refactor: minor changes in probabilistic.py

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.3.0
+current_version = 0.2.0
 commit = True
 tag = True
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)

.pre-commit-config.yaml

@@ -18,12 +18,12 @@ repos:
   - id: autoflake
 
 - repo: http://github.com/PyCQA/isort
-  rev: 5.9.3
+  rev: 5.8.0
   hooks:
   - id: isort
 
 - repo: https://github.com/pre-commit/mirrors-mypy
-  rev: v0.910-1
+  rev: v0.902
   hooks:
   - id: mypy
     files: prototorch
@@ -42,10 +42,9 @@ repos:
   - id: python-check-blanket-noqa
 
 - repo: https://github.com/asottile/pyupgrade
-  rev: v2.29.0
+  rev: v2.19.4
   hooks:
   - id: pyupgrade
-    args: [--py36-plus]
 
 - repo: https://github.com/si-cim/gitlint
   rev: v0.15.2-unofficial

.travis.yml

@@ -1,11 +1,7 @@
 dist: bionic
 sudo: false
 language: python
-python:
-  - 3.9
-  - 3.8
-  - 3.7
-  - 3.6
+python: 3.9
 cache:
   directories:
   - "$HOME/.cache/pip"
@@ -19,26 +15,11 @@ script:
 - ./tests/test_examples.sh examples/
 after_success:
 - bash <(curl -s https://codecov.io/bash)
-
-# Publish on PyPI
-jobs:
-  include:
-    - stage: build
-      python: 3.9
-      script: echo "Starting Pypi build"
-      deploy:
-        provider: pypi
-        username: __token__
-        distributions: "sdist bdist_wheel"
-        password:
-          secure: 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
-        on:
-          tags: true
-          skip_existing: true
-
-# The password is encrypted with:
-# `cd prototorch && travis encrypt your-pypi-api-token --add deploy.password`
-# See https://docs.travis-ci.com/user/deployment/pypi and
-# https://github.com/travis-ci/travis.rb#installation
-# for more details
-# Note: The encrypt command does not work well in ZSH.
+deploy:
+  provider: pypi
+  username: __token__
+  password:
+    secure: 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
+  on:
+    tags: true
+    skip_existing: true

docs/source/conf.py

@@ -23,7 +23,7 @@ author = "Jensun Ravichandran"
 
 # The full version, including alpha/beta/rc tags
 #
-release = "0.3.0"
+release = "0.2.0"
 
 # -- General configuration ---------------------------------------------------
 

examples/binnam_tecator.py

@@ -0,0 +1,81 @@
+"""Neural Additive Model (NAM) example for binary classification."""
+
+import argparse
+
+import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from matplotlib import pyplot as plt
+
+if __name__ == "__main__":
+    # Command-line arguments
+    parser = argparse.ArgumentParser()
+    parser = pl.Trainer.add_argparse_args(parser)
+    args = parser.parse_args()
+
+    # Dataset
+    train_ds = pt.datasets.Tecator("~/datasets")
+
+    # Dataloaders
+    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=64)
+
+    # Hyperparameters
+    hparams = dict(lr=0.1)
+
+    # Define the feature extractor
+    class FE(torch.nn.Module):
+        def __init__(self):
+            super().__init__()
+            self.modules_list = torch.nn.ModuleList([
+                torch.nn.Linear(1, 3),
+                torch.nn.Sigmoid(),
+                torch.nn.Linear(3, 1),
+                torch.nn.Sigmoid(),
+            ])
+
+        def forward(self, x):
+            for m in self.modules_list:
+                x = m(x)
+            return x
+
+    # Initialize the model
+    model = pt.models.BinaryNAM(
+        hparams,
+        extractors=torch.nn.ModuleList([FE() for _ in range(100)]),
+    )
+
+    # Compute intermediate input and output sizes
+    model.example_input_array = torch.zeros(4, 100)
+
+    # Callbacks
+    es = pl.callbacks.EarlyStopping(
+        monitor="train_loss",
+        min_delta=0.001,
+        patience=20,
+        mode="min",
+        verbose=True,
+        check_on_train_epoch_end=True,
+    )
+
+    # Setup trainer
+    trainer = pl.Trainer.from_argparse_args(
+        args,
+        callbacks=[
+            es,
+        ],
+        terminate_on_nan=True,
+        weights_summary=None,
+        accelerator="ddp",
+    )
+
+    # Training loop
+    trainer.fit(model, train_loader)
+
+    # Visualize extractor shape functions
+    fig, axes = plt.subplots(10, 10)
+    for i, ax in enumerate(axes.flat):
+        x = torch.linspace(-2, 2, 100)  # TODO use min/max from data
+        y = model.extractors[i](x.view(100, 1)).squeeze().detach()
+        ax.plot(x, y)
+        ax.set(title=f"Feature {i + 1}", xticklabels=[], yticklabels=[])
+    plt.show()

examples/binnam_xor.py

@@ -0,0 +1,86 @@
+"""Neural Additive Model (NAM) example for binary classification."""
+
+import argparse
+
+import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from matplotlib import pyplot as plt
+
+if __name__ == "__main__":
+    # Command-line arguments
+    parser = argparse.ArgumentParser()
+    parser = pl.Trainer.add_argparse_args(parser)
+    args = parser.parse_args()
+
+    # Dataset
+    train_ds = pt.datasets.XOR()
+
+    # Dataloaders
+    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=256)
+
+    # Hyperparameters
+    hparams = dict(lr=0.001)
+
+    # Define the feature extractor
+    class FE(torch.nn.Module):
+        def __init__(self, hidden_size=10):
+            super().__init__()
+            self.modules_list = torch.nn.ModuleList([
+                torch.nn.Linear(1, hidden_size),
+                torch.nn.ReLU(),
+                torch.nn.Linear(hidden_size, 1),
+                torch.nn.ReLU(),
+            ])
+
+        def forward(self, x):
+            for m in self.modules_list:
+                x = m(x)
+            return x
+
+    # Initialize the model
+    model = pt.models.BinaryNAM(
+        hparams,
+        extractors=torch.nn.ModuleList([FE(20) for _ in range(2)]),
+    )
+
+    # Compute intermediate input and output sizes
+    model.example_input_array = torch.zeros(4, 2)
+
+    # Summary
+    print(model)
+
+    # Callbacks
+    vis = pt.models.Vis2D(data=train_ds)
+    es = pl.callbacks.EarlyStopping(
+        monitor="train_loss",
+        min_delta=0.001,
+        patience=50,
+        mode="min",
+        verbose=False,
+        check_on_train_epoch_end=True,
+    )
+
+    # Setup trainer
+    trainer = pl.Trainer.from_argparse_args(
+        args,
+        callbacks=[
+            vis,
+            es,
+        ],
+        terminate_on_nan=True,
+        weights_summary="full",
+        accelerator="ddp",
+    )
+
+    # Training loop
+    trainer.fit(model, train_loader)
+
+    # Visualize extractor shape functions
+    fig, axes = plt.subplots(2)
+    for i, ax in enumerate(axes.flat):
+        x = torch.linspace(0, 1, 100)  # TODO use min/max from data
+        y = model.extractors[i](x.view(100, 1)).squeeze().detach()
+        ax.plot(x, y)
+        ax.set(title=f"Feature {i + 1}")
+    plt.show()

examples/cbc_iris.py

@@ -38,12 +38,10 @@ if __name__ == "__main__":
     )
 
