build: bump version 0.7.0 → 0.7.1

Necessary for different optimizer runs

.bumpversion.cfg

@@ -1,10 +1,13 @@
 [bumpversion]
-current_version = 0.1.8
+current_version = 0.7.1
 commit = True
 tag = True
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)
 serialize = {major}.{minor}.{patch}
+message = build: bump version {current_version} → {new_version}
 
-[bumpversion:file:setup.py]
+[bumpversion:file:pyproject.toml]
 
-[bumpversion:file:./prototorch/models/__init__.py]
+[bumpversion:file:./src/prototorch/models/__init__.py]
+
+[bumpversion:file:./docs/source/conf.py]

.codacy.yml

@@ -1,15 +0,0 @@
-# To validate the contents of your configuration file
-# run the following command in the folder where the configuration file is located:
-# codacy-analysis-cli validate-configuration --directory `pwd`
-# To analyse, run:
-# codacy-analysis-cli analyse --tool remark-lint --directory `pwd`
----
-engines:
-  pylintpython3:
-    exclude_paths:
-      - config/engines.yml
-  remark-lint:
-    exclude_paths:
-      - config/engines.yml
-exclude_paths:
-  - 'tests/**'

.codecov.yml

@@ -1,2 +0,0 @@
-comment:
-  require_changes: yes

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,38 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**Steps to reproduce the behavior**
+1. ...
+2. Run script '...' or this snippet:
+```python
+import prototorch as pt
+
+...
+```
+3. See errors
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Observed behavior**
+A clear and concise description of what actually happened.
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**System and version information**
+- OS: [e.g. Ubuntu 20.10]
+- ProtoTorch Version: [e.g. 0.4.0]
+- Python Version: [e.g. 3.9.5]
+
+**Additional context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,20 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+
+**Describe the solution you'd like**
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've considered.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

.github/workflows/examples.yml

@@ -0,0 +1,25 @@
+# Thi workflow will install Python dependencies, run tests and lint with a single version of Python
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: examples
+
+on:
+  push:
+    paths:
+      - "examples/**.py"
+jobs:
+  cpu:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.11"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install .[all]
+      - name: Run examples
+        run: |
+          ./tests/test_examples.sh examples/

.github/workflows/pythonapp.yml

@@ -0,0 +1,75 @@
+# This workflow will install Python dependencies, run tests and lint with a single version of Python
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: tests
+
+on:
+  push:
+  pull_request:
+    branches: [master]
+
+jobs:
+  style:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.11"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install .[all]
+      - uses: pre-commit/action@v3.0.0
+  compatibility:
+    needs: style
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.8", "3.9", "3.10", "3.11"]
+        os: [ubuntu-latest, windows-latest]
+        exclude:
+          - os: windows-latest
+            python-version: "3.8"
+          - os: windows-latest
+            python-version: "3.9"
+          - os: windows-latest
+            python-version: "3.10"
+
+    runs-on: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install .[all]
+      - name: Test with pytest
+        run: |
+          pytest
+  publish_pypi:
+    if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags')
+    needs: compatibility
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.11"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install .[all]
+          pip install build
+      - name: Build package
+        run: python -m build . -C verbose
+      - name: Publish a Python distribution to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          user: __token__
+          password: ${{ secrets.PYPI_API_TOKEN }}

.gitignore

@@ -128,14 +128,19 @@ dmypy.json
 # Pyre type checker
 .pyre/
 
-# Datasets
-datasets/
-
-# PyTorch-Lightning
-lightning_logs/
-
 .vscode/
 
+# Vim
+*~
+*.swp
+*.swo
+
 #  Pytorch Models or Weights
 #  If necessary make exceptions for single pretrained models
 *.pt
+
+# Artifacts created by ProtoTorch Models
+datasets/
+lightning_logs/
+examples/_*.py
+examples/_*.ipynb

