Bump version: 0.4.5 → 0.5.0

Update Iris example to new component API
Update Tecator example to new component API
Update LGMLVQ example to new component API
Update GTLVQ to new component API

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.4.1
+current_version = 0.5.0
 commit = True
 tag = True
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)

.gitignore

@@ -155,3 +155,4 @@ scratch*
 .vscode/
 
 reports
+artifacts

.travis.yml

@@ -4,7 +4,9 @@ language: python
 python: 3.8
 cache:
   directories:
+  - "$HOME/.cache/pip"
   - "./tests/artifacts"
+  - "$HOME/datasets"
 install:
 - pip install .[all] --progress-bar off
 

RELEASE.md

@@ -1,5 +1,10 @@
 # ProtoTorch Releases
 
+## Release 0.5.0
+
+- Breaking: Removed deprecated `prototorch.modules.Prototypes1D`
+  - Use `prototorch.components.LabeledComponents` instead
+
 ## Release 0.2.0
 
 ### Includes

docs/source/api.rst

@@ -1,13 +1,24 @@
-.. ProtoFlow API Reference
+.. ProtoTorch API Reference
 
-ProtoFlow API Reference
+ProtoTorch API Reference
 ======================================
 
 Datasets
 --------------------------------------
+
+Common Datasets
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 .. automodule:: prototorch.datasets
    :members:
-   :undoc-members:
+
+
+Abstract Datasets
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Abstract Datasets are used to build your own datasets.
+
+.. autoclass:: prototorch.datasets.abstract.NumpyDataset
+   :members:
 
 Functions
 --------------------------------------

docs/source/conf.py

@@ -23,7 +23,7 @@ author = "Jensun Ravichandran"
 
 # The full version, including alpha/beta/rc tags
 #
-release = "0.4.1"
+release = "0.5.0"
 
 # -- General configuration ---------------------------------------------------
 
@@ -46,6 +46,7 @@ extensions = [
     "sphinx.ext.viewcode",
     "sphinx_rtd_theme",
     "sphinxcontrib.katex",
+    'sphinx_autodoc_typehints',
 ]
 
 # katex_prerender = True
@@ -179,6 +180,9 @@ texinfo_documents = [
 intersphinx_mapping = {
     "python": ("https://docs.python.org/", None),
     "numpy": ("https://docs.scipy.org/doc/numpy/", None),
+    "torch": ('https://pytorch.org/docs/stable/', None),
+    "pytorch_lightning":
+    ("https://pytorch-lightning.readthedocs.io/en/stable/", None),
 }
 
 # -- Options for Epub output ----------------------------------------------

examples/glvq_iris.py

@@ -3,14 +3,13 @@
 import numpy as np
 import torch
 from matplotlib import pyplot as plt
-from sklearn.datasets import load_iris
-from sklearn.preprocessing import StandardScaler
-from torchinfo import summary
-
+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 prototorch.modules.prototypes import Prototypes1D
+from sklearn.datasets import load_iris
+from sklearn.preprocessing import StandardScaler
+from torchinfo import summary
 
 # Prepare and preprocess the data
 scaler = StandardScaler()
@@ -25,19 +24,17 @@ class Model(torch.nn.Module):
     def __init__(self):
         """GLVQ model for training on 2D Iris data."""
         super().__init__()
-        self.proto_layer = Prototypes1D(
-            input_dim=2,
-            prototypes_per_class=3,
-            nclasses=3,
-            prototype_initializer="stratified_random",
-            data=[x_train, y_train],
+        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):
-        protos = self.proto_layer.prototypes
-        plabels = self.proto_layer.prototype_labels
-        dis = euclidean_distance(x, protos)
-        return dis, plabels
+        prototypes, prototype_labels = self.proto_layer()
+        distances = euclidean_distance(x, prototypes)
+        return distances, prototype_labels
 
 
 # Build the GLVQ model
@@ -54,43 +51,46 @@ x_in = torch.Tensor(x_train)
 y_in = torch.Tensor(y_train)
 
 # Training loop
-title = "Prototype Visualization"
-fig = plt.figure(title)
+TITLE = "Prototype Visualization"
+fig = plt.figure(TITLE)
 for epoch in range(70):
     # Compute loss
-    dis, plabels = model(x_in)
-    loss = criterion([dis, plabels], y_in)
+    distances, prototype_labels = model(x_in)
+    loss = criterion([distances, prototype_labels], y_in)
+
+    # Compute Accuracy
     with torch.no_grad():
-        pred = wtac(dis, plabels)
-        correct = pred.eq(y_in.view_as(pred)).sum().item()
+        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}%"
     )
 
-    # Take a gradient descent step
+    # Optimizer step
     optimizer.zero_grad()
     loss.backward()
     optimizer.step()
 
     # Get the prototypes form the model
-    protos = model.proto_layer.prototypes.data.numpy()
-    if np.isnan(np.sum(protos)):
+    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_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,
+        prototypes[:, 0],
+        prototypes[:, 1],
+        c=prototype_labels,
         cmap=cmap,
         edgecolor="k",
         marker="D",
@@ -98,7 +98,7 @@ for epoch in range(70):
     )
 
     # Paint decision regions
-    x = np.vstack((x_train, protos))
+    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),
@@ -108,7 +108,7 @@ for epoch in range(70):
     torch_input = torch.Tensor(mesh_input)
     d = model(torch_input)[0]
     w_indices = torch.argmin(d, dim=1)
-    y_pred = torch.index_select(plabels, 0, w_indices)
+    y_pred = torch.index_select(prototype_labels, 0, w_indices)
     y_pred = y_pred.reshape(xx.shape)
 
     # Plot voronoi regions

examples/gmlvq_tecator.py

@@ -2,13 +2,12 @@
 
 import matplotlib.pyplot as plt
 import torch
-from torch.utils.data import DataLoader
-
+from prototorch.components import LabeledComponents, StratifiedMeanInitializer
 from prototorch.datasets.tecator import Tecator
 from prototorch.functions.distances import sed
-from prototorch.modules import Prototypes1D
 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)
@@ -19,22 +18,22 @@ class Model(torch.nn.Module):
     def __init__(self, **kwargs):
         """GMLVQ model as a siamese network."""
         super().__init__()
-        x, y = train_data.data, train_data.targets
-        self.p1 = Prototypes1D(
-            input_dim=100,
-            prototypes_per_class=2,
-            nclasses=2,
-            prototype_initializer="stratified_random",
-            data=[x, y],
+        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.p1.prototypes
-        plabels = self.p1.prototype_labels
+        protos = self.proto_layer.components
+        plabels = self.proto_layer.component_labels
 
         # Process `x` and `protos` through `omega`
         x_map = self.omega(x)
@@ -86,8 +85,8 @@ im = ax.imshow(omega.dot(omega.T), cmap="viridis")
 plt.show()
 
 # Get the prototypes form the model
-protos = model.p1.prototypes.data.numpy()
-plabels = model.p1.prototype_labels
+protos = model.proto_layer.components.numpy()
+plabels = model.proto_layer.component_labels.numpy()
 
 # Visualize the prototypes
 title = "Tecator Prototypes"

examples/gtlvq_mnist.py

@@ -12,20 +12,19 @@ import numpy as np
 import torch
 import torch.nn as nn
 import torchvision
-from torchvision import transforms
-
 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
-n_epochs = 50
+num_epochs = 50
 batch_size_train = 64
 batch_size_test = 1000
 learning_rate = 0.1
 momentum = 0.5
 log_interval = 10
-cuda = "cuda:1"
+cuda = "cuda:0"
 random_seed = 1
 device = torch.device(cuda if torch.cuda.is_available() else "cpu")
 
@@ -141,14 +140,14 @@ optimizer = torch.optim.Adam(
 criterion = GLVQLoss(squashing="sigmoid_beta", beta=10)
 
 # Training loop
-for epoch in range(n_epochs):
+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.prototype_labels.to(device)
+        plabels = model.gtlvq.cls.component_labels.to(device)
 