     # Callbacks
-    vis = pt.models.Visualize2DVoronoiCallback(
-        data=train_ds,
-        title="CBC Iris Example",
-        resolution=100,
-        axis_off=True,
-    )
+    vis = pt.models.VisCBC2D(data=train_ds,
+                             title="CBC Iris Example",
+                             resolution=100,
+                             axis_off=True)
 
     # Setup trainer
     trainer = pl.Trainer.from_argparse_args(

examples/cli/README.md

@@ -0,0 +1,8 @@
+# Examples using Lightning CLI
+
+Examples in this folder use the experimental [Lightning CLI](https://pytorch-lightning.readthedocs.io/en/latest/common/lightning_cli.html).
+
+To use the example run
+```
+python gmlvq.py --config gmlvq.yaml
+```

examples/cli/gmlvq.py

@@ -0,0 +1,19 @@
+"""GMLVQ example using the MNIST dataset."""
+
+import prototorch as pt
+import torch
+from prototorch.models import ImageGMLVQ
+from prototorch.models.abstract import PrototypeModel
+from prototorch.models.data import MNISTDataModule
+from pytorch_lightning.utilities.cli import LightningCLI
+
+
+class ExperimentClass(ImageGMLVQ):
+    def __init__(self, hparams, **kwargs):
+        super().__init__(hparams,
+                         optimizer=torch.optim.Adam,
+                         prototype_initializer=pt.components.zeros(28 * 28),
+                         **kwargs)
+
+
+cli = LightningCLI(ImageGMLVQ, MNISTDataModule)

examples/cli/gmlvq.yaml

@@ -0,0 +1,11 @@
+model:
+  hparams:
+    input_dim: 784
+    latent_dim: 784
+    distribution:
+      num_classes: 10
+      prototypes_per_class: 2
+    proto_lr: 0.01
+    bb_lr: 0.01
+data:
+  batch_size: 32

examples/glvq_iris.py

@@ -3,7 +3,6 @@
 import argparse
 
 import prototorch as pt
-import prototorch.models.clcc
 import pytorch_lightning as pl
 import torch
 from torch.optim.lr_scheduler import ExponentialLR
@@ -30,7 +29,7 @@ if __name__ == "__main__":
     )
 
     # Initialize the model
-    model = prototorch.models.GLVQ(
+    model = pt.models.GLVQ(
         hparams,
         optimizer=torch.optim.Adam,
         prototypes_initializer=pt.initializers.SMCI(train_ds),
@@ -42,13 +41,7 @@ if __name__ == "__main__":
     model.example_input_array = torch.zeros(4, 2)
 
     # Callbacks
-    vis = pt.models.Visualize2DVoronoiCallback(
-        data=train_ds,
-        resolution=200,
-        title="Example: GLVQ on Iris",
-        x_label="sepal length",
-        y_label="petal length",
-    )
+    vis = pt.models.VisGLVQ2D(data=train_ds)
 
     # Setup trainer
     trainer = pl.Trainer.from_argparse_args(

examples/gmlvq_iris.py

@@ -1,58 +0,0 @@
-"""GMLVQ example using the Iris dataset."""
-
-import argparse
-
-import prototorch as pt
-import pytorch_lightning as pl
-import torch
-from torch.optim.lr_scheduler import ExponentialLR
-
-if __name__ == "__main__":
-    # Command-line arguments
-    parser = argparse.ArgumentParser()
-    parser = pl.Trainer.add_argparse_args(parser)
-    args = parser.parse_args()
-
-    # Dataset
-    train_ds = pt.datasets.Iris()
-
-    # Dataloaders
-    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=64)
-
-    # Hyperparameters
-    hparams = dict(
-        input_dim=4,
-        latent_dim=4,
-        distribution={
-            "num_classes": 3,
-            "per_class": 2
-        },
-        proto_lr=0.01,
-        bb_lr=0.01,
-    )
-
-    # Initialize the model
-    model = pt.models.GMLVQ(
-        hparams,
-        optimizer=torch.optim.Adam,
-        prototypes_initializer=pt.initializers.SMCI(train_ds),
-        lr_scheduler=ExponentialLR,
-        lr_scheduler_kwargs=dict(gamma=0.99, verbose=False),
-    )
-
-    # Compute intermediate input and output sizes
-    model.example_input_array = torch.zeros(4, 4)
-
-    # Callbacks
-    vis = pt.models.VisGMLVQ2D(data=train_ds)
-
-    # Setup trainer
-    trainer = pl.Trainer.from_argparse_args(
-        args,
-        callbacks=[vis],
-        weights_summary="full",
-        accelerator="ddp",
-    )
-
-    # Training loop
-    trainer.fit(model, train_loader)

examples/knn_iris.py

@@ -6,7 +6,6 @@ import prototorch as pt
 import pytorch_lightning as pl
 import torch
 from sklearn.datasets import load_iris
-from sklearn.model_selection import train_test_split
 
 if __name__ == "__main__":
     # Command-line arguments
@@ -15,20 +14,12 @@ if __name__ == "__main__":
     args = parser.parse_args()
 
     # Dataset
-    X, y = load_iris(return_X_y=True)
-    X = X[:, [0, 2]]
-
-    X_train, X_test, y_train, y_test = train_test_split(X,
-                                                        y,
-                                                        test_size=0.5,
-                                                        random_state=42)
-
-    train_ds = pt.datasets.NumpyDataset(X_train, y_train)
-    test_ds = pt.datasets.NumpyDataset(X_test, y_test)
+    x_train, y_train = load_iris(return_X_y=True)
+    x_train = x_train[:, [0, 2]]
+    train_ds = pt.datasets.NumpyDataset(x_train, y_train)
 
     # Dataloaders
-    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=16)
-    test_loader = torch.utils.data.DataLoader(test_ds, batch_size=16)
+    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=150)
 
     # Hyperparameters
     hparams = dict(k=5)
@@ -44,7 +35,7 @@ if __name__ == "__main__":
 
     # Callbacks
     vis = pt.models.VisGLVQ2D(
-        data=(X_train, y_train),
+        data=(x_train, y_train),
         resolution=200,
         block=True,
     )
@@ -62,8 +53,5 @@ if __name__ == "__main__":
     trainer.fit(model, train_loader)
 
     # Recall
-    y_pred = model.predict(torch.tensor(X_train))
+    y_pred = model.predict(torch.tensor(x_train))
     print(y_pred)
-
-    # Test
-    trainer.test(model, dataloaders=test_loader)

prototorch/models/__init__.py

@@ -1,5 +1,7 @@
 """`models` plugin for the `prototorch` package."""
 
+from importlib.metadata import PackageNotFoundError, version
+
 from .callbacks import PrototypeConvergence, PruneLoserPrototypes
 from .cbc import CBC, ImageCBC
 from .glvq import (
@@ -17,8 +19,9 @@ from .glvq import (
 )
 from .knn import KNN
 from .lvq import LVQ1, LVQ21, MedianLVQ
+from .nam import BinaryNAM
 from .probabilistic import CELVQ, PLVQ, RSLVQ, SLVQ
 from .unsupervised import GrowingNeuralGas, HeskesSOM, KohonenSOM, NeuralGas
 from .vis import *
 
-__version__ = "0.3.0"
+__version__ = "0.2.0"

prototorch/models/abstract.py

@@ -1,14 +1,17 @@
 """Abstract classes to be inherited by prototorch models."""
 