.pre-commit-config.yaml

@@ -1,8 +1,9 @@
 # See https://pre-commit.com for more information
 # See https://pre-commit.com/hooks.html for more hooks
+
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.0.1
+    rev: v4.4.0
     hooks:
       - id: trailing-whitespace
       - id: end-of-file-fixer
@@ -11,44 +12,43 @@ repos:
       - id: check-ast
       - id: check-case-conflict
 
-
   - repo: https://github.com/myint/autoflake
-  rev: v1.4
+    rev: v2.1.1
     hooks:
       - id: autoflake
 
   - repo: http://github.com/PyCQA/isort
-  rev: 5.8.0
+    rev: 5.12.0
     hooks:
       - id: isort
 
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: 'v0.902'
+    rev: v1.3.0
     hooks:
       - id: mypy
         files: prototorch
         additional_dependencies: [types-pkg_resources]
 
   - repo: https://github.com/pre-commit/mirrors-yapf
-    rev: 'v0.31.0'  # Use the sha / tag you want to point at
+    rev: v0.32.0
     hooks:
       - id: yapf
+        additional_dependencies: ["toml"]
 
   - repo: https://github.com/pre-commit/pygrep-hooks
-    rev: v1.9.0  # Use the ref you want to point at
+    rev: v1.10.0
     hooks:
       - id: python-use-type-annotations
       - id: python-no-log-warn
       - id: python-check-blanket-noqa
 
-
   - repo: https://github.com/asottile/pyupgrade
-    rev: v2.19.4
+    rev: v3.7.0
     hooks:
       - id: pyupgrade
 
--   repo: https://github.com/jorisroovers/gitlint
-    rev: "v0.15.1"
+  - repo: https://github.com/si-cim/gitlint
+    rev: v0.15.2-unofficial
     hooks:
       - id: gitlint
         args: [--contrib=CT1, --ignore=B6, --msg-filename]

.travis.yml

@@ -1,25 +0,0 @@
-dist: bionic
-sudo: false
-language: python
-python: 3.9
-cache:
-  directories:
-  - "$HOME/.cache/pip"
-  - "./tests/artifacts"
-  - "$HOME/datasets"
-install:
-- pip install git+git://github.com/si-cim/prototorch@dev --progress-bar off
-- pip install .[all] --progress-bar off
-script:
-- coverage run -m pytest
-- ./tests/test_examples.sh examples/
-after_success:
-- bash <(curl -s https://codecov.io/bash)
-deploy:
-  provider: pypi
-  username: __token__
-  password:
-    secure: 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
-  on:
-    tags: true
-    skip_existing: true

README.md

@@ -1,6 +1,5 @@
 # ProtoTorch Models
 
-[![Build Status](https://api.travis-ci.com/si-cim/prototorch_models.svg?branch=main)](https://travis-ci.com/github/si-cim/prototorch_models)
 [![GitHub tag (latest by date)](https://img.shields.io/github/v/tag/si-cim/prototorch_models?color=yellow&label=version)](https://github.com/si-cim/prototorch_models/releases)
 [![PyPI](https://img.shields.io/pypi/v/prototorch_models)](https://pypi.org/project/prototorch_models/)
 [![GitHub license](https://img.shields.io/github/license/si-cim/prototorch_models)](https://github.com/si-cim/prototorch_models/blob/master/LICENSE)
@@ -20,23 +19,6 @@ pip install prototorch_models
 of** [ProtoTorch](https://github.com/si-cim/prototorch). The plugin should then
 be available for use in your Python environment as `prototorch.models`.
 