         # Compute loss.
         loss = criterion([distances, plabels], y_train)
@@ -161,7 +160,7 @@ for epoch in range(n_epochs):
         if batch_idx % log_interval == 0:
             acc = calculate_prototype_accuracy(distances, y_train, plabels)
             print(
-                f"Epoch: {epoch + 1:02d}/{n_epochs:02d} Epoch Progress: {100. * batch_idx / len(train_loader):02.02f} % Loss: {loss.item():02.02f} \
+                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

examples/lgmlvq_iris.py

@@ -3,14 +3,12 @@
 import numpy as np
 import torch
 from matplotlib import pyplot as plt
-from sklearn.datasets import load_iris
-from sklearn.metrics import accuracy_score
-
+from prototorch.components import LabeledComponents, StratifiedMeanInitializer
 from prototorch.functions.competitions import stratified_min
 from prototorch.functions.distances import lomega_distance
-from prototorch.functions.init import eye_
 from prototorch.modules.losses import GLVQLoss
-from prototorch.modules.prototypes import Prototypes1D
+from sklearn.datasets import load_iris
+from sklearn.metrics import accuracy_score
 
 # Prepare training data
 x_train, y_train = load_iris(True)
@@ -22,19 +20,19 @@ class Model(torch.nn.Module):
     def __init__(self):
         """Local-GMLVQ model."""
         super().__init__()
-        self.p1 = Prototypes1D(
-            input_dim=2,
-            prototype_distribution=[1, 2, 2],
-            prototype_initializer="stratified_random",
-            data=[x_train, y_train],
+
+        prototype_initializer = StratifiedMeanInitializer([x_train, y_train])
+        prototype_distribution = [1, 2, 2]
+        self.proto_layer = LabeledComponents(
+            prototype_distribution,
+            prototype_initializer,
         )
-        omegas = torch.zeros(5, 2, 2)
+
+        omegas = torch.eye(2, 2).repeat(5, 1, 1)
         self.omegas = torch.nn.Parameter(omegas)
-        eye_(self.omegas)
 
     def forward(self, x):
-        protos = self.p1.prototypes
-        plabels = self.p1.prototype_labels
+        protos, plabels = self.proto_layer()
         omegas = self.omegas
         dis = lomega_distance(x, protos, omegas)
         return dis, plabels
@@ -69,7 +67,7 @@ for epoch in range(100):
     optimizer.step()
 
     # Get the prototypes form the model
-    protos = model.p1.prototypes.data.numpy()
+    protos = model.proto_layer.components.numpy()
 
     # Visualize the data and the prototypes
     ax = fig.gca()

prototorch/__init__.py

@@ -1,21 +1,24 @@
 """ProtoTorch package."""
 
+import pkgutil
+
+import pkg_resources
+
+from . import components, datasets, functions, modules, utils
+from .datasets import *
+
 # Core Setup
-__version__ = "0.4.1"
+__version__ = "0.5.0"
 
 __all_core__ = [
     "datasets",
     "functions",
     "modules",
+    "components",
+    "utils",
 ]
 
-from .datasets import *
-
 # Plugin Loader
-import pkgutil
-
-import pkg_resources
-
 __path__ = pkgutil.extend_path(__path__, __name__)
 
 

prototorch/components/components.py

@@ -1,48 +1,54 @@
 """ProtoTorch components modules."""
 
 import warnings
-from typing import Tuple
 
 import torch
-from prototorch.components.initializers import (ComponentsInitializer,
-                                                EqualLabelInitializer,
+from prototorch.components.initializers import (ClassAwareInitializer,
+                                                ComponentsInitializer,
+                                                CustomLabelsInitializer,
+                                                EqualLabelsInitializer,
+                                                UnequalLabelsInitializer,
                                                 ZeroReasoningsInitializer)
-from prototorch.functions.initializers import get_initializer
 from torch.nn.parameter import Parameter
 
 
 class Components(torch.nn.Module):
     """Components is a set of learnable Tensors."""
     def __init__(self,
-                 number_of_components=None,
+                 num_components=None,
                  initializer=None,
                  *,
-                 initialized_components=None,
-                 dtype=torch.float32):
+                 initialized_components=None):
         super().__init__()
 
+        self.num_components = num_components
+
         # Ignore all initialization settings if initialized_components is given.
         if initialized_components is not None:
-            self._components = Parameter(initialized_components)
-            if number_of_components is not None or initializer is not None:
+            self.register_parameter("_components",
+                                    Parameter(initialized_components))
+            if num_components is not None or initializer is not None:
                 wmsg = "Arguments ignored while initializing Components"
                 warnings.warn(wmsg)
         else:
-            self._initialize_components(number_of_components, initializer)
+            self._initialize_components(initializer)
 
-    def _initialize_components(self, number_of_components, initializer):
+    def _precheck_initializer(self, initializer):
         if not isinstance(initializer, ComponentsInitializer):
             emsg = f"`initializer` has to be some subtype of " \
                 f"{ComponentsInitializer}. " \
                 f"You have provided: {initializer=} instead."
             raise TypeError(emsg)
-        self._components = Parameter(
-            initializer.generate(number_of_components))
+
+    def _initialize_components(self, initializer):
+        self._precheck_initializer(initializer)
+        _components = initializer.generate(self.num_components)
+        self.register_parameter("_components", Parameter(_components))
 
     @property
     def components(self):
         """Tensor containing the component tensors."""
-        return self._components.detach().cpu()
+        return self._components.detach()
 
     def forward(self):
         return self._components
@@ -57,29 +63,49 @@ class LabeledComponents(Components):
     Every Component has a label assigned.
     """
     def __init__(self,
-                 labels=None,
+                 distribution=None,
                  initializer=None,
                  *,
                  initialized_components=None):
         if initialized_components is not None:
-            super().__init__(initialized_components=initialized_components[0])
-            self._labels = initialized_components[1]
+            components, component_labels = initialized_components
+            super().__init__(initialized_components=components)
+            self._labels = component_labels
         else:
-            self._initialize_labels(labels)
-            super().__init__(number_of_components=len(self._labels),
-                             initializer=initializer)
+            _labels = self._initialize_labels(distribution)
+            super().__init__(len(_labels), initializer=initializer)
+            self.register_buffer("_labels", _labels)
 
-    def _initialize_labels(self, labels):
-        if type(labels) == tuple:
-            num_classes, prototypes_per_class = labels
-            labels = EqualLabelInitializer(num_classes, prototypes_per_class)
+    def _initialize_components(self, initializer):
+        if isinstance(initializer, ClassAwareInitializer):
+            self._precheck_initializer(initializer)
+            _components = initializer.generate(self.num_components,
+                                               self.distribution)
+            self.register_parameter("_components", Parameter(_components))
+        else:
+            super()._initialize_components(initializer)
 
-        self._labels = labels.generate()
+    def _initialize_labels(self, distribution):
+        if type(distribution) == dict:
+            if "num_classes" in distribution.keys():
+                labels = EqualLabelsInitializer(
+                    distribution["num_classes"],
+                    distribution["prototypes_per_class"])
+            else:
+                labels = CustomLabelsInitializer(distribution)
+        elif type(distribution) == tuple:
+            num_classes, prototypes_per_class = distribution
+            labels = EqualLabelsInitializer(num_classes, prototypes_per_class)
+        elif type(distribution) == list:
+            labels = UnequalLabelsInitializer(distribution)
+
+        self.distribution = labels.distribution
+        return labels.generate()
 
     @property
     def component_labels(self):
         """Tensor containing the component tensors."""
-        return self._labels.detach().cpu()
+        return self._labels.detach()
 
     def forward(self):
         return super().forward(), self._labels
@@ -106,20 +132,21 @@ class ReasoningComponents(Components):
                  *,
                  initialized_components=None):
         if initialized_components is not None:
-            super().__init__(initialized_components=initialized_components[0])
-            self._reasonings = initialized_components[1]
+            components, reasonings = initialized_components
+
+            super().__init__(initialized_components=components)
+            self.register_parameter("_reasonings", reasonings)
         else:
             self._initialize_reasonings(reasonings)
-            super().__init__(number_of_components=len(self._reasonings),
-                             initializer=initializer)
+            super().__init__(len(self._reasonings), initializer=initializer)
 
     def _initialize_reasonings(self, reasonings):
         if type(reasonings) == tuple:
-            num_classes, number_of_components = reasonings
-            reasonings = ZeroReasoningsInitializer(num_classes,
-                                                   number_of_components)
+            num_classes, num_components = reasonings
+            reasonings = ZeroReasoningsInitializer(num_classes, num_components)
 