+from typing import Final, final
+
 import pytorch_lightning as pl
 import torch
 import torchmetrics
-from prototorch.core.competitions import WTAC
-from prototorch.core.components import Components, LabeledComponents
-from prototorch.core.distances import euclidean_distance
-from prototorch.core.initializers import LabelsInitializer
-from prototorch.core.pooling import stratified_min_pooling
-from prototorch.nn.wrappers import LambdaLayer
+
+from ..core.competitions import WTAC
+from ..core.components import Components, LabeledComponents
+from ..core.distances import euclidean_distance
+from ..core.initializers import LabelsInitializer
+from ..core.pooling import stratified_min_pooling
+from ..nn.wrappers import LambdaLayer
 
 
 class ProtoTorchBolt(pl.LightningModule):
@@ -40,6 +43,7 @@ class ProtoTorchBolt(pl.LightningModule):
         else:
             return optimizer
 
+    @final
     def reconfigure_optimizers(self):
         self.trainer.accelerator.setup_optimizers(self.trainer)
 
@@ -92,7 +96,7 @@ class UnsupervisedPrototypeModel(PrototypeModel):
             )
 
     def compute_distances(self, x):
-        protos = self.proto_layer().type_as(x)
+        protos = self.proto_layer()
         distances = self.distance_layer(x, protos)
         return distances
 
@@ -132,14 +136,14 @@ class SupervisedPrototypeModel(PrototypeModel):
 
     def forward(self, x):
         distances = self.compute_distances(x)
-        _, plabels = self.proto_layer()
+        plabels = self.proto_layer.labels
         winning = stratified_min_pooling(distances, plabels)
         y_pred = torch.nn.functional.softmin(winning)
         return y_pred
 
     def predict_from_distances(self, distances):
         with torch.no_grad():
-            _, plabels = self.proto_layer()
+            plabels = self.proto_layer.labels
             y_pred = self.competition_layer(distances, plabels)
         return y_pred
 
@@ -161,10 +165,32 @@ class SupervisedPrototypeModel(PrototypeModel):
                  prog_bar=True,
                  logger=True)
 
-    def test_step(self, batch, batch_idx):
-        x, targets = batch
 
-        preds = self.predict(x)
-        accuracy = torchmetrics.functional.accuracy(preds.int(), targets.int())
+class ProtoTorchMixin(object):
+    """All mixins are ProtoTorchMixins."""
+    pass
 
-        self.log("test_acc", accuracy)
+
+class NonGradientMixin(ProtoTorchMixin):
+    """Mixin for custom non-gradient optimization."""
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.automatic_optimization: Final = False
+
+    def training_step(self, train_batch, batch_idx, optimizer_idx=None):
+        raise NotImplementedError
+
+
+class ImagePrototypesMixin(ProtoTorchMixin):
+    """Mixin for models with image prototypes."""
+    @final
+    def on_train_batch_end(self, outputs, batch, batch_idx, dataloader_idx):
+        """Constrain the components to the range [0, 1] by clamping after updates."""
+        self.proto_layer.components.data.clamp_(0.0, 1.0)
+
+    def get_prototype_grid(self, num_columns=2, return_channels_last=True):
+        from torchvision.utils import make_grid
+        grid = make_grid(self.components, nrow=num_columns)
+        if return_channels_last:
+            grid = grid.permute((1, 2, 0))
+        return grid.cpu()

prototorch/models/callbacks.py

@@ -4,9 +4,9 @@ import logging
 
 import pytorch_lightning as pl
 import torch
-from prototorch.core.components import Components
-from prototorch.core.initializers import LiteralCompInitializer
 
+from ..core.components import Components
+from ..core.initializers import LiteralCompInitializer
 from .extras import ConnectionTopology
 
 
@@ -55,7 +55,7 @@ class PruneLoserPrototypes(pl.Callback):
                 distribution = dict(zip(labels.tolist(), counts.tolist()))
                 if self.verbose:
                     print(f"Re-adding pruned prototypes...")
-                    print(f"distribution={distribution}")
+                    print(f"{distribution=}")
                 pl_module.add_prototypes(
                     distribution=distribution,
                     components_initializer=self.prototypes_initializer)
@@ -134,4 +134,4 @@ class GNGCallback(pl.Callback):
             pl_module.errors[
                 worst_neighbor] = errors[worst_neighbor] * self.reduction
 
-            trainer.accelerator.setup_optimizers(trainer)
+            trainer.accelerator_backend.setup_optimizers(trainer)

prototorch/models/cbc.py

@@ -1,14 +1,14 @@
 import torch
 import torchmetrics
-from prototorch.core.competitions import CBCC
-from prototorch.core.components import ReasoningComponents
-from prototorch.core.initializers import RandomReasoningsInitializer
-from prototorch.core.losses import MarginLoss
-from prototorch.core.similarities import euclidean_similarity
-from prototorch.nn.wrappers import LambdaLayer
 
+from ..core.competitions import CBCC
+from ..core.components import ReasoningComponents
+from ..core.initializers import RandomReasoningsInitializer
+from ..core.losses import MarginLoss
+from ..core.similarities import euclidean_similarity
+from ..nn.wrappers import LambdaLayer
+from .abstract import ImagePrototypesMixin
 from .glvq import SiameseGLVQ
-from .mixin import ImagePrototypesMixin
 
 
 class CBC(SiameseGLVQ):

prototorch/models/clcc/clcc_glvq.py

@@ -1,86 +0,0 @@
-from dataclasses import dataclass
-from typing import Callable
-
-import torch
-from prototorch.core.competitions import WTAC
-from prototorch.core.components import LabeledComponents
-from prototorch.core.distances import euclidean_distance
-from prototorch.core.initializers import AbstractComponentsInitializer, LabelsInitializer
-from prototorch.core.losses import GLVQLoss
-from prototorch.models.clcc.clcc_scheme import CLCCScheme
-from prototorch.nn.wrappers import LambdaLayer
-
-
-@dataclass
-class GLVQhparams:
-    distribution: dict
-    component_initializer: AbstractComponentsInitializer
-    distance_fn: Callable = euclidean_distance
-    lr: float = 0.01
-    margin: float = 0.0
-    # TODO: make nicer
-    transfer_fn: str = "identity"
-    transfer_beta: float = 10.0
-    optimizer: torch.optim.Optimizer = torch.optim.Adam
-
-
-class GLVQ(CLCCScheme):
-    def __init__(self, hparams: GLVQhparams) -> None:
-        super().__init__(hparams)
-        self.lr = hparams.lr
-        self.optimizer = hparams.optimizer
-
-    # Initializers
-    def init_components(self, hparams):
-        # initialize Component Layer
-        self.components_layer = LabeledComponents(
-            distribution=hparams.distribution,
-            components_initializer=hparams.component_initializer,
-            labels_initializer=LabelsInitializer(),
-        )
-
-    def init_comparison(self, hparams):
-        # initialize Distance Layer
-        self.comparison_layer = LambdaLayer(hparams.distance_fn)
-
-    def init_inference(self, hparams):
-        self.competition_layer = WTAC()
-
-    def init_loss(self, hparams):
-        self.loss_layer = GLVQLoss(
-            margin=hparams.margin,
-            transfer_fn=hparams.transfer_fn,
-            beta=hparams.transfer_beta,
-        )
-
-    # Steps
-    def comparison(self, batch, components):
-        comp_tensor, _ = components
-        batch_tensor, _ = batch
-
-        comp_tensor = comp_tensor.unsqueeze(1)
-
-        distances = self.comparison_layer(batch_tensor, comp_tensor)
-
-        return distances
-
-    def inference(self, comparisonmeasures, components):
-        comp_labels = components[1]
-        return self.competition_layer(comparisonmeasures, comp_labels)
-
-    def loss(self, comparisonmeasures, batch, components):
-        target = batch[1]
-        comp_labels = components[1]
-        return self.loss_layer(comparisonmeasures, target, comp_labels)
-
-    def configure_optimizers(self):
-        return self.optimizer(self.parameters(), lr=self.lr)
-
-    # Properties
-    @property
-    def prototypes(self):
-        return self.components_layer.components.detach().cpu()
-
-    @property
-    def prototype_labels(self):
-        return self.components_layer.labels.detach().cpu()