-## Contribution
-
-This repository contains definition for [git hooks](https://githooks.com).
-[Pre-commit](https://pre-commit.com) is automatically installed as development
-dependency with prototorch or you can install it manually with `pip install
-pre-commit`.
-
-Please install the hooks by running:
-```bash
-pre-commit install
-pre-commit install --hook-type commit-msg
-```
-before creating the first commit.
-
-The commit will fail if the commit message does not follow the specification
-provided [here](https://www.conventionalcommits.org/en/v1.0.0/#specification).
-
 ## Available models
 
 ### LVQ Family
@@ -53,6 +35,7 @@ provided [here](https://www.conventionalcommits.org/en/v1.0.0/#specification).
 - Soft Learning Vector Quantization (SLVQ)
 - Robust Soft Learning Vector Quantization (RSLVQ)
 - Probabilistic Learning Vector Quantization (PLVQ)
+- Median-LVQ
 
 ### Other
 
@@ -68,7 +51,6 @@ provided [here](https://www.conventionalcommits.org/en/v1.0.0/#specification).
 
 ## Planned models
 
-- Median-LVQ
 - Generalized Tangent Learning Vector Quantization (GTLVQ)
 - Self-Incremental Learning Vector Quantization (SILVQ)
 
@@ -103,6 +85,23 @@ To assist in the development process, you may also find it useful to install
 please avoid installing Tensorflow in this environment. It is known to cause
 problems with PyTorch-Lightning.**
 
+## Contribution
+
+This repository contains definition for [git hooks](https://githooks.com).
+[Pre-commit](https://pre-commit.com) is automatically installed as development
+dependency with prototorch or you can install it manually with `pip install
+pre-commit`.
+
+Please install the hooks by running:
+```bash
+pre-commit install
+pre-commit install --hook-type commit-msg
+```
+before creating the first commit.
+
+The commit will fail if the commit message does not follow the specification
+provided [here](https://www.conventionalcommits.org/en/v1.0.0/#specification).
+
 ## FAQ
 
 ### How do I update the plugin?

docs/source/conf.py

@@ -23,7 +23,7 @@ author = "Jensun Ravichandran"
 
 # The full version, including alpha/beta/rc tags
 #
-release = "0.4.4"
+release = "0.7.1"
 
 # -- General configuration ---------------------------------------------------
 

examples/cbc_iris.py

@@ -1,49 +1,68 @@
 """CBC example using the Iris dataset."""
-
 import argparse
-
-import pytorch_lightning as pl
-import torch
+import warnings
 
 import prototorch as pt
+import pytorch_lightning as pl
+from lightning_fabric.utilities.seed import seed_everything
+from prototorch.models import CBC, VisCBC2D
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
+from torch.utils.data import DataLoader
+
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
+warnings.filterwarnings("ignore", category=UserWarning)
 
 if __name__ == "__main__":
+    # Reproducibility
+    seed_everything(seed=4)
+
     # Command-line arguments
     parser = argparse.ArgumentParser()
-    parser = pl.Trainer.add_argparse_args(parser)
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
     args = parser.parse_args()
 
     # Dataset
     train_ds = pt.datasets.Iris(dims=[0, 2])
 
-    # Reproducibility
-    pl.utilities.seed.seed_everything(seed=42)
-
     # Dataloaders
-    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=32)
+    train_loader = DataLoader(train_ds, batch_size=32)
 
     # Hyperparameters
     hparams = dict(
-        distribution=[2, 2, 2],
-        proto_lr=0.1,
+        distribution=[1, 0, 3],
+        margin=0.1,
+        proto_lr=0.01,
+        bb_lr=0.01,
     )
 
     # Initialize the model
-    model = pt.models.CBC(
+    model = CBC(
         hparams,
-        prototype_initializer=pt.components.SSI(train_ds, noise=0.01),
+        components_initializer=pt.initializers.SSCI(train_ds, noise=0.1),
+        reasonings_initializer=pt.initializers.
+        PurePositiveReasoningsInitializer(),
     )
 
     # Callbacks
-    vis = pt.models.VisCBC2D(data=train_ds,
+    vis = VisCBC2D(
+        data=train_ds,
         title="CBC Iris Example",
         resolution=100,
-                             axis_off=True)
+        axis_off=True,
+    )
 
     # Setup trainer
-    trainer = pl.Trainer.from_argparse_args(
-        args,
-        callbacks=[vis],
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
+        callbacks=[
+            vis,
+        ],
+        detect_anomaly=True,
+        log_every_n_steps=1,
+        max_epochs=1000,
     )
 