-        self._reasonings = reasonings.generate()
+        _reasonings = reasonings.generate()
+        self.register_parameter("_reasonings", _reasonings)
 
     @property
     def reasonings(self):
@@ -128,7 +155,7 @@ class ReasoningComponents(Components):
         Dimension NxCx2
 
         """
-        return self._reasonings.detach().cpu()
+        return self._reasonings.detach()
 
     def forward(self):
         return super().forward(), self._reasonings

prototorch/components/initializers.py

@@ -1,17 +1,24 @@
 """ProtoTroch Initializers."""
 import warnings
 from collections.abc import Iterable
+from itertools import chain
 
 import torch
 from torch.utils.data import DataLoader, Dataset
 
 
-def parse_init_arg(arg):
-    if isinstance(arg, Dataset):
-        data, labels = next(iter(DataLoader(arg, batch_size=len(arg))))
-        # data = data.view(len(arg), -1)  # flatten
+def parse_data_arg(data_arg):
+    if isinstance(data_arg, Dataset):
+        data_arg = DataLoader(data_arg, batch_size=len(data_arg))
+
+    if isinstance(data_arg, DataLoader):
+        data = torch.tensor([])
+        labels = torch.tensor([])
+        for x, y in data_arg:
+            data = torch.cat([data, x])
+            labels = torch.cat([labels, y])
     else:
-        data, labels = arg
+        data, labels = data_arg
         if not isinstance(data, torch.Tensor):
             wmsg = f"Converting data to {torch.Tensor}."
             warnings.warn(wmsg)
@@ -62,19 +69,19 @@ class UniformInitializer(DimensionAwareInitializer):
         return torch.ones(gen_dims).uniform_(self.min, self.max)
 
 
-class PositionAwareInitializer(ComponentsInitializer):
-    def __init__(self, positions):
+class DataAwareInitializer(ComponentsInitializer):
+    def __init__(self, data):
         super().__init__()
-        self.data = positions
+        self.data = data
 
 
-class SelectionInitializer(PositionAwareInitializer):
+class SelectionInitializer(DataAwareInitializer):
     def generate(self, length):
         indices = torch.LongTensor(length).random_(0, len(self.data))
         return self.data[indices]
 
 
-class MeanInitializer(PositionAwareInitializer):
+class MeanInitializer(DataAwareInitializer):
     def generate(self, length):
         mean = torch.mean(self.data, dim=0)
         repeat_dim = [length] + [1] * len(mean.shape)
@@ -82,19 +89,39 @@ class MeanInitializer(PositionAwareInitializer):
 
 
 class ClassAwareInitializer(ComponentsInitializer):
-    def __init__(self, arg):
+    def __init__(self, data, transform=torch.nn.Identity()):
         super().__init__()
-        data, labels = parse_init_arg(arg)
+        data, labels = parse_data_arg(data)
         self.data = data
         self.labels = labels
 
+        self.transform = transform
+
         self.clabels = torch.unique(self.labels)
         self.num_classes = len(self.clabels)
 
+    def _get_samples_from_initializer(self, length, dist):
+        if not dist:
+            per_class = length // self.num_classes
+            dist = self.num_classes * [per_class]
+        if type(dist) == dict:
+            dist = dist.values()
+        samples_list = [
+            init.generate(n) for init, n in zip(self.initializers, dist)
+        ]
+        out = torch.vstack(samples_list)
+        with torch.no_grad():
+            out = self.transform(out)
+        return out
+
+    def __del__(self):
+        del self.data
+        del self.labels
+
 
 class StratifiedMeanInitializer(ClassAwareInitializer):
-    def __init__(self, arg):
-        super().__init__(arg)
+    def __init__(self, data, **kwargs):
+        super().__init__(data, **kwargs)
 
         self.initializers = []
         for clabel in self.clabels:
@@ -102,15 +129,14 @@ class StratifiedMeanInitializer(ClassAwareInitializer):
             class_initializer = MeanInitializer(class_data)
             self.initializers.append(class_initializer)
 
-    def generate(self, length):
-        per_class = length // self.num_classes
-        samples_list = [init.generate(per_class) for init in self.initializers]
-        return torch.vstack(samples_list)
+    def generate(self, length, dist=[]):
+        samples = self._get_samples_from_initializer(length, dist)
+        return samples
 
 
 class StratifiedSelectionInitializer(ClassAwareInitializer):
-    def __init__(self, arg, *, noise=None):
-        super().__init__(arg)
+    def __init__(self, data, noise=None, **kwargs):
+        super().__init__(data, **kwargs)
         self.noise = noise
 
         self.initializers = []
@@ -119,20 +145,20 @@ class StratifiedSelectionInitializer(ClassAwareInitializer):
             class_initializer = SelectionInitializer(class_data)
             self.initializers.append(class_initializer)
 
-    def add_noise(self, x):
+    def add_noise_v1(self, x):
+        return x + self.noise
+
+    def add_noise_v2(self, x):
         """Shifts some dimensions of the data randomly."""
         n1 = torch.rand_like(x)
         n2 = torch.rand_like(x)
         mask = torch.bernoulli(n1) - torch.bernoulli(n2)
         return x + (self.noise * mask)
 
-    def generate(self, length):
-        per_class = length // self.num_classes
-        samples_list = [init.generate(per_class) for init in self.initializers]
-        samples = torch.vstack(samples_list)
+    def generate(self, length, dist=[]):
+        samples = self._get_samples_from_initializer(length, dist)
         if self.noise is not None:
-            # samples = self.add_noise(samples)
-            samples = samples + self.noise
+            samples = self.add_noise_v1(samples)
         return samples
 
 
@@ -142,15 +168,43 @@ class LabelsInitializer:
         raise NotImplementedError("Subclasses should implement this!")
 
 
-class EqualLabelInitializer(LabelsInitializer):
+class UnequalLabelsInitializer(LabelsInitializer):
+    def __init__(self, dist):
+        self.dist = dist
+
+    @property
+    def distribution(self):
+        return self.dist
+
+    def generate(self, clabels=None, dist=None):
+        if not clabels:
+            clabels = range(len(self.dist))
+        if not dist:
+            dist = self.dist
+        labels = list(chain(*[[i] * n for i, n in zip(clabels, dist)]))
+        return torch.LongTensor(labels)
+
+
+class EqualLabelsInitializer(LabelsInitializer):
     def __init__(self, classes, per_class):
         self.classes = classes
         self.per_class = per_class
 
+    @property
+    def distribution(self):
+        return self.classes * [self.per_class]
+
     def generate(self):
         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):
@@ -170,3 +224,5 @@ class ZeroReasoningsInitializer(ReasoningsInitializer):
 SSI = StratifiedSampleInitializer = StratifiedSelectionInitializer
 SMI = StratifiedMeanInitializer
 Random = RandomInitializer = UniformInitializer
+Zeros = ZerosInitializer
+Ones = OnesInitializer

prototorch/datasets/__init__.py

@@ -1,11 +1,8 @@
 """ProtoTorch datasets."""
 
 from .abstract import NumpyDataset
+from .iris import Iris
 from .spiral import Spiral
 from .tecator import Tecator
 
-__all__ = [
-    "NumpyDataset",
-    "Spiral",
-    "Tecator",
-]
+__all__ = ['Iris', 'Spiral', 'Tecator']

prototorch/datasets/abstract.py

@@ -14,8 +14,10 @@ import torch
 
 class NumpyDataset(torch.utils.data.TensorDataset):
     """Create a PyTorch TensorDataset from NumPy arrays."""
-    def __init__(self, *arrays):
-        tensors = [torch.Tensor(arr) for arr in arrays]
+    def __init__(self, data, targets):
+        self.data = data
+        self.targets = targets
+        tensors = [torch.Tensor(data), torch.Tensor(targets)]
         super().__init__(*tensors)
 