prototorch/models/clcc/clcc_scheme.py

@@ -1,192 +0,0 @@
-"""
-CLCC Scheme
-
-CLCC is a LVQ scheme containing 4 steps
-- Components
-- Latent Space
-- Comparison
-- Competition
-
-"""
-from typing import Dict, Set, Type
-
-import pytorch_lightning as pl
-import torch
-import torchmetrics
-
-
-class CLCCScheme(pl.LightningModule):
-    registered_metrics: Dict[Type[torchmetrics.Metric],
-                             torchmetrics.Metric] = {}
-    registered_metric_names: Dict[Type[torchmetrics.Metric], Set[str]] = {}
-
-    def __init__(self, hparams) -> None:
-        super().__init__()
-
-        # Common Steps
-        self.init_components(hparams)
-        self.init_latent(hparams)
-        self.init_comparison(hparams)
-        self.init_competition(hparams)
-
-        # Train Steps
-        self.init_loss(hparams)
-
-        # Inference Steps
-        self.init_inference(hparams)
-
-        # Initialize Model Metrics
-        self.init_model_metrics()
-
-    # internal API, called by models and callbacks
-    def register_torchmetric(self, name: str, metric: torchmetrics.Metric):
-        if metric not in self.registered_metrics:
-            self.registered_metrics[metric] = metric()
-            self.registered_metric_names[metric] = {name}
-        else:
-            self.registered_metric_names[metric].add(name)
-
-    # external API
-    def get_competion(self, batch, components):
-        latent_batch, latent_components = self.latent(batch, components)
-        # TODO: => Latent Hook
-        comparison_tensor = self.comparison(latent_batch, latent_components)
-        # TODO: => Comparison Hook
-        return comparison_tensor
-
-    def forward(self, batch):
-        if isinstance(batch, torch.Tensor):
-            batch = (batch, None)
-        # TODO: manage different datatypes?
-        components = self.components_layer()
-        # TODO: => Component Hook
-        comparison_tensor = self.get_competion(batch, components)
-        # TODO: => Competition Hook
-        return self.inference(comparison_tensor, components)
-
-    def predict(self, batch):
-        """
-        Alias for forward
-        """
-        return self.forward(batch)
-
-    def loss_forward(self, batch):
-        # TODO: manage different datatypes?
-        components = self.components_layer()
-        # TODO: => Component Hook
-        comparison_tensor = self.get_competion(batch, components)
-        # TODO: => Competition Hook
-        return self.loss(comparison_tensor, batch, components)
-
-    # Empty Initialization
-    # TODO: Type hints
-    # TODO: Docs
-    def init_components(self, hparams):
-        ...
-
-    def init_latent(self, hparams):
-        ...
-
-    def init_comparison(self, hparams):
-        ...
-
-    def init_competition(self, hparams):
-        ...
-
-    def init_loss(self, hparams):
-        ...
-
-    def init_inference(self, hparams):
-        ...
-
-    def init_model_metrics(self):
-        self.register_torchmetric('train_accuracy', torchmetrics.Accuracy)
-
-    # Empty Steps
-    # TODO: Type hints
-    def components(self):
-        """
-        This step has no input.
-
-        It returns the components.
-        """
-        raise NotImplementedError(
-            "The components step has no reasonable default.")
-
-    def latent(self, batch, components):
-        """
-        The latent step receives the data batch and the components.
-        It can transform both by an arbitrary function.
-
-        It returns the transformed batch and components, each of the same length as the original input.
-        """
-        return batch, components
-
-    def comparison(self, batch, components):
-        """
-        Takes a batch of size N and the componentsset of size M.
-
-        It returns an NxMxD tensor containing D (usually 1) pairwise comparison measures.
-        """
-        raise NotImplementedError(
-            "The comparison step has no reasonable default.")
-
-    def competition(self, comparisonmeasures, components):
-        """
-        Takes the tensor of comparison measures.
-
-        Assigns a competition vector to each class.
-        """
-        raise NotImplementedError(
-            "The competition step has no reasonable default.")
-
-    def loss(self, comparisonmeasures, batch, components):
-        """
-        Takes the tensor of competition measures.
-
-        Calculates a single loss value
-        """
-        raise NotImplementedError("The loss step has no reasonable default.")
-
-    def inference(self, comparisonmeasures, components):
-        """
-        Takes the tensor of competition measures.
-
-        Returns the inferred vector.
-        """
-        raise NotImplementedError(
-            "The inference step has no reasonable default.")
-
-    def update_metrics_step(self, batch):
-        x, y = batch
-        preds = self(x)
-
-        for metric in self.registered_metrics:
-            instance = self.registered_metrics[metric].to(self.device)
-            value = instance(y, preds)
-
-            for name in self.registered_metric_names[metric]:
-                self.log(name, value)
-
-    def update_metrics_epoch(self):
-        for metric in self.registered_metrics:
-            instance = self.registered_metrics[metric].to(self.device)
-            value = instance.compute()
-
-            for name in self.registered_metric_names[metric]:
-                self.log(name, value)
-
-    # Lightning Hooks
-    def training_step(self, batch, batch_idx, optimizer_idx=None):
-        self.update_metrics_step(batch)
-
-        return self.loss_forward(batch)
-
-    def train_epoch_end(self, outs) -> None:
-        self.update_metrics_epoch()
-
-    def validation_step(self, batch, batch_idx):
-        return self.loss_forward(batch)
-
-    def test_step(self, batch, batch_idx):
-        return self.loss_forward(batch)

prototorch/models/clcc/test_clcc.py

@@ -1,76 +0,0 @@
-from typing import Optional
-
-import matplotlib.pyplot as plt
-import prototorch as pt
-import pytorch_lightning as pl
-import torch
-import torchmetrics
-from prototorch.core.initializers import SMCI, RandomNormalCompInitializer
-from prototorch.models.clcc.clcc_glvq import GLVQ, GLVQhparams
-from prototorch.models.clcc.clcc_scheme import CLCCScheme
-from prototorch.models.vis import Visualize2DVoronoiCallback
-
-# NEW STUFF
-# ##############################################################################
-
-
-# TODO: Metrics
-class MetricsTestCallback(pl.Callback):
-    metric_name = "test_cb_acc"
-
-    def setup(self,
-              trainer: pl.Trainer,
-              pl_module: CLCCScheme,
-              stage: Optional[str] = None) -> None:
-        pl_module.register_torchmetric(self.metric_name, torchmetrics.Accuracy)
-
-    def on_epoch_end(self, trainer: pl.Trainer,
-                     pl_module: pl.LightningModule) -> None:
-        metric = trainer.logged_metrics[self.metric_name]
-        if metric > 0.95:
-            trainer.should_stop = True
-
-
-# TODO: Pruning
-
-# ##############################################################################
-
-if __name__ == "__main__":
-    # Dataset
-    train_ds = pt.datasets.Iris(dims=[0, 2])
-    # Dataloaders
-    train_loader = torch.utils.data.DataLoader(train_ds,
-                                               batch_size=64,
-                                               num_workers=8)
-
-    components_initializer = SMCI(train_ds)
-
-    hparams = GLVQhparams(
-        distribution=dict(
-            num_classes=3,
-            per_class=2,
-        ),
-        component_initializer=components_initializer,
-    )
-    model = GLVQ(hparams)
-
-    print(model)
-    # Callbacks
-    vis = Visualize2DVoronoiCallback(
-        data=train_ds,
-        resolution=500,
-    )
-    metrics = MetricsTestCallback()
-
-    # Train
-    trainer = pl.Trainer(
-        callbacks=[
-            #vis,
-            metrics,
-        ],
-        gpus=1,
-        max_epochs=100,
-        weights_summary=None,
-        log_every_n_steps=1,
-    )
-    trainer.fit(model, train_loader)