     # Training loop

examples/cli/README.md

@@ -1,8 +0,0 @@
-# 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

@@ -1,20 +0,0 @@
-"""GMLVQ example using the MNIST dataset."""
-
-import torch
-from pytorch_lightning.utilities.cli import LightningCLI
-
-import prototorch as pt
-from prototorch.models import ImageGMLVQ
-from prototorch.models.abstract import PrototypeModel
-from prototorch.models.data import MNISTDataModule
-
-
-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

@@ -1,11 +0,0 @@
-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/dynamic_pruning.py

@@ -1,31 +1,50 @@
 """Dynamically prune 'loser' prototypes in GLVQ-type models."""
 
 import argparse
-
-import pytorch_lightning as pl
-import torch
+import logging
+import warnings
 
 import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from lightning_fabric.utilities.seed import seed_everything
+from prototorch.models import (
+    CELVQ,
+    PruneLoserPrototypes,
+    VisGLVQ2D,
+)
+from pytorch_lightning.callbacks import EarlyStopping
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
+from torch.utils.data import DataLoader
+
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
+warnings.filterwarnings("ignore", category=UserWarning)
 
 if __name__ == "__main__":
+    # Reproducibility
+    seed_everything(seed=4)
+
     # Command-line arguments
     parser = argparse.ArgumentParser()
-    parser = pl.Trainer.add_argparse_args(parser)
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
     args = parser.parse_args()
 
     # Dataset
     num_classes = 4
     num_features = 2
     num_clusters = 1
-    train_ds = pt.datasets.Random(num_samples=500,
+    train_ds = pt.datasets.Random(
+        num_samples=500,
         num_classes=num_classes,
         num_features=num_features,
         num_clusters=num_clusters,
         separation=3.0,
-                                  seed=42)
+        seed=42,
+    )
 
     # Dataloaders
-    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=256)
+    train_loader = DataLoader(train_ds, batch_size=256)
 
     # Hyperparameters
     prototypes_per_class = num_clusters * 5
@@ -35,27 +54,27 @@ if __name__ == "__main__":
     )
 
     # Initialize the model
-    model = pt.models.CELVQ(
+    model = CELVQ(
         hparams,
-        prototype_initializer=pt.components.Ones(2, scale=3),
+        prototypes_initializer=pt.initializers.FVCI(2, 3.0),
     )
 
     # Compute intermediate input and output sizes
     model.example_input_array = torch.zeros(4, 2)
 
     # Summary
-    print(model)
+    logging.info(model)
 
     # Callbacks
-    vis = pt.models.VisGLVQ2D(train_ds)
-    pruning = pt.models.PruneLoserPrototypes(
+    vis = VisGLVQ2D(train_ds)
+    pruning = PruneLoserPrototypes(
         threshold=0.01,  # prune prototype if it wins less than 1%
         idle_epochs=20,  # pruning too early may cause problems
         prune_quota_per_epoch=2,  # prune at most 2 prototypes per epoch
         frequency=1,  # prune every epoch
         verbose=True,
     )
-    es = pl.callbacks.EarlyStopping(
+    es = EarlyStopping(
         monitor="train_loss",
         min_delta=0.001,
         patience=20,
@@ -65,17 +84,18 @@ if __name__ == "__main__":
     )
 
     # Setup trainer
-    trainer = pl.Trainer.from_argparse_args(
-        args,
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
         callbacks=[
             vis,
             pruning,
             es,
         ],
-        progress_bar_refresh_rate=0,
-        terminate_on_nan=True,
-        weights_summary="full",
-        accelerator="ddp",
+        detect_anomaly=True,
+        log_every_n_steps=1,
+        max_epochs=1000,
     )
 
     # Training loop

examples/glvq_iris.py

@@ -1,39 +1,50 @@
 """GLVQ example using the Iris dataset."""
 