 

prototorch/datasets/iris.py

@@ -0,0 +1,40 @@
+"""Thin wrapper for the Iris classification dataset from sklearn.
+
+URL:
+    https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_iris.html
+
+"""
+
+from typing import Sequence
+
+from prototorch.datasets.abstract import NumpyDataset
+from sklearn.datasets import load_iris
+
+
+class Iris(NumpyDataset):
+    """
+    Iris Dataset by Ronald Fisher introduced in 1936.
+
+    The dataset contains four measurements from flowers of three species of iris.
+
+    .. list-table:: Iris
+        :header-rows: 1
+
+        * - dimensions
+          - classes
+          - training size
+          - validation size
+          - test size
+        * - 4
+          - 3
+          - 150
+          - 0
+          - 0
+
+    :param dims: select a subset of dimensions
+    """
+    def __init__(self, dims: Sequence[int] = None):
+        x, y = load_iris(return_X_y=True)
+        if dims:
+            x = x[:, dims]
+        super().__init__(x, y)

prototorch/datasets/spiral.py

@@ -4,18 +4,22 @@ import numpy as np
 import torch
 
 
-def make_spiral(n_samples=500, noise=0.3):
+def make_spiral(num_samples=500, noise=0.3):
+    """Generates the Spiral Dataset.
+    
+    For use in Prototorch use `prototorch.datasets.Spiral` instead.
+    """
     def get_samples(n, delta_t):
         points = []
         for i in range(n):
-            r = i / n_samples * 5
+            r = i / num_samples * 5
             t = 1.75 * i / n * 2 * np.pi + delta_t
             x = r * np.sin(t) + np.random.rand(1) * noise
             y = r * np.cos(t) + np.random.rand(1) * noise
             points.append([x, y])
         return points
 
-    n = n_samples // 2
+    n = num_samples // 2
     positive = get_samples(n=n, delta_t=0)
     negative = get_samples(n=n, delta_t=np.pi)
     x = np.concatenate(
@@ -27,7 +31,27 @@ def make_spiral(n_samples=500, noise=0.3):
 
 
 class Spiral(torch.utils.data.TensorDataset):
-    """Spiral dataset for binary classification."""
-    def __init__(self, n_samples=500, noise=0.3):
-        x, y = make_spiral(n_samples, noise)
+    """Spiral dataset for binary classification.
+
+    This datasets consists of two spirals of two different classes.
+
+    .. list-table:: Spiral
+        :header-rows: 1
+
+        * - dimensions
+          - classes
+          - training size
+          - validation size
+          - test size
+        * - 2
+          - 2
+          - num_samples
+          - 0
+          - 0
+
+    :param num_samples: number of random samples
+    :param noise: noise added to the spirals
+    """
+    def __init__(self, num_samples: int = 500, noise: float = 0.3):
+        x, y = make_spiral(num_samples, noise)
         super().__init__(torch.Tensor(x), torch.LongTensor(y))

prototorch/datasets/tecator.py

@@ -40,15 +40,29 @@ import os
 
 import numpy as np
 import torch
-from torchvision.datasets.utils import download_file_from_google_drive
-
 from prototorch.datasets.abstract import ProtoDataset
+from torchvision.datasets.utils import download_file_from_google_drive
 
 
 class Tecator(ProtoDataset):
     """
-    `Tecator Dataset <http://lib.stat.cmu.edu/datasets/tecator>`__
-    for classification.
+    `Tecator Dataset <http://lib.stat.cmu.edu/datasets/tecator>`__ for classification.
+
+    The dataset contains wavelength measurements of meat.
+
+    .. list-table:: Tecator
+        :header-rows: 1
+
+        * - dimensions
+          - classes
+          - training size
+          - validation size
+          - test size
+        * - 100
+          - 2
+          - 129
+          - 43
+          - 43
     """
 
     _resources = [

prototorch/functions/competitions.py

@@ -3,15 +3,14 @@
 import torch
 
 
-# @torch.jit.script
 def stratified_min(distances, labels):
     clabels = torch.unique(labels, dim=0)
-    nclasses = clabels.size()[0]
-    if distances.size()[1] == nclasses:
+    num_classes = clabels.size()[0]
+    if distances.size()[1] == num_classes:
         # skip if only one prototype per class
         return distances
     batch_size = distances.size()[0]
-    winning_distances = torch.zeros(nclasses, batch_size)
+    winning_distances = torch.zeros(num_classes, batch_size)
     inf = torch.full_like(distances.T, fill_value=float("inf"))
     # distances_to_wpluses = torch.where(matcher, distances, inf)
     for i, cl in enumerate(clabels):
@@ -19,7 +18,7 @@ def stratified_min(distances, labels):
         matcher = torch.eq(labels.unsqueeze(dim=1), cl)
         if labels.ndim == 2:
             # if the labels are one-hot vectors
-            matcher = torch.eq(torch.sum(matcher, dim=-1), nclasses)
+            matcher = torch.eq(torch.sum(matcher, dim=-1), num_classes)
         cdists = torch.where(matcher, distances.T, inf).T
         winning_distances[i] = torch.min(cdists, dim=1,
                                          keepdim=True).values.squeeze()
@@ -31,15 +30,15 @@ def stratified_min(distances, labels):
     return winning_distances.T  # return with `batch_size` first
 
 
-# @torch.jit.script
 def wtac(distances, labels):
     winning_indices = torch.min(distances, dim=1).indices
     winning_labels = labels[winning_indices].squeeze()
     return winning_labels
 
 
-# @torch.jit.script
-def knnc(distances, labels, k):
-    winning_indices = torch.topk(-distances, k=k.item(), dim=1).indices
-    winning_labels = labels[winning_indices].squeeze()
+def knnc(distances, labels, k=1):
+    winning_indices = torch.topk(-distances, k=k, dim=1).indices
+    # winning_labels = torch.mode(labels[winning_indices].squeeze(),
+    #                             dim=1).values
+    winning_labels = torch.mode(labels[winning_indices], dim=1).values
     return winning_labels

prototorch/functions/distances.py

@@ -2,9 +2,8 @@
 
 import numpy as np
 import torch
-
 from prototorch.functions.helper import (_check_shapes, _int_and_mixed_shape,
-                                         equal_int_shape)
+                                         equal_int_shape, get_flat)
 
 
 def squared_euclidean_distance(x, y):
@@ -12,12 +11,10 @@ def squared_euclidean_distance(x, y):
 
     Compute :math:`{\langle \bm x - \bm y \rangle}_2`
 
-    :param `torch.tensor` x: Two dimensional vector
-    :param `torch.tensor` y: Two dimensional vector
-
     **Alias:**
     ``prototorch.functions.distances.sed``
     """
+    x, y = get_flat(x, y)
     expanded_x = x.unsqueeze(dim=1)
     batchwise_difference = y - expanded_x
     differences_raised = torch.pow(batchwise_difference, 2)
@@ -30,18 +27,17 @@ def euclidean_distance(x, y):
 
     Compute :math:`\sqrt{{\langle \bm x - \bm y \rangle}_2}`
 
-    :param `torch.tensor` x: Input Tensor of shape :math:`X \times N`
-    :param `torch.tensor` y: Input Tensor of shape :math:`Y \times N`
-
     :returns: Distance Tensor of shape :math:`X \times Y`
     :rtype: `torch.tensor`
     """
+    x, y = get_flat(x, y)
     distances_raised = squared_euclidean_distance(x, y)
     distances = torch.sqrt(distances_raised)
     return distances
 
 
 def euclidean_distance_v2(x, y):
+    x, y = get_flat(x, y)
     diff = y - x.unsqueeze(1)
     pairwise_distances = (diff @ diff.permute((0, 2, 1))).sqrt()
     # Passing `dim1=-2` and `dim2=-1` to `diagonal()` takes the
@@ -62,10 +58,9 @@ def lpnorm_distance(x, y, p):
 
     Calls ``torch.cdist``
 
-    :param `torch.tensor` x: Two dimensional vector
-    :param `torch.tensor` y: Two dimensional vector
     :param p: p parameter of the lp norm
     """
+    x, y = get_flat(x, y)
     distances = torch.cdist(x, y, p=p)
     return distances
 
@@ -75,10 +70,9 @@ def omega_distance(x, y, omega):
 
     Compute :math:`{\| \Omega \bm x - \Omega \bm y \|}_p`
 
-    :param `torch.tensor` x: Two dimensional vector
-    :param `torch.tensor` y: Two dimensional vector
     :param `torch.tensor` omega: Two dimensional matrix
     """
+    x, y = get_flat(x, y)
     projected_x = x @ omega
     projected_y = y @ omega
     distances = squared_euclidean_distance(projected_x, projected_y)
@@ -90,10 +84,9 @@ def lomega_distance(x, y, omegas):
 