prototorch/models/data.py

@@ -0,0 +1,123 @@
+"""Prototorch Data Modules
+
+This allows to store the used dataset inside a Lightning Module.
+Mainly used for PytorchLightningCLI configurations.
+"""
+from typing import Any, Optional, Type
+
+import prototorch as pt
+import pytorch_lightning as pl
+from torch.utils.data import DataLoader, Dataset, random_split
+from torchvision import transforms
+from torchvision.datasets import MNIST
+
+
+# MNIST
+class MNISTDataModule(pl.LightningDataModule):
+    def __init__(self, batch_size=32):
+        super().__init__()
+        self.batch_size = batch_size
+
+    # Download mnist dataset as side-effect, only called on the first cpu
+    def prepare_data(self):
+        MNIST("~/datasets", train=True, download=True)
+        MNIST("~/datasets", train=False, download=True)
+
+    # called for every GPU/machine (assigning state is OK)
+    def setup(self, stage=None):
+        # Transforms
+        transform = transforms.Compose([
+            transforms.ToTensor(),
+        ])
+        # Split dataset
+        if stage in (None, "fit"):
+            mnist_train = MNIST("~/datasets", train=True, transform=transform)
+            self.mnist_train, self.mnist_val = random_split(
+                mnist_train,
+                [55000, 5000],
+            )
+        if stage == (None, "test"):
+            self.mnist_test = MNIST(
+                "~/datasets",
+                train=False,
+                transform=transform,
+            )
+
+    # Dataloaders
+    def train_dataloader(self):
+        mnist_train = DataLoader(self.mnist_train, batch_size=self.batch_size)
+        return mnist_train
+
+    def val_dataloader(self):
+        mnist_val = DataLoader(self.mnist_val, batch_size=self.batch_size)
+        return mnist_val
+
+    def test_dataloader(self):
+        mnist_test = DataLoader(self.mnist_test, batch_size=self.batch_size)
+        return mnist_test
+
+
+# def train_on_mnist(batch_size=256) -> type:
+#     class DataClass(pl.LightningModule):
+#         datamodule = MNISTDataModule(batch_size=batch_size)
+
+#         def __init__(self, *args, **kwargs):
+#             prototype_initializer = kwargs.pop(
+#                 "prototype_initializer", pt.components.Zeros((28, 28, 1)))
+#             super().__init__(*args,
+#                              prototype_initializer=prototype_initializer,
+#                              **kwargs)
+
+#     dc: Type[DataClass] = DataClass
+#     return dc
+
+
+# ABSTRACT
+class GeneralDataModule(pl.LightningDataModule):
+    def __init__(self, dataset: Dataset, batch_size: int = 32) -> None:
+        super().__init__()
+        self.train_dataset = dataset
+        self.batch_size = batch_size
+
+    def train_dataloader(self) -> DataLoader:
+        return DataLoader(self.train_dataset, batch_size=self.batch_size)
+
+
+# def train_on_dataset(dataset: Dataset, batch_size: int = 256):
+#     class DataClass(pl.LightningModule):
+#         datamodule = GeneralDataModule(dataset, batch_size)
+#         datashape = dataset[0][0].shape
+#         example_input_array = torch.zeros_like(dataset[0][0]).unsqueeze(0)
+
+#         def __init__(self, *args: Any, **kwargs: Any) -> None:
+#             prototype_initializer = kwargs.pop(
+#                 "prototype_initializer",
+#                 pt.components.Zeros(self.datashape),
+#             )
+#             super().__init__(*args,
+#                              prototype_initializer=prototype_initializer,
+#                              **kwargs)
+
+#     return DataClass
+
+# if __name__ == "__main__":
+#     from prototorch.models import GLVQ
+
+#     demo_dataset = pt.datasets.Iris()
+
+#     TrainingClass: Type = train_on_dataset(demo_dataset)
+
+#     class DemoGLVQ(TrainingClass, GLVQ):
+#         """Model Definition."""
+
+#     # Hyperparameters
+#     hparams = dict(
+#         distribution={
+#             "num_classes": 3,
+#             "prototypes_per_class": 4
+#         },
+#         lr=0.01,
+#     )
+
+#     initialized = DemoGLVQ(hparams)
+#     print(initialized)

prototorch/models/extras.py

@@ -5,7 +5,8 @@ Modules not yet available in prototorch go here temporarily.
 """
 
 import torch
-from prototorch.core.similarities import gaussian
+
+from ..core.similarities import gaussian
 
 
 def rank_scaled_gaussian(distances, lambd):

prototorch/models/glvq.py

@@ -1,16 +1,15 @@
 """Models based on the GLVQ framework."""
 
 import torch
-from prototorch.core.competitions import wtac
-from prototorch.core.distances import lomega_distance, omega_distance, squared_euclidean_distance
-from prototorch.core.initializers import EyeTransformInitializer
-from prototorch.core.losses import GLVQLoss, lvq1_loss, lvq21_loss
-from prototorch.core.transforms import LinearTransform
-from prototorch.nn.wrappers import LambdaLayer, LossLayer
 from torch.nn.parameter import Parameter
 
-from .abstract import SupervisedPrototypeModel
-from .mixin import ImagePrototypesMixin
+from ..core.competitions import wtac
+from ..core.distances import lomega_distance, omega_distance, squared_euclidean_distance
+from ..core.initializers import EyeTransformInitializer
+from ..core.losses import GLVQLoss, lvq1_loss, lvq21_loss
+from ..core.transforms import LinearTransform
+from ..nn.wrappers import LambdaLayer, LossLayer
+from .abstract import ImagePrototypesMixin, SupervisedPrototypeModel
 
 
 class GLVQ(SupervisedPrototypeModel):
@@ -56,7 +55,7 @@ class GLVQ(SupervisedPrototypeModel):
     def shared_step(self, batch, batch_idx, optimizer_idx=None):
         x, y = batch
         out = self.compute_distances(x)
-        _, plabels = self.proto_layer()
+        plabels = self.proto_layer.labels
         loss = self.loss(out, y, plabels)
         return out, loss
 
@@ -113,8 +112,7 @@ class SiameseGLVQ(GLVQ):
         proto_opt = self.optimizer(self.proto_layer.parameters(),
                                    lr=self.hparams.proto_lr)
         # Only add a backbone optimizer if backbone has trainable parameters
-        bb_params = list(self.backbone.parameters())
-        if (bb_params):
+        if (bb_params := list(self.backbone.parameters())):
             bb_opt = self.optimizer(bb_params, lr=self.hparams.bb_lr)
             optimizers = [proto_opt, bb_opt]
         else:
@@ -131,7 +129,7 @@ class SiameseGLVQ(GLVQ):
 
     def compute_distances(self, x):
         protos, _ = self.proto_layer()
-        x, protos = (arr.view(arr.size(0), -1) for arr in (x, protos))
+        x, protos = [arr.view(arr.size(0), -1) for arr in (x, protos)]
         latent_x = self.backbone(x)
         self.backbone.requires_grad_(self.both_path_gradients)
         latent_protos = self.backbone(protos)
@@ -252,12 +250,6 @@ class GMLVQ(GLVQ):
     def omega_matrix(self):
         return self._omega.detach().cpu()
 