 import argparse
-
-import pytorch_lightning as pl
-import torch
-from torch.optim.lr_scheduler import ExponentialLR
+import logging
+import warnings
 
 import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from lightning_fabric.utilities.seed import seed_everything
+from prototorch.models import GLVQ, VisGLVQ2D
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
+from torch.optim.lr_scheduler import ExponentialLR
+from torch.utils.data import DataLoader
+
+warnings.filterwarnings("ignore", category=UserWarning)
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
 
 if __name__ == "__main__":
+    # Reproducibility
+    seed_everything(seed=4)
     # Command-line arguments
     parser = argparse.ArgumentParser()
-    parser = pl.Trainer.add_argparse_args(parser)
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
     args = parser.parse_args()
 
     # Dataset
     train_ds = pt.datasets.Iris(dims=[0, 2])
 
     # Dataloaders
-    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=64)
+    train_loader = DataLoader(train_ds, batch_size=64, num_workers=4)
 
     # Hyperparameters
     hparams = dict(
         distribution={
             "num_classes": 3,
-            "prototypes_per_class": 4
+            "per_class": 4
         },
         lr=0.01,
     )
 
     # Initialize the model
-    model = pt.models.GLVQ(
+    model = GLVQ(
         hparams,
         optimizer=torch.optim.Adam,
-        prototype_initializer=pt.components.SMI(train_ds),
+        prototypes_initializer=pt.initializers.SMCI(train_ds),
         lr_scheduler=ExponentialLR,
         lr_scheduler_kwargs=dict(gamma=0.99, verbose=False),
     )
@@ -42,15 +53,30 @@ if __name__ == "__main__":
     model.example_input_array = torch.zeros(4, 2)
 
     # Callbacks
-    vis = pt.models.VisGLVQ2D(data=train_ds)
+    vis = VisGLVQ2D(data=train_ds)
 
     # Setup trainer
-    trainer = pl.Trainer.from_argparse_args(
-        args,
-        callbacks=[vis],
-        weights_summary="full",
-        accelerator="ddp",
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
+        callbacks=[
+            vis,
+        ],
+        max_epochs=100,
+        log_every_n_steps=1,
+        detect_anomaly=True,
     )
 
     # Training loop
     trainer.fit(model, train_loader)
+
+    # Manual save
+    trainer.save_checkpoint("./glvq_iris.ckpt")
+
+    # Load saved model
+    new_model = GLVQ.load_from_checkpoint(
+        checkpoint_path="./glvq_iris.ckpt",
+        strict=False,
+    )
+    logging.info(new_model)

examples/glvq_spiral.py

@@ -1,78 +0,0 @@
-"""GLVQ example using the spiral dataset."""
-
-import argparse
-
-import pytorch_lightning as pl
-import torch
-
-import prototorch as pt
-
-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.Spiral(num_samples=500, noise=0.5)
-
-    # Dataloaders
-    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=256)
-
-    # Hyperparameters
-    num_classes = 2
-    prototypes_per_class = 10
-    hparams = dict(
-        distribution=(num_classes, prototypes_per_class),
-        transfer_function="swish_beta",
-        transfer_beta=10.0,
-        # lr=0.1,
-        proto_lr=0.1,
-        bb_lr=0.1,
-        input_dim=2,
-        latent_dim=2,
-    )
-
-    # Initialize the model
-    model = pt.models.GMLVQ(
-        hparams,
-        optimizer=torch.optim.Adam,
-        prototype_initializer=pt.components.SSI(train_ds, noise=1e-2),
-    )
-
-    # Callbacks
-    vis = pt.models.VisGLVQ2D(
-        train_ds,
-        show_last_only=False,
-        block=False,
-    )
-    pruning = pt.models.PruneLoserPrototypes(
-        threshold=0.02,
-        idle_epochs=10,
-        prune_quota_per_epoch=5,
-        frequency=2,
-        replace=True,
-        initializer=pt.components.SSI(train_ds, noise=1e-2),
-        verbose=True,
-    )
-    es = pl.callbacks.EarlyStopping(
-        monitor="train_loss",
-        min_delta=1.0,
-        patience=5,
-        mode="min",
-        check_on_train_epoch_end=True,
-    )
-
-    # Setup trainer
-    trainer = pl.Trainer.from_argparse_args(
-        args,
-        callbacks=[
-            vis,
-            # es,
-            pruning,
-        ],
-        terminate_on_nan=True,
-    )
-
-    # Training loop
-    trainer.fit(model, train_loader)