     Compute :math:`{\| \Omega_k \bm x - \Omega_k \bm y_k \|}_p`
 
-    :param `torch.tensor` x: Two dimensional vector
-    :param `torch.tensor` y: Two dimensional vector
     :param `torch.tensor` omegas: Three dimensional matrix
     """
+    x, y = get_flat(x, y)
     projected_x = x @ omegas
     projected_y = torch.diagonal(y @ omegas).T
     expanded_y = torch.unsqueeze(projected_y, dim=1)

prototorch/functions/helper.py

@@ -1,6 +1,11 @@
 import torch
 
 
+def get_flat(*args):
+    rv = [x.view(x.size(0), -1) for x in args]
+    return rv
+
+
 def calculate_prototype_accuracy(y_pred, y_true, plabels):
     """Computes the accuracy of a prototype based model.
     via Winner-Takes-All rule.

prototorch/functions/initializers.py

@@ -15,59 +15,59 @@ def register_initializer(function):
 
 def labels_from(distribution, one_hot=True):
     """Takes a distribution tensor and returns a labels tensor."""
-    nclasses = distribution.shape[0]
-    llist = [[i] * n for i, n in zip(range(nclasses), distribution)]
+    num_classes = distribution.shape[0]
+    llist = [[i] * n for i, n in zip(range(num_classes), distribution)]
     # labels = [l for cl in llist for l in cl]  # flatten the list of lists
     flat_llist = list(chain(*llist))  # flatten label list with itertools.chain
     plabels = torch.tensor(flat_llist, requires_grad=False)
     if one_hot:
-        return torch.eye(nclasses)[plabels]
+        return torch.eye(num_classes)[plabels]
     return plabels
 
 
 @register_initializer
 def ones(x_train, y_train, prototype_distribution, one_hot=True):
-    nprotos = torch.sum(prototype_distribution)
-    protos = torch.ones(nprotos, *x_train.shape[1:])
+    num_protos = torch.sum(prototype_distribution)
+    protos = torch.ones(num_protos, *x_train.shape[1:])
     plabels = labels_from(prototype_distribution, one_hot)
     return protos, plabels
 
 
 @register_initializer
 def zeros(x_train, y_train, prototype_distribution, one_hot=True):
-    nprotos = torch.sum(prototype_distribution)
-    protos = torch.zeros(nprotos, *x_train.shape[1:])
+    num_protos = torch.sum(prototype_distribution)
+    protos = torch.zeros(num_protos, *x_train.shape[1:])
     plabels = labels_from(prototype_distribution, one_hot)
     return protos, plabels
 
 
 @register_initializer
 def rand(x_train, y_train, prototype_distribution, one_hot=True):
-    nprotos = torch.sum(prototype_distribution)
-    protos = torch.rand(nprotos, *x_train.shape[1:])
+    num_protos = torch.sum(prototype_distribution)
+    protos = torch.rand(num_protos, *x_train.shape[1:])
     plabels = labels_from(prototype_distribution, one_hot)
     return protos, plabels
 
 
 @register_initializer
 def randn(x_train, y_train, prototype_distribution, one_hot=True):
-    nprotos = torch.sum(prototype_distribution)
-    protos = torch.randn(nprotos, *x_train.shape[1:])
+    num_protos = torch.sum(prototype_distribution)
+    protos = torch.randn(num_protos, *x_train.shape[1:])
     plabels = labels_from(prototype_distribution, one_hot)
     return protos, plabels
 
 
 @register_initializer
 def stratified_mean(x_train, y_train, prototype_distribution, one_hot=True):
-    nprotos = torch.sum(prototype_distribution)
+    num_protos = torch.sum(prototype_distribution)
     pdim = x_train.shape[1]
-    protos = torch.empty(nprotos, pdim)
+    protos = torch.empty(num_protos, pdim)
     plabels = labels_from(prototype_distribution, one_hot)
     for i, label in enumerate(plabels):
         matcher = torch.eq(label.unsqueeze(dim=0), y_train)
         if one_hot:
-            nclasses = y_train.size()[1]
-            matcher = torch.eq(torch.sum(matcher, dim=-1), nclasses)
+            num_classes = y_train.size()[1]
+            matcher = torch.eq(torch.sum(matcher, dim=-1), num_classes)
         xl = x_train[matcher]
         mean_xl = torch.mean(xl, dim=0)
         protos[i] = mean_xl
@@ -81,15 +81,15 @@ def stratified_random(x_train,
                       prototype_distribution,
                       one_hot=True,
                       epsilon=1e-7):
-    nprotos = torch.sum(prototype_distribution)
+    num_protos = torch.sum(prototype_distribution)
     pdim = x_train.shape[1]
-    protos = torch.empty(nprotos, pdim)
+    protos = torch.empty(num_protos, pdim)
     plabels = labels_from(prototype_distribution, one_hot)
     for i, label in enumerate(plabels):
         matcher = torch.eq(label.unsqueeze(dim=0), y_train)
         if one_hot:
-            nclasses = y_train.size()[1]
-            matcher = torch.eq(torch.sum(matcher, dim=-1), nclasses)
+            num_classes = y_train.size()[1]
+            matcher = torch.eq(torch.sum(matcher, dim=-1), num_classes)
         xl = x_train[matcher]
         rand_index = torch.zeros(1).long().random_(0, xl.shape[0] - 1)
         random_xl = xl[rand_index]

prototorch/functions/losses.py

@@ -8,12 +8,12 @@ def _get_matcher(targets, labels):
     matcher = torch.eq(targets.unsqueeze(dim=1), labels)
     if labels.ndim == 2:
         # if the labels are one-hot vectors
-        nclasses = targets.size()[1]
-        matcher = torch.eq(torch.sum(matcher, dim=-1), nclasses)
+        num_classes = targets.size()[1]
+        matcher = torch.eq(torch.sum(matcher, dim=-1), num_classes)
     return matcher
 
 
-def _get_dp_dm(distances, targets, plabels):
+def _get_dp_dm(distances, targets, plabels, with_indices=False):
     """Returns the d+ and d- values for a batch of distances."""
     matcher = _get_matcher(targets, plabels)
     not_matcher = torch.bitwise_not(matcher)
@@ -21,9 +21,11 @@ def _get_dp_dm(distances, targets, plabels):
     inf = torch.full_like(distances, fill_value=float("inf"))
     d_matching = torch.where(matcher, distances, inf)
     d_unmatching = torch.where(not_matcher, distances, inf)
-    dp = torch.min(d_matching, dim=1, keepdim=True).values
-    dm = torch.min(d_unmatching, dim=1, keepdim=True).values
+    dp = torch.min(d_matching, dim=-1, keepdim=True)
+    dm = torch.min(d_unmatching, dim=-1, keepdim=True)
+    if with_indices:
         return dp, dm
+    return dp.values, dm.values
 
 
 def glvq_loss(distances, target_labels, prototype_labels):
@@ -53,4 +55,5 @@ def lvq21_loss(distances, target_labels, prototype_labels):
     """
     dp, dm = _get_dp_dm(distances, target_labels, prototype_labels)
     mu = dp - dm
+
     return mu

prototorch/modules/__init__.py

@@ -1,7 +1 @@
 """ProtoTorch modules."""
-
-from .prototypes import Prototypes1D
-
-__all__ = [
-    "Prototypes1D",
-]

prototorch/modules/models.py

@@ -1,11 +1,8 @@
 import torch
-from torch import nn
-
-from prototorch.functions.distances import (euclidean_distance_matrix,
-                                            tangent_distance)
-from prototorch.functions.helper import _check_shapes, _int_and_mixed_shape
+from prototorch.components import LabeledComponents, StratifiedMeanInitializer
+from prototorch.functions.distances import euclidean_distance_matrix
 from prototorch.functions.normalization import orthogonalization
-from prototorch.modules.prototypes import Prototypes1D
+from torch import nn
 
 
 class GTLVQ(nn.Module):
@@ -80,45 +77,35 @@ class GTLVQ(nn.Module):
         super(GTLVQ, self).__init__()
 
         self.num_protos = num_classes * prototypes_per_class
+        self.num_protos_class = prototypes_per_class
         self.subspace_size = feature_dim if subspace_size is None else subspace_size
         self.feature_dim = feature_dim
+        self.num_classes = num_classes
+
+        cls_initializer = StratifiedMeanInitializer(prototype_data)
+        cls_distribution = {
+            "num_classes": num_classes,
+            "prototypes_per_class": prototypes_per_class,
+        }
+
+        self.cls = LabeledComponents(cls_distribution, cls_initializer)
 
         if subspace_data is None:
             raise ValueError("Init Data must be specified!")
 