-    @property
-    def lambda_matrix(self):
-        omega = self._omega.detach()  # (input_dim, latent_dim)
-        lam = omega @ omega.T
-        return lam.detach().cpu()
-
     def compute_distances(self, x):
         protos, _ = self.proto_layer()
         distances = self.distance_layer(x, protos, self._omega)

prototorch/models/knn.py

@@ -2,11 +2,10 @@
 
 import warnings
 
-from prototorch.core.competitions import KNNC
-from prototorch.core.components import LabeledComponents
-from prototorch.core.initializers import LiteralCompInitializer, LiteralLabelsInitializer
-from prototorch.utils.utils import parse_data_arg
-
+from ..core.competitions import KNNC
+from ..core.components import LabeledComponents
+from ..core.initializers import LiteralCompInitializer, LiteralLabelsInitializer
+from ..utils.utils import parse_data_arg
 from .abstract import SupervisedPrototypeModel
 
 

prototorch/models/lvq.py

@@ -1,17 +1,18 @@
 """LVQ models that are optimized using non-gradient methods."""
 
-from prototorch.core.losses import _get_dp_dm
-from prototorch.nn.activations import get_activation
-from prototorch.nn.wrappers import LambdaLayer
-
+from ..core.losses import _get_dp_dm
+from ..nn.activations import get_activation
+from ..nn.wrappers import LambdaLayer
+from .abstract import NonGradientMixin
 from .glvq import GLVQ
-from .mixin import NonGradientMixin
 
 
 class LVQ1(NonGradientMixin, GLVQ):
     """Learning Vector Quantization 1."""
     def training_step(self, train_batch, batch_idx, optimizer_idx=None):
-        protos, plables = self.proto_layer()
+        protos = self.proto_layer.components
+        plabels = self.proto_layer.labels
+
         x, y = train_batch
         dis = self.compute_distances(x)
         # TODO Vectorized implementation
@@ -29,8 +30,8 @@ class LVQ1(NonGradientMixin, GLVQ):
             self.proto_layer.load_state_dict({"_components": updated_protos},
                                              strict=False)
 
-        print(f"dis={dis}")
-        print(f"y={y}")
+        print(f"{dis=}")
+        print(f"{y=}")
         # Logging
         self.log_acc(dis, y, tag="train_acc")
 
@@ -40,7 +41,8 @@ class LVQ1(NonGradientMixin, GLVQ):
 class LVQ21(NonGradientMixin, GLVQ):
     """Learning Vector Quantization 2.1."""
     def training_step(self, train_batch, batch_idx, optimizer_idx=None):
-        protos, plabels = self.proto_layer()
+        protos = self.proto_layer.components
+        plabels = self.proto_layer.labels
 
         x, y = train_batch
         dis = self.compute_distances(x)
@@ -97,7 +99,8 @@ class MedianLVQ(NonGradientMixin, GLVQ):
         return lower_bound
 
     def training_step(self, train_batch, batch_idx, optimizer_idx=None):
-        protos, plabels = self.proto_layer()
+        protos = self.proto_layer.components
+        plabels = self.proto_layer.labels
 
         x, y = train_batch
         dis = self.compute_distances(x)

prototorch/models/mixin.py

@@ -1,27 +0,0 @@
-class ProtoTorchMixin:
-    """All mixins are ProtoTorchMixins."""
-    pass
-
-
-class NonGradientMixin(ProtoTorchMixin):
-    """Mixin for custom non-gradient optimization."""
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.automatic_optimization = False
-
-    def training_step(self, train_batch, batch_idx, optimizer_idx=None):
-        raise NotImplementedError
-
-
-class ImagePrototypesMixin(ProtoTorchMixin):
-    """Mixin for models with image prototypes."""
-    def on_train_batch_end(self, outputs, batch, batch_idx, dataloader_idx):
-        """Constrain the components to the range [0, 1] by clamping after updates."""
-        self.proto_layer.components.data.clamp_(0.0, 1.0)
-
-    def get_prototype_grid(self, num_columns=2, return_channels_last=True):
-        from torchvision.utils import make_grid
-        grid = make_grid(self.components, nrow=num_columns)
-        if return_channels_last:
-            grid = grid.permute((1, 2, 0))
-        return grid.cpu()

prototorch/models/nam.py

@@ -0,0 +1,58 @@
+"""ProtoTorch Neural Additive Model."""
+
+import torch
+import torchmetrics
+
+from .abstract import ProtoTorchBolt
+
+
+class BinaryNAM(ProtoTorchBolt):
+    """Neural Additive Model for binary classification.
+
+    Paper: https://arxiv.org/abs/2004.13912
+    Official implementation: https://github.com/google-research/google-research/tree/master/neural_additive_models
+
+    """
+    def __init__(self, hparams: dict, extractors: torch.nn.ModuleList,
+                 **kwargs):
+        super().__init__(hparams, **kwargs)
+
+        # Default hparams
+        self.hparams.setdefault("threshold", 0.5)
+
+        self.extractors = extractors
+        self.linear = torch.nn.Linear(in_features=len(extractors),
+                                      out_features=1,
+                                      bias=True)
+
+    def extract(self, x):
+        """Apply the local extractors batch-wise on features."""
+        out = torch.zeros_like(x)
+        for j in range(x.shape[1]):
+            out[:, j] = self.extractors[j](x[:, j].unsqueeze(1)).squeeze()
+        return out
+
+    def forward(self, x):
+        x = self.extract(x)
+        x = self.linear(x)
+        return torch.sigmoid(x)
+
+    def training_step(self, batch, batch_idx, optimizer_idx=None):
+        x, y = batch
+        preds = self(x).squeeze()
+        train_loss = torch.nn.functional.binary_cross_entropy(preds, y.float())
+        self.log("train_loss", train_loss)
+        accuracy = torchmetrics.functional.accuracy(preds.int(), y.int())
+        self.log("train_acc",
+                 accuracy,
+                 on_step=False,
+                 on_epoch=True,
+                 prog_bar=True,
+                 logger=True)
+        return train_loss
+
+    def predict(self, x):
+        out = self(x)
+        pred = torch.zeros_like(out, device=self.device)
+        pred[out > self.hparams.threshold] = 1
+        return pred

prototorch/models/probabilistic.py

@@ -1,10 +1,9 @@
 """Probabilistic GLVQ methods"""
-
 import torch
-from prototorch.core.losses import nllr_loss, rslvq_loss
-from prototorch.core.pooling import stratified_min_pooling, stratified_sum_pooling
-from prototorch.nn.wrappers import LambdaLayer, LossLayer
 
+from ..core.losses import nllr_loss, rslvq_loss
+from ..core.pooling import stratified_min_pooling, stratified_sum_pooling
+from ..nn.wrappers import LambdaLayer, LossLayer
 from .extras import GaussianPrior, RankScaledGaussianPrior
 from .glvq import GLVQ, SiameseGMLVQ
 
@@ -20,7 +19,7 @@ class CELVQ(GLVQ):
     def shared_step(self, batch, batch_idx, optimizer_idx=None):
         x, y = batch
         out = self.compute_distances(x)  # [None, num_protos]
-        _, plabels = self.proto_layer()
+        plabels = self.proto_layer.labels
         winning = stratified_min_pooling(out, plabels)  # [None, num_classes]
         probs = -1.0 * winning
         batch_loss = self.loss(probs, y.long())
@@ -32,7 +31,7 @@ class ProbabilisticLVQ(GLVQ):
     def __init__(self, hparams, rejection_confidence=0.0, **kwargs):
         super().__init__(hparams, **kwargs)
 