examples/gmlvq_iris.py

@@ -1,59 +1,78 @@
-"""GLVQ example using the Iris dataset."""
+"""GMLVQ example using the Iris dataset."""
 
 import argparse
+import warnings
 
 import prototorch as pt
 import pytorch_lightning as pl
 import torch
+from lightning_fabric.utilities.seed import seed_everything
+from prototorch.models import GMLVQ, VisGMLVQ2D
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from torch.optim.lr_scheduler import ExponentialLR
+from torch.utils.data import DataLoader
+
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
+warnings.filterwarnings("ignore", category=UserWarning)
 
 if __name__ == "__main__":
+
+    # Reproducibility
+    seed_everything(seed=4)
+
     # Command-line arguments
     parser = argparse.ArgumentParser()
-    parser = pl.Trainer.add_argparse_args(parser)
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
     args = parser.parse_args()
 
     # Dataset
     train_ds = pt.datasets.Iris()
 
     # Dataloaders
-    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=64)
+    train_loader = DataLoader(train_ds, batch_size=64)
 
     # Hyperparameters
     hparams = dict(
         input_dim=4,
-        latent_dim=3,
+        latent_dim=4,
         distribution={
             "num_classes": 3,
-            "prototypes_per_class": 2
+            "per_class": 2
         },
-        proto_lr=0.0005,
-        bb_lr=0.0005,
+        proto_lr=0.01,
+        bb_lr=0.01,
     )
 
     # Initialize the model
-    model = pt.models.GMLVQ(
+    model = GMLVQ(
         hparams,
         optimizer=torch.optim.Adam,
-        prototype_initializer=pt.components.SSI(train_ds),
+        prototypes_initializer=pt.initializers.SMCI(train_ds),
         lr_scheduler=ExponentialLR,
         lr_scheduler_kwargs=dict(gamma=0.99, verbose=False),
-        omega_initializer=pt.components.PCA(train_ds.data)
     )
 
     # Compute intermediate input and output sizes
-    #model.example_input_array = torch.zeros(4, 2)
+    model.example_input_array = torch.zeros(4, 4)
 
     # Callbacks
-    vis = pt.models.VisGMLVQ2D(data=train_ds, border=0.1)
+    vis = VisGMLVQ2D(data=train_ds)
 
     # Setup trainer
-    trainer = pl.Trainer.from_argparse_args(
-        args,
-        callbacks=[vis],
-        weights_summary="full",
-        accelerator="ddp",
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
+        callbacks=[
+            vis,
+        ],
+        max_epochs=100,
+        log_every_n_steps=1,
+        detect_anomaly=True,
     )
 
     # Training loop
     trainer.fit(model, train_loader)
+
+    torch.save(model, "iris.pth")

examples/gmlvq_mnist.py

@@ -1,18 +1,33 @@
 """GMLVQ example using the MNIST dataset."""
 
 import argparse
+import warnings
 
+import prototorch as pt
 import pytorch_lightning as pl
 import torch
+from lightning_fabric.utilities.seed import seed_everything
+from prototorch.models import (
+    ImageGMLVQ,
+    PruneLoserPrototypes,
+    VisImgComp,
+)
+from pytorch_lightning.callbacks import EarlyStopping
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
+from torch.utils.data import DataLoader
 from torchvision import transforms
 from torchvision.datasets import MNIST
 