         self.tpt = tangent_projection_type
         with torch.no_grad():
-            if self.tpt == "local" or self.tpt == "local_proj":
-                self.init_local_subspace(subspace_data)
+            if self.tpt == "local":
+                self.init_local_subspace(subspace_data, subspace_size,
+                                         self.num_protos)
             elif self.tpt == "global":
                 self.init_gobal_subspace(subspace_data, subspace_size)
             else:
                 self.subspaces = None
 
-        # Hypothesis-Margin-Classifier
-        self.cls = Prototypes1D(
-            input_dim=feature_dim,
-            prototypes_per_class=prototypes_per_class,
-            nclasses=num_classes,
-            prototype_initializer="stratified_mean",
-            data=prototype_data,
-        )
-
     def forward(self, x):
-        # Tangent Projection
-        if self.tpt == "local_proj":
-            x_conform = (x.unsqueeze(1).repeat_interleave(self.num_protos,
-                                                          1).unsqueeze(2))
-            dis, proj_x = self.local_tangent_projection(x_conform)
-
-            proj_x = proj_x.reshape(x.shape[0] * self.num_protos,
-                                    self.feature_dim)
-            return proj_x, dis
-        elif self.tpt == "local":
-            x_conform = (x.unsqueeze(1).repeat_interleave(self.num_protos,
-                                                          1).unsqueeze(2))
-            dis = tangent_distance(x_conform, self.cls.prototypes,
-                                   self.subspaces)
+        if self.tpt == "local":
+            dis = self.local_tangent_distances(x)
         elif self.tpt == "gloabl":
             dis = self.global_tangent_distances(x)
         else:
@@ -131,16 +118,14 @@ class GTLVQ(nn.Module):
         _, _, v = torch.svd(data)
         subspace = (torch.eye(v.shape[0]) - (v @ v.T)).T
         subspaces = subspace[:, :num_subspaces]
-        self.subspaces = (torch.nn.Parameter(
-            subspaces).clone().detach().requires_grad_(True))
+        self.subspaces = nn.Parameter(subspaces, requires_grad=True)
 
-    def init_local_subspace(self, data):
-        _, _, v = torch.svd(data)
-        inital_projector = (torch.eye(v.shape[0]) - (v @ v.T)).T
-        subspaces = inital_projector.unsqueeze(0).repeat_interleave(
-            self.num_protos, 0)
-        self.subspaces = (torch.nn.Parameter(
-            subspaces).clone().detach().requires_grad_(True))
+    def init_local_subspace(self, data, num_subspaces, num_protos):
+        data = data - torch.mean(data, dim=0)
+        _, _, v = torch.svd(data, some=False)
+        v = v[:, :num_subspaces]
+        subspaces = v.unsqueeze(0).repeat_interleave(num_protos, 0)
+        self.subspaces = nn.Parameter(subspaces, requires_grad=True)
 
     def global_tangent_distances(self, x):
         # Tangent Projection
@@ -151,37 +136,26 @@ class GTLVQ(nn.Module):
         # Euclidean Distance
         return euclidean_distance_matrix(x, projected_prototypes)
 
-    def local_tangent_projection(self, signals):
-        # Note: subspaces is always assumed as transposed and must be orthogonal!
-        # shape(signals): batch x proto_number x channels x dim1 x dim2 x ... x dimN
-        # shape(protos): proto_number x dim1 x dim2 x ... x dimN
-        # shape(subspaces): (optional [proto_number]) x prod(dim1 * dim2 * ... * dimN)  x prod(projected_atom_shape)
-        # subspace should be orthogonalized
-        # Origin Source Code
-        # Origin Author:
-        protos = self.cls.prototypes
-        subspaces = self.subspaces
-        signal_shape, signal_int_shape = _int_and_mixed_shape(signals)
-        _, proto_int_shape = _int_and_mixed_shape(protos)
+    def local_tangent_distances(self, x):
 
-        # check if the shapes are correct
-        _check_shapes(signal_int_shape, proto_int_shape)
-
-        # Tangent Data Projections
-        projected_protos = torch.bmm(protos.unsqueeze(1), subspaces).squeeze(1)
-        data = signals.squeeze(2).permute([1, 0, 2])
-        projected_data = torch.bmm(data, subspaces)
-        projected_data = projected_data.permute([1, 0, 2]).unsqueeze(1)
-        diff = projected_data - projected_protos
-        projected_diff = torch.reshape(
-            diff, (signal_shape[1], signal_shape[0], signal_shape[2]) +
-            signal_shape[3:])
-        diss = torch.norm(projected_diff, 2, dim=-1)
-        return diss.permute([1, 0, 2]).squeeze(-1), projected_data.squeeze(1)
+        # Tangent Distance
+        x = x.unsqueeze(1).expand(x.size(0), self.cls.num_components,
+                                  x.size(-1))
+        protos = self.cls()[0].unsqueeze(0).expand(x.size(0),
+                                                   self.cls.num_components,
+                                                   x.size(-1))
+        projectors = torch.eye(
+            self.subspaces.shape[-2], device=x.device) - torch.bmm(
+                self.subspaces, self.subspaces.permute([0, 2, 1]))
+        diff = (x - protos)
+        diff = diff.permute([1, 0, 2])
+        diff = torch.bmm(diff, projectors)
+        diff = torch.norm(diff, 2, dim=-1).T
+        return diff
 
     def get_parameters(self):
         return {
-            "params": self.cls.prototypes,
+            "params": self.cls.components,
         }, {
             "params": self.subspaces
         }