-        self.conditional_distribution = None
+        self.conditional_distribution = GaussianPrior(self.hparams.variance)
         self.rejection_confidence = rejection_confidence
 
     def forward(self, x):
@@ -54,10 +53,11 @@ class ProbabilisticLVQ(GLVQ):
     def training_step(self, batch, batch_idx, optimizer_idx=None):
         x, y = batch
         out = self.forward(x)
-        _, plabels = self.proto_layer()
+        plabels = self.proto_layer.labels
         batch_loss = self.loss(out, y, plabels)
-        loss = batch_loss.sum()
-        return loss
+        train_loss = batch_loss.sum()
+        self.log("train_loss", train_loss)
+        return train_loss
 
 
 class SLVQ(ProbabilisticLVQ):
@@ -65,7 +65,6 @@ class SLVQ(ProbabilisticLVQ):
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
         self.loss = LossLayer(nllr_loss)
-        self.conditional_distribution = GaussianPrior(self.hparams.variance)
 
 
 class RSLVQ(ProbabilisticLVQ):
@@ -73,7 +72,6 @@ class RSLVQ(ProbabilisticLVQ):
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
         self.loss = LossLayer(rslvq_loss)
-        self.conditional_distribution = GaussianPrior(self.hparams.variance)
 
 
 class PLVQ(ProbabilisticLVQ, SiameseGMLVQ):

prototorch/models/unsupervised.py

@@ -2,15 +2,14 @@
 
 import numpy as np
 import torch
-from prototorch.core.competitions import wtac
-from prototorch.core.distances import squared_euclidean_distance
-from prototorch.core.losses import NeuralGasEnergy
-from prototorch.nn.wrappers import LambdaLayer
 
-from .abstract import UnsupervisedPrototypeModel
+from ..core.competitions import wtac
+from ..core.distances import squared_euclidean_distance
+from ..core.losses import NeuralGasEnergy
+from ..nn.wrappers import LambdaLayer
+from .abstract import NonGradientMixin, UnsupervisedPrototypeModel
 from .callbacks import GNGCallback
 from .extras import ConnectionTopology
-from .mixin import NonGradientMixin
 
 
 class KohonenSOM(NonGradientMixin, UnsupervisedPrototypeModel):
@@ -54,7 +53,7 @@ class KohonenSOM(NonGradientMixin, UnsupervisedPrototypeModel):
         grid = self._grid.view(-1, 2)
         gd = squared_euclidean_distance(wp, grid)
         nh = torch.exp(-gd / self._sigma**2)
-        protos = self.proto_layer()
+        protos = self.proto_layer.components
         diff = x.unsqueeze(dim=1) - protos
         delta = self._lr * self.hparams.alpha * nh.unsqueeze(-1) * diff
         updated_protos = protos + delta.sum(dim=0)

prototorch/models/vis.py

@@ -5,18 +5,15 @@ import pytorch_lightning as pl
 import torch
 import torchvision
 from matplotlib import pyplot as plt
-from prototorch.utils.utils import generate_mesh, mesh2d
 from torch.utils.data import DataLoader, Dataset
 
-COLOR_UNLABELED = 'w'
+from ..utils.utils import mesh2d
 
 
 class Vis2DAbstract(pl.Callback):
     def __init__(self,
                  data,
-                 title=None,
-                 x_label=None,
-                 y_label=None,
+                 title="Prototype Visualization",
                  cmap="viridis",
                  border=0.1,
                  resolution=100,
@@ -48,8 +45,6 @@ class Vis2DAbstract(pl.Callback):
         self.y_train = y
 
         self.title = title
-        self.x_label = x_label
-        self.y_label = y_label
         self.fig = plt.figure(self.title)
         self.cmap = cmap
         self.border = border
@@ -62,19 +57,20 @@ class Vis2DAbstract(pl.Callback):
         self.pause_time = pause_time
         self.block = block
 
-    def show_on_current_epoch(self, trainer):
-        if self.show_last_only and trainer.current_epoch != trainer.max_epochs - 1:
-            return False
+    def precheck(self, trainer):
+        if self.show_last_only:
+            if trainer.current_epoch != trainer.max_epochs - 1:
+                return False
         return True
 
-    def setup_ax(self):
+    def setup_ax(self, xlabel=None, ylabel=None):
         ax = self.fig.gca()
         ax.cla()
         ax.set_title(self.title)
-        if self.x_label:
-            ax.set_xlabel(self.x_label)
-        if self.x_label:
-            ax.set_ylabel(self.y_label)
+        if xlabel:
+            ax.set_xlabel("Data dimension 1")
+        if ylabel:
+            ax.set_ylabel("Data dimension 2")
         if self.axis_off:
             ax.axis("off")
         return ax
@@ -121,64 +117,43 @@ class Vis2DAbstract(pl.Callback):
         plt.close()
 
 
-class Visualize2DVoronoiCallback(Vis2DAbstract):
-    def __init__(self, data, **kwargs):
-        super().__init__(data, **kwargs)
-
-        self.data_min = torch.min(self.x_train, axis=0).values
-        self.data_max = torch.max(self.x_train, axis=0).values
-
-    def current_span(self, proto_values):
-        proto_min = torch.min(proto_values, axis=0).values
-        proto_max = torch.max(proto_values, axis=0).values
-
-        overall_min = torch.minimum(proto_min, self.data_min)
-        overall_max = torch.maximum(proto_max, self.data_max)
-
-        return overall_min, overall_max
-
-    def get_voronoi_diagram(self, min, max, model):
-        mesh_input, (xx, yy) = generate_mesh(
-            min,
-            max,
-            border=self.border,
-            resolution=self.resolution,
-            device=model.device,
-        )
-
-        y_pred = model.predict(mesh_input)
-        return xx, yy, y_pred.reshape(xx.shape)
-
+class Vis2D(Vis2DAbstract):
     def on_epoch_end(self, trainer, pl_module):
-        if not self.show_on_current_epoch(trainer):
+        if not self.precheck(trainer):
             return True
 
-        # Extract Prototypes
-        proto_values = pl_module.prototypes
-        if hasattr(pl_module, "prototype_labels"):
-            proto_labels = pl_module.prototype_labels
-        else:
-            proto_labels = COLOR_UNLABELED
+        x_train, y_train = self.x_train, self.y_train
+        ax = self.setup_ax(xlabel="Data dimension 1",
+                           ylabel="Data dimension 2")
+        self.plot_data(ax, x_train, y_train)
+        mesh_input, xx, yy = mesh2d(x_train, self.border, self.resolution)
+        mesh_input = torch.from_numpy(mesh_input).type_as(x_train)
+        y_pred = pl_module.predict(mesh_input)
+        y_pred = y_pred.cpu().reshape(xx.shape)
+        ax.contourf(xx, yy, y_pred, cmap=self.cmap, alpha=0.35)
 
-        # Calculate Voronoi Diagram
-        overall_min, overall_max = self.current_span(proto_values)
-        xx, yy, y_pred = self.get_voronoi_diagram(
-            overall_min,
-            overall_max,
-            pl_module,
-        )
+        self.log_and_display(trainer, pl_module)
 
-        ax = self.setup_ax()
-        ax.contourf(
-            xx.cpu(),
-            yy.cpu(),
-            y_pred.cpu(),
-            cmap=self.cmap,
-            alpha=0.35,
-        )
 