-import prototorch as pt
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
+warnings.filterwarnings("ignore", category=UserWarning)
 
 if __name__ == "__main__":
+    # Reproducibility
+    seed_everything(seed=4)
     # Command-line arguments
     parser = argparse.ArgumentParser()
-    parser = pl.Trainer.add_argparse_args(parser)
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
     args = parser.parse_args()
 
     # Dataset
@@ -34,12 +49,8 @@ if __name__ == "__main__":
     )
 
     # Dataloaders
-    train_loader = torch.utils.data.DataLoader(train_ds,
-                                               num_workers=0,
-                                               batch_size=256)
-    test_loader = torch.utils.data.DataLoader(test_ds,
-                                              num_workers=0,
-                                              batch_size=256)
+    train_loader = DataLoader(train_ds, num_workers=4, batch_size=256)
+    test_loader = DataLoader(test_ds, num_workers=4, batch_size=256)
 
     # Hyperparameters
     num_classes = 10
@@ -53,14 +64,14 @@ if __name__ == "__main__":
     )
 
     # Initialize the model
-    model = pt.models.ImageGMLVQ(
+    model = ImageGMLVQ(
         hparams,
         optimizer=torch.optim.Adam,
-        prototype_initializer=pt.components.SMI(train_ds),
+        prototypes_initializer=pt.initializers.SMCI(train_ds),
     )
 
     # Callbacks
-    vis = pt.models.VisImgComp(
+    vis = VisImgComp(
         data=train_ds,
         num_columns=10,
         show=False,
@@ -70,14 +81,14 @@ if __name__ == "__main__":
         embedding_data=200,
         flatten_data=False,
     )
-    pruning = pt.models.PruneLoserPrototypes(
+    pruning = PruneLoserPrototypes(
         threshold=0.01,
         idle_epochs=1,
         prune_quota_per_epoch=10,
         frequency=1,
         verbose=True,
     )
-    es = pl.callbacks.EarlyStopping(
+    es = EarlyStopping(
         monitor="train_loss",
         min_delta=0.001,
         patience=15,
@@ -86,16 +97,18 @@ if __name__ == "__main__":
     )
 
     # Setup trainer
-    trainer = pl.Trainer.from_argparse_args(
-        args,
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
         callbacks=[
             vis,
             pruning,
-            # es,
+            es,
         ],
-        terminate_on_nan=True,
-        weights_summary=None,
-        accelerator="ddp",
+        max_epochs=1000,
+        log_every_n_steps=1,
+        detect_anomaly=True,
     )
 
     # Training loop

examples/gmlvq_spiral.py

@@ -0,0 +1,97 @@
+"""GMLVQ example using the spiral dataset."""
+
+import argparse
+import warnings
+
+import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from lightning_fabric.utilities.seed import seed_everything
+from prototorch.models import (
+    GMLVQ,
+    PruneLoserPrototypes,
+    VisGLVQ2D,
+)
+from pytorch_lightning.callbacks import EarlyStopping
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
+from torch.utils.data import DataLoader
+
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
+warnings.filterwarnings("ignore", category=UserWarning)
+
+if __name__ == "__main__":
+    # Reproducibility
+    seed_everything(seed=4)
+
+    # Command-line arguments
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
+    args = parser.parse_args()
+
+    # Dataset
+    train_ds = pt.datasets.Spiral(num_samples=500, noise=0.5)
+
+    # Dataloaders
+    train_loader = DataLoader(train_ds, batch_size=256)
+
+    # Hyperparameters
+    num_classes = 2
+    prototypes_per_class = 10
+    hparams = dict(
+        distribution=(num_classes, prototypes_per_class),
+        transfer_function="swish_beta",
+        transfer_beta=10.0,
+        proto_lr=0.1,
+        bb_lr=0.1,
+        input_dim=2,
+        latent_dim=2,
+    )
+
+    # Initialize the model
+    model = GMLVQ(
+        hparams,
+        optimizer=torch.optim.Adam,
+        prototypes_initializer=pt.initializers.SSCI(train_ds, noise=1e-2),
+    )
+
+    # Callbacks
+    vis = VisGLVQ2D(
+        train_ds,
+        show_last_only=False,
+        block=False,
+    )
+    pruning = PruneLoserPrototypes(
+        threshold=0.01,
+        idle_epochs=10,
+        prune_quota_per_epoch=5,
+        frequency=5,
+        replace=True,
+        prototypes_initializer=pt.initializers.SSCI(train_ds, noise=1e-1),
+        verbose=True,
+    )
+    es = EarlyStopping(
+        monitor="train_loss",
+        min_delta=1.0,
+        patience=5,
+        mode="min",
+        check_on_train_epoch_end=True,
+    )
+
+    # Setup trainer
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
+        callbacks=[
+            vis,
+            es,
+            pruning,
+        ],
+        max_epochs=1000,
+        log_every_n_steps=1,
+        detect_anomaly=True,
+    )
+
+    # Training loop
+    trainer.fit(model, train_loader)