prototorch/modules/prototypes.py

@@ -1,137 +0,0 @@
-"""ProtoTorch prototype modules."""
-
-import warnings
-
-import torch
-
-from prototorch.functions.initializers import get_initializer
-
-
-class _Prototypes(torch.nn.Module):
-    """Abstract prototypes class."""
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-
-    def _validate_prototype_distribution(self):
-        if 0 in self.prototype_distribution:
-            warnings.warn("Are you sure about the `0` in "
-                          "`prototype_distribution`?")
-
-    def extra_repr(self):
-        return f"prototypes.shape: {tuple(self.prototypes.shape)}"
-
-    def forward(self):
-        return self.prototypes, self.prototype_labels
-
-
-class Prototypes1D(_Prototypes):
-    """Create a learnable set of one-dimensional prototypes.
-
-    TODO Complete this doc-string.
-    """
-    def __init__(
-        self,
-        prototypes_per_class=1,
-        prototype_initializer="ones",
-        prototype_distribution=None,
-        data=None,
-        dtype=torch.float32,
-        one_hot_labels=False,
-        **kwargs,
-    ):
-        warnings.warn(
-            PendingDeprecationWarning(
-                "Prototypes1D will be replaced in future versions."))
-
-        # Convert tensors to python lists before processing
-        if prototype_distribution is not None:
-            if not isinstance(prototype_distribution, list):
-                prototype_distribution = prototype_distribution.tolist()
-
-        if data is None:
-            if "input_dim" not in kwargs:
-                raise NameError("`input_dim` required if "
-                                "no `data` is provided.")
-            if prototype_distribution:
-                kwargs_nclasses = sum(prototype_distribution)
-            else:
-                if "nclasses" not in kwargs:
-                    raise NameError("`prototype_distribution` required if "
-                                    "both `data` and `nclasses` are not "
-                                    "provided.")
-                kwargs_nclasses = kwargs.pop("nclasses")
-            input_dim = kwargs.pop("input_dim")
-            if prototype_initializer in [
-                    "stratified_mean", "stratified_random"
-            ]:
-                warnings.warn(
-                    f"`prototype_initializer`: `{prototype_initializer}` "
-                    "requires `data`, but `data` is not provided. "
-                    "Using randomly generated data instead.")
-            x_train = torch.rand(kwargs_nclasses, input_dim)
-            y_train = torch.arange(kwargs_nclasses)
-            if one_hot_labels:
-                y_train = torch.eye(kwargs_nclasses)[y_train]
-            data = [x_train, y_train]
-
-        x_train, y_train = data
-        x_train = torch.as_tensor(x_train).type(dtype)
-        y_train = torch.as_tensor(y_train).type(torch.int)
-        nclasses = torch.unique(y_train, dim=-1).shape[-1]
-
-        if nclasses == 1:
-            warnings.warn("Are you sure about having one class only?")
-
-        if x_train.ndim != 2:
-            raise ValueError("`data[0].ndim != 2`.")
-
-        if y_train.ndim == 2:
-            if y_train.shape[1] == 1 and one_hot_labels:
-                raise ValueError("`one_hot_labels` is set to `True` "
-                                 "but target labels are not one-hot-encoded.")
-            if y_train.shape[1] != 1 and not one_hot_labels:
-                raise ValueError("`one_hot_labels` is set to `False` "
-                                 "but target labels in `data` "
-                                 "are one-hot-encoded.")
-        if y_train.ndim == 1 and one_hot_labels:
-            raise ValueError("`one_hot_labels` is set to `True` "
-                             "but target labels are not one-hot-encoded.")
-
-        # Verify input dimension if `input_dim` is provided
-        if "input_dim" in kwargs:
-            input_dim = kwargs.pop("input_dim")
-            if input_dim != x_train.shape[1]:
-                raise ValueError(f"Provided `input_dim`={input_dim} does "
-                                 "not match data dimension "
-                                 f"`data[0].shape[1]`={x_train.shape[1]}")
-
-        # Verify the number of classes if `nclasses` is provided
-        if "nclasses" in kwargs:
-            kwargs_nclasses = kwargs.pop("nclasses")
-            if kwargs_nclasses != nclasses:
-                raise ValueError(f"Provided `nclasses={kwargs_nclasses}` does "
-                                 "not match data labels "
-                                 "`torch.unique(data[1]).shape[0]`"
-                                 f"={nclasses}")
-
-        super().__init__(**kwargs)
-
-        if not prototype_distribution:
-            prototype_distribution = [prototypes_per_class] * nclasses
-        with torch.no_grad():
-            self.prototype_distribution = torch.tensor(prototype_distribution)
-
-        self._validate_prototype_distribution()
-
-        self.prototype_initializer = get_initializer(prototype_initializer)
-        prototypes, prototype_labels = self.prototype_initializer(
-            x_train,
-            y_train,
-            prototype_distribution=self.prototype_distribution,
-            one_hot=one_hot_labels,
-        )
-
-        # Register module parameters
-        self.prototypes = torch.nn.Parameter(prototypes)
-        self.prototype_labels = torch.nn.Parameter(
-            prototype_labels.type(dtype)).requires_grad_(False)

setup.py

@@ -20,6 +20,7 @@ INSTALL_REQUIRES = [
     "torch>=1.3.1",
     "torchvision>=0.5.0",
     "numpy>=1.9.1",
+    "sklearn",
 ]
 DATASETS = [
     "requests",
@@ -31,9 +32,9 @@ DOCS = [
     "sphinx",
     "sphinx_rtd_theme",
     "sphinxcontrib-katex",
+    "sphinx-autodoc-typehints",
 ]
 EXAMPLES = [
-    "sklearn",
     "matplotlib",
     "torchinfo",
 ]
@@ -42,7 +43,7 @@ ALL = DATASETS + DEV + DOCS + EXAMPLES + TESTS
 
 setup(
     name="prototorch",
-    version="0.4.1",
+    version="0.5.0",
     description="Highly extensible, GPU-supported "
     "Learning Vector Quantization (LVQ) toolbox "
     "built using PyTorch and its nn API.",

tests/test_components.py

@@ -0,0 +1,25 @@
+"""ProtoTorch components test suite."""
+
+import prototorch as pt
+import torch
+
+
+def test_labcomps_zeros_init():
+    protos = torch.zeros(3, 2)
+    c = pt.components.LabeledComponents(
+        distribution=[1, 1, 1],
+        initializer=pt.components.Zeros(2),
+    )
+    assert (c.components == protos).any() == True
+
+
+def test_labcomps_warmstart():
+    protos = torch.randn(3, 2)
+    plabels = torch.tensor([1, 2, 3])
+    c = pt.components.LabeledComponents(
+        distribution=[1, 1, 1],
+        initializer=None,
+        initialized_components=[protos, plabels],
+    )
+    assert (c.components == protos).any() == True
+    assert (c.component_labels == plabels).any() == True

tests/test_functions.py

@@ -4,7 +4,6 @@ import unittest
 
 import numpy as np
 import torch
-
 from prototorch.functions import (activations, competitions, distances,
                                   initializers, losses)
 
@@ -139,7 +138,7 @@ class TestCompetitions(unittest.TestCase):
     def test_knnc_k1(self):
         d = torch.tensor([[2.0, 3.0, 1.99, 3.01], [2.0, 3.0, 2.01, 3.0]])
         labels = torch.tensor([0, 1, 2, 3])
-        actual = competitions.knnc(d, labels, k=torch.tensor([1]))
+        actual = competitions.knnc(d, labels, k=1)
         desired = torch.tensor([2, 0])
         mismatch = np.testing.assert_array_almost_equal(actual,
                                                         desired,

