO
-        raise NotImplementedError()
-
-
-# Aliases
-EV = EigenVectorInitializer
-Random = RandomInitializer = UniformInitializer
-Zeros = ZerosInitializer
-Ones = OnesInitializer

prototorch/modules/losses.py

@@ -1,6 +1,7 @@
 """ProtoTorch losses."""
 
 import torch
+
 from prototorch.functions.activations import get_activation
 from prototorch.functions.losses import glvq_loss
 

prototorch/modules/models.py

@@ -1,8 +1,9 @@
 import torch
+from torch import nn
+
 from prototorch.components import LabeledComponents, StratifiedMeanInitializer
 from prototorch.functions.distances import euclidean_distance_matrix
 from prototorch.functions.normalization import orthogonalization
-from torch import nn
 
 
 class GTLVQ(nn.Module):

prototorch/modules/pooling.py

@@ -1,6 +1,7 @@
 """ProtoTorch Pooling Modules."""
 
 import torch
+
 from prototorch.functions.pooling import (stratified_max_pooling,
                                           stratified_min_pooling,
                                           stratified_prod_pooling,

prototorch/modules/transformations.py

@@ -1,49 +0,0 @@
-"""ProtoTorch Transformation Layers."""
-
-import torch
-from torch.nn.parameter import Parameter
-
-from .initializers import MatrixInitializer
-
-
-def _precheck_initializer(initializer):
-    if not isinstance(initializer, MatrixInitializer):
-        emsg = f"`initializer` has to be some subtype of " \
-            f"{MatrixInitializer}. " \
-            f"You have provided: {initializer=} instead."
-        raise TypeError(emsg)
-
-
-class Omega(torch.nn.Module):
-    """The Omega mapping used in GMLVQ."""
-    def __init__(self,
-                 num_replicas=1,
-                 input_dim=None,
-                 latent_dim=None,
-                 initializer=None,
-                 *,
-                 initialized_weights=None):
-        super().__init__()
-
-        if initialized_weights is not None:
-            self._register_weights(initialized_weights)
-        else:
-            if num_replicas == 1:
-                shape = (input_dim, latent_dim)
-            else:
-                shape = (num_replicas, input_dim, latent_dim)
-            self._initialize_weights(shape, initializer)
-
-    def _register_weights(self, weights):
-        self.register_parameter("_omega", Parameter(weights))
-
-    def _initialize_weights(self, shape, initializer):
-        _precheck_initializer(initializer)
-        _omega = initializer.generate(shape)
-        self._register_weights(_omega)
-
-    def forward(self):
-        return self._omega
-
-    def extra_repr(self):
-        return f"(omega): (shape: {tuple(self._omega.shape)})"

setup.py

@@ -1,10 +1,12 @@
 """
-  _____           _     _______             _
+
- |  __ \         | |   |__   __|           | |
+ ######
- | |__) | __ ___ | |_ ___ | | ___  _ __ ___| |__
+ #     # #####   ####  #####  ####  #####  ####  #####   ####  #    #
- |  ___/ '__/ _ \| __/ _ \| |/ _ \| '__/ __| '_ \
+ #     # #    # #    #   #   #    #   #   #    # #    # #    # #    #
- | |   | | | (_) | || (_) | | (_) | | | (__| | | |
+ ######  #    # #    #   #   #    #   #   #    # #    # #      ######
- |_|   |_|  \___/ \__\___/|_|\___/|_|  \___|_| |_|
+ #       #####  #    #   #   #    #   #   #    # #####  #      #    #
+ #       #   #  #    #   #   #    #   #   #    # #   #  #    # #    #
+ #       #    #  ####    #    ####    #    ####  #    #  ####  #    #
 
 ProtoTorch Core Package
 """
@@ -18,7 +20,7 @@ with open("README.md", "r") as fh:
 
 INSTALL_REQUIRES = [
     "torch>=1.3.1",
-    "torchvision>=0.5.0",
+    "torchvision>=0.5.1",
     "numpy>=1.9.1",
     "sklearn",
 ]
@@ -26,7 +28,10 @@ DATASETS = [
     "requests",
     "tqdm",
 ]
-DEV = ["bumpversion"]
+DEV = [
+    "bumpversion",
+    "pre-commit",
+]
 DOCS = [
     "recommonmark",
     "sphinx",
@@ -43,7 +48,7 @@ ALL = DATASETS + DEV + DOCS + EXAMPLES + TESTS
 
 setup(
     name="prototorch",
-    version="0.5.0",
+    version="0.5.1",
     description="Highly extensible, GPU-supported "
     "Learning Vector Quantization (LVQ) toolbox "
     "built using PyTorch and its nn API.",

tests/test_components.py

@@ -1,8 +1,9 @@
 """ProtoTorch components test suite."""
 
-import prototorch as pt
 import torch
 
+import prototorch as pt
+
 
 def test_labcomps_zeros_init():
     protos = torch.zeros(3, 2)

tests/test_functions.py

@@ -4,6 +4,7 @@ import unittest
 
 import numpy as np
 import torch
+
 from prototorch.functions import (activations, competitions, distances,
                                   initializers, losses, pooling)