-        self.plot_data(ax, self.x_train, self.y_train)
-        self.plot_protos(ax, proto_values, proto_labels)
+class VisGLVQ2D(Vis2DAbstract):
+    def on_epoch_end(self, trainer, pl_module):
+        if not self.precheck(trainer):
+            return True
+
+        protos = pl_module.prototypes
+        plabels = pl_module.prototype_labels
+        x_train, y_train = self.x_train, self.y_train
+        ax = self.setup_ax(xlabel="Data dimension 1",
+                           ylabel="Data dimension 2")
+        self.plot_data(ax, x_train, y_train)
+        self.plot_protos(ax, protos, plabels)
+        x = np.vstack((x_train, protos))
+        mesh_input, xx, yy = mesh2d(x, self.border, self.resolution)
+        _components = pl_module.proto_layer._components
+        mesh_input = torch.from_numpy(mesh_input).type_as(_components)
+        y_pred = pl_module.predict(mesh_input)
+        y_pred = y_pred.cpu().reshape(xx.shape)
+        ax.contourf(xx, yy, y_pred, cmap=self.cmap, alpha=0.35)
 
         self.log_and_display(trainer, pl_module)
 
@@ -189,7 +164,7 @@ class VisSiameseGLVQ2D(Vis2DAbstract):
         self.map_protos = map_protos
 
     def on_epoch_end(self, trainer, pl_module):
-        if not self.show_on_current_epoch(trainer):
+        if not self.precheck(trainer):
             return True
 
         protos = pl_module.prototypes
@@ -221,49 +196,40 @@ class VisSiameseGLVQ2D(Vis2DAbstract):
         self.log_and_display(trainer, pl_module)
 
 
-class VisGMLVQ2D(Vis2DAbstract):
-    def __init__(self, *args, ev_proj=True, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.ev_proj = ev_proj
-
+class VisCBC2D(Vis2DAbstract):
     def on_epoch_end(self, trainer, pl_module):
-        if not self.show_on_current_epoch(trainer):
+        if not self.precheck(trainer):
             return True
 
-        protos = pl_module.prototypes
-        plabels = pl_module.prototype_labels
         x_train, y_train = self.x_train, self.y_train
-        device = pl_module.device
-        omega = pl_module._omega.detach()
-        lam = omega @ omega.T
-        u, _, _ = torch.pca_lowrank(lam, q=2)
-        with torch.no_grad():
-            x_train = torch.Tensor(x_train).to(device)
-            x_train = x_train @ u
-            x_train = x_train.cpu().detach()
-        if self.show_protos:
-            with torch.no_grad():
-                protos = torch.Tensor(protos).to(device)
-                protos = protos @ u
-                protos = protos.cpu().detach()
-        ax = self.setup_ax()
+        protos = pl_module.components
+        ax = self.setup_ax(xlabel="Data dimension 1",
+                           ylabel="Data dimension 2")
         self.plot_data(ax, x_train, y_train)
-        if self.show_protos:
-            self.plot_protos(ax, protos, plabels)
+        self.plot_protos(ax, protos, "w")
+        x = np.vstack((x_train, protos))
+        mesh_input, xx, yy = mesh2d(x, self.border, self.resolution)
+        _components = pl_module.components_layer._components
+        y_pred = pl_module.predict(
+            torch.Tensor(mesh_input).type_as(_components))
+        y_pred = y_pred.cpu().reshape(xx.shape)
+
+        ax.contourf(xx, yy, y_pred, cmap=self.cmap, alpha=0.35)
 
         self.log_and_display(trainer, pl_module)
 
 
 class VisNG2D(Vis2DAbstract):
     def on_epoch_end(self, trainer, pl_module):
-        if not self.show_on_current_epoch(trainer):
+        if not self.precheck(trainer):
             return True
 
         x_train, y_train = self.x_train, self.y_train
         protos = pl_module.prototypes
         cmat = pl_module.topology_layer.cmat.cpu().numpy()
 
-        ax = self.setup_ax()
+        ax = self.setup_ax(xlabel="Data dimension 1",
+                           ylabel="Data dimension 2")
         self.plot_data(ax, x_train, y_train)
         self.plot_protos(ax, protos, "w")
 
@@ -303,6 +269,8 @@ class VisImgComp(Vis2DAbstract):
                                    size=self.embedding_data,
                                    replace=False)
             data = self.x_train[ind]
+            # print(f"{data.shape=}")
+            # print(f"{self.y_train[ind].shape=}")
             tb.add_embedding(data.view(len(ind), -1),
                              label_img=data,
                              global_step=None,
@@ -334,7 +302,7 @@ class VisImgComp(Vis2DAbstract):
         )
 
     def on_epoch_end(self, trainer, pl_module):
-        if not self.show_on_current_epoch(trainer):
+        if not self.precheck(trainer):
             return True
 
         if self.show:

setup.py

@@ -18,11 +18,11 @@ PLUGIN_NAME = "models"
 PROJECT_URL = "https://github.com/si-cim/prototorch_models"
 DOWNLOAD_URL = "https://github.com/si-cim/prototorch_models.git"
 
-with open("README.md") as fh:
+with open("README.md", "r") as fh:
     long_description = fh.read()
 
 INSTALL_REQUIRES = [
-    "prototorch>=0.7.0",
+    "prototorch>=0.6.0",
     "pytorch_lightning>=1.3.5",
     "torchmetrics",
 ]
@@ -37,7 +37,6 @@ DOCS = [
     "recommonmark",
     "sphinx",
     "nbsphinx",
-    "ipykernel",
     "sphinx_rtd_theme",
     "sphinxcontrib-katex",
     "sphinxcontrib-bibtex",
@@ -54,7 +53,7 @@ ALL = CLI + DEV + DOCS + EXAMPLES + TESTS
 
 setup(
     name=safe_name("prototorch_" + PLUGIN_NAME),
-    version="0.3.0",
+    version="0.2.0",
     description="Pre-packaged prototype-based "
     "machine learning models using ProtoTorch and PyTorch-Lightning.",
     long_description=long_description,
@@ -64,7 +63,7 @@ setup(
     url=PROJECT_URL,
     download_url=DOWNLOAD_URL,
     license="MIT",
-    python_requires=">=3.6",
+    python_requires=">=3.9",
     install_requires=INSTALL_REQUIRES,
     extras_require={
         "dev": DEV,
@@ -81,9 +80,6 @@ setup(
         "License :: OSI Approved :: MIT License",
         "Natural Language :: English",
         "Programming Language :: Python :: 3.9",
-        "Programming Language :: Python :: 3.8",
-        "Programming Language :: Python :: 3.7",
-        "Programming Language :: Python :: 3.6",
         "Operating System :: OS Independent",
         "Topic :: Scientific/Engineering :: Artificial Intelligence",
         "Topic :: Software Development :: Libraries",

tests/test_examples.sh

@@ -1,27 +1,11 @@
 #! /bin/bash
 
-
-# Read Flags
-gpu=0
-while [ -n "$1" ]; do
-	case "$1" in
-	    --gpu) gpu=1;;
-	    -g) gpu=1;;
-        *) path=$1;;
-	esac
-	shift
-done
-
-python --version
-echo "Using GPU: " $gpu
-
-# Loop
 failed=0
 
-for example in $(find $path -maxdepth 1 -name "*.py")
+for example in $(find $1 -maxdepth 1 -name "*.py")
 do
     echo  -n "$x" $example '... '
-    export DISPLAY= && python $example --fast_dev_run 1 --gpus $gpu &> run_log.txt
+    export DISPLAY= && python $example --fast_dev_run 1 &> run_log.txt
     if [[ $? -ne 0 ]]; then
         echo "FAILED!!"
         cat run_log.txt