tests/test_modules.py

@@ -1,298 +0,0 @@
-"""ProtoTorch modules test suite."""
-
-import unittest
-
-import numpy as np
-import torch
-
-from prototorch.modules import losses, prototypes
-
-
-class TestPrototypes(unittest.TestCase):
-    def setUp(self):
-        self.x = torch.tensor(
-            [[0, -1, -2], [10, 11, 12], [0, 0, 0], [2, 2, 2]],
-            dtype=torch.float32)
-        self.y = torch.tensor([0, 0, 1, 1])
-        self.gen = torch.manual_seed(42)
-
-    def test_prototypes1d_init_without_input_dim(self):
-        with self.assertRaises(NameError):
-            _ = prototypes.Prototypes1D(nclasses=2)
-
-    def test_prototypes1d_init_without_nclasses(self):
-        with self.assertRaises(NameError):
-            _ = prototypes.Prototypes1D(input_dim=1)
-
-    def test_prototypes1d_init_with_nclasses_1(self):
-        with self.assertWarns(UserWarning):
-            _ = prototypes.Prototypes1D(nclasses=1, input_dim=1)
-
-    def test_prototypes1d_init_without_pdist(self):
-        p1 = prototypes.Prototypes1D(
-            input_dim=6,
-            nclasses=2,
-            prototypes_per_class=4,
-            prototype_initializer="ones",
-        )
-        protos = p1.prototypes
-        actual = protos.detach().numpy()
-        desired = torch.ones(8, 6)
-        mismatch = np.testing.assert_array_almost_equal(actual,
-                                                        desired,
-                                                        decimal=5)
-        self.assertIsNone(mismatch)
-
-    def test_prototypes1d_init_without_data(self):
-        pdist = [2, 2]
-        p1 = prototypes.Prototypes1D(input_dim=3,
-                                     prototype_distribution=pdist,
-                                     prototype_initializer="zeros")
-        protos = p1.prototypes
-        actual = protos.detach().numpy()
-        desired = torch.zeros(4, 3)
-        mismatch = np.testing.assert_array_almost_equal(actual,
-                                                        desired,
-                                                        decimal=5)
-        self.assertIsNone(mismatch)
-
-    def test_prototypes1d_proto_init_without_data(self):
-        with self.assertWarns(UserWarning):
-            _ = prototypes.Prototypes1D(
-                input_dim=3,
-                nclasses=2,
-                prototypes_per_class=1,
-                prototype_initializer="stratified_mean",
-                data=None,
-            )
-
-    def test_prototypes1d_init_torch_pdist(self):
-        pdist = torch.tensor([2, 2])
-        p1 = prototypes.Prototypes1D(input_dim=3,
-                                     prototype_distribution=pdist,
-                                     prototype_initializer="zeros")
-        protos = p1.prototypes
-        actual = protos.detach().numpy()
-        desired = torch.zeros(4, 3)
-        mismatch = np.testing.assert_array_almost_equal(actual,
-                                                        desired,
-                                                        decimal=5)
-        self.assertIsNone(mismatch)
-
-    def test_prototypes1d_init_without_inputdim_with_data(self):
-        _ = prototypes.Prototypes1D(
-            nclasses=2,
-            prototypes_per_class=1,
-            prototype_initializer="stratified_mean",
-            data=[[[1.0], [0.0]], [1, 0]],
-        )
-
-    def test_prototypes1d_init_with_int_data(self):
-        _ = prototypes.Prototypes1D(
-            nclasses=2,
-            prototypes_per_class=1,
-            prototype_initializer="stratified_mean",
-            data=[[[1], [0]], [1, 0]],
-        )
-
-    def test_prototypes1d_init_one_hot_without_data(self):
-        _ = prototypes.Prototypes1D(
-            input_dim=1,
-            nclasses=2,
-            prototypes_per_class=1,
-            prototype_initializer="stratified_mean",
-            data=None,
-            one_hot_labels=True,
-        )
-
-    def test_prototypes1d_init_one_hot_labels_false(self):
-        """Test if ValueError is raised when `one_hot_labels` is set to `False`
-        but the provided `data` has one-hot encoded labels.
-        """
-        with self.assertRaises(ValueError):
-            _ = prototypes.Prototypes1D(
-                input_dim=1,
-                nclasses=2,
-                prototypes_per_class=1,
-                prototype_initializer="stratified_mean",
-                data=([[0.0], [1.0]], [[0, 1], [1, 0]]),
-                one_hot_labels=False,
-            )
-
-    def test_prototypes1d_init_1d_y_data_one_hot_labels_true(self):
-        """Test if ValueError is raised when `one_hot_labels` is set to `True`
-        but the provided `data` does not contain one-hot encoded labels.
-        """
-        with self.assertRaises(ValueError):
-            _ = prototypes.Prototypes1D(
-                input_dim=1,
-                nclasses=2,
-                prototypes_per_class=1,
-                prototype_initializer="stratified_mean",
-                data=([[0.0], [1.0]], [0, 1]),
-                one_hot_labels=True,
-            )
-
-    def test_prototypes1d_init_one_hot_labels_true(self):
-        """Test if ValueError is raised when `one_hot_labels` is set to `True`
-        but the provided `data` contains 2D targets but
-        does not contain one-hot encoded labels.
-        """
-        with self.assertRaises(ValueError):
-            _ = prototypes.Prototypes1D(
-                input_dim=1,
-                nclasses=2,
-                prototypes_per_class=1,
-                prototype_initializer="stratified_mean",
-                data=([[0.0], [1.0]], [[0], [1]]),
-                one_hot_labels=True,
-            )
-
-    def test_prototypes1d_init_with_int_dtype(self):
-        with self.assertRaises(RuntimeError):
-            _ = prototypes.Prototypes1D(
-                nclasses=2,
-                prototypes_per_class=1,
-                prototype_initializer="stratified_mean",
-                data=[[[1], [0]], [1, 0]],
-                dtype=torch.int32,
-            )
-
-    def test_prototypes1d_inputndim_with_data(self):
-        with self.assertRaises(ValueError):
-            _ = prototypes.Prototypes1D(input_dim=1,
-                                        nclasses=1,
-                                        prototypes_per_class=1,
-                                        data=[[1.0], [1]])
-
-    def test_prototypes1d_inputdim_with_data(self):
-        with self.assertRaises(ValueError):
-            _ = prototypes.Prototypes1D(
-                input_dim=2,
-                nclasses=2,
-                prototypes_per_class=1,
-                prototype_initializer="stratified_mean",
-                data=[[[1.0], [0.0]], [1, 0]],
-            )
-
-    def test_prototypes1d_nclasses_with_data(self):
-        """Test ValueError raise if provided `nclasses` is not the same
-        as the one computed from the provided `data`.
-        """
-        with self.assertRaises(ValueError):
-            _ = prototypes.Prototypes1D(
-                input_dim=1,
-                nclasses=1,
-                prototypes_per_class=1,
-                prototype_initializer="stratified_mean",
-                data=[[[1.0], [2.0]], [1, 2]],
-            )
-
-    def test_prototypes1d_init_with_ppc(self):
-        p1 = prototypes.Prototypes1D(data=[self.x, self.y],
-                                     prototypes_per_class=2,
-                                     prototype_initializer="zeros")
-        protos = p1.prototypes
-        actual = protos.detach().numpy()
-        desired = torch.zeros(4, 3)
-        mismatch = np.testing.assert_array_almost_equal(actual,
-                                                        desired,
-                                                        decimal=5)
-        self.assertIsNone(mismatch)
-
-    def test_prototypes1d_init_with_pdist(self):
-        p1 = prototypes.Prototypes1D(
-            data=[self.x, self.y],
-            prototype_distribution=[6, 9],
-            prototype_initializer="zeros",
-        )
-        protos = p1.prototypes
-        actual = protos.detach().numpy()
-        desired = torch.zeros(15, 3)
-        mismatch = np.testing.assert_array_almost_equal(actual,
-                                                        desired,
-                                                        decimal=5)
-        self.assertIsNone(mismatch)
-
-    def test_prototypes1d_func_initializer(self):
-        def my_initializer(*args, **kwargs):
-            return torch.full((2, 99), 99.0), torch.tensor([0, 1])
-
-        p1 = prototypes.Prototypes1D(
-            input_dim=99,
-            nclasses=2,
-            prototypes_per_class=1,
-            prototype_initializer=my_initializer,
-        )
-        protos = p1.prototypes
-        actual = protos.detach().numpy()
-        desired = 99 * torch.ones(2, 99)
-        mismatch = np.testing.assert_array_almost_equal(actual,
-                                                        desired,
-                                                        decimal=5)
-        self.assertIsNone(mismatch)
-
-    def test_prototypes1d_forward(self):
-        p1 = prototypes.Prototypes1D(data=[self.x, self.y])
-        protos, _ = p1()
-        actual = protos.detach().numpy()
-        desired = torch.ones(2, 3)
-        mismatch = np.testing.assert_array_almost_equal(actual,
-                                                        desired,
-                                                        decimal=5)
-        self.assertIsNone(mismatch)
-
-    def test_prototypes1d_dist_validate(self):
-        p1 = prototypes.Prototypes1D(input_dim=0, prototype_distribution=[0])
-        with self.assertWarns(UserWarning):
-            _ = p1._validate_prototype_distribution()
-
-    def test_prototypes1d_validate_extra_repr_not_empty(self):
-        p1 = prototypes.Prototypes1D(input_dim=0, prototype_distribution=[0])
-        rep = p1.extra_repr()
-        self.assertNotEqual(rep, "")
-
-    def tearDown(self):
-        del self.x, self.y, self.gen
-        _ = torch.seed()
-
-
-class TestLosses(unittest.TestCase):
-    def setUp(self):
-        pass
-
-    def test_glvqloss_init(self):
-        _ = losses.GLVQLoss(0, "swish_beta", beta=20)
-
-    def test_glvqloss_forward_1ppc(self):
-        criterion = losses.GLVQLoss(margin=0,
-                                    squashing="sigmoid_beta",
-                                    beta=100)
-        d = torch.stack([torch.ones(100), torch.zeros(100)], dim=1)
-        labels = torch.tensor([0, 1])
-        targets = torch.ones(100)
-        outputs = [d, labels]
-        loss = criterion(outputs, targets)
-        loss_value = loss.item()
-        self.assertAlmostEqual(loss_value, 0.0)
-
-    def test_glvqloss_forward_2ppc(self):
-        criterion = losses.GLVQLoss(margin=0,
-                                    squashing="sigmoid_beta",
-                                    beta=100)
-        d = torch.stack([
-            torch.ones(100),
-            torch.ones(100),
-            torch.zeros(100),
-            torch.ones(100)
-        ],
-                        dim=1)
-        labels = torch.tensor([0, 0, 1, 1])
-        targets = torch.ones(100)
-        outputs = [d, labels]
-        loss = criterion(outputs, targets)
-        loss_value = loss.item()
-        self.assertAlmostEqual(loss_value, 0.0)
-
-    def tearDown(self):
-        pass