examples/gng_iris.py

@@ -1,24 +1,33 @@
 """Growing Neural Gas example using the Iris dataset."""
 
 import argparse
-
-import pytorch_lightning as pl
-import torch
+import logging
+import warnings
 
 import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from lightning_fabric.utilities.seed import seed_everything
+from prototorch.models import GrowingNeuralGas, VisNG2D
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
+from torch.utils.data import DataLoader
+
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
+warnings.filterwarnings("ignore", category=UserWarning)
 
 if __name__ == "__main__":
     # Command-line arguments
     parser = argparse.ArgumentParser()
-    parser = pl.Trainer.add_argparse_args(parser)
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
     args = parser.parse_args()
 
     # Reproducibility
-    pl.utilities.seed.seed_everything(seed=42)
+    seed_everything(seed=42)
 
     # Prepare the data
     train_ds = pt.datasets.Iris(dims=[0, 2])
-    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=64)
+    train_loader = DataLoader(train_ds, batch_size=64)
 
     # Hyperparameters
     hparams = dict(
@@ -28,26 +37,31 @@ if __name__ == "__main__":
     )
 
     # Initialize the model
-    model = pt.models.GrowingNeuralGas(
+    model = GrowingNeuralGas(
         hparams,
-        prototype_initializer=pt.components.Zeros(2),
+        prototypes_initializer=pt.initializers.ZCI(2),
     )
 
     # Compute intermediate input and output sizes
     model.example_input_array = torch.zeros(4, 2)
 
     # Model summary
-    print(model)
+    logging.info(model)
 
     # Callbacks
-    vis = pt.models.VisNG2D(data=train_loader)
+    vis = VisNG2D(data=train_loader)
 
     # Setup trainer
-    trainer = pl.Trainer.from_argparse_args(
-        args,
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
+        callbacks=[
+            vis,
+        ],
         max_epochs=100,
-        callbacks=[vis],
-        weights_summary="full",
+        log_every_n_steps=1,
+        detect_anomaly=True,
     )
 
     # Training loop

examples/grlvq_iris.py

@@ -0,0 +1,77 @@
+"""GMLVQ example using the Iris dataset."""
+
+import argparse
+import warnings
+
+import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from lightning_fabric.utilities.seed import seed_everything
+from prototorch.models import GRLVQ, VisSiameseGLVQ2D
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
+from torch.optim.lr_scheduler import ExponentialLR
+from torch.utils.data import DataLoader
+
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
+warnings.filterwarnings("ignore", category=UserWarning)
+
+if __name__ == "__main__":
+
+    # Reproducibility
+    seed_everything(seed=4)
+
+    # Command-line arguments
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
+    args = parser.parse_args()
+
+    # Dataset
+    train_ds = pt.datasets.Iris([0, 1])
+
+    # Dataloaders
+    train_loader = DataLoader(train_ds, batch_size=64)
+
+    # Hyperparameters
+    hparams = dict(
+        input_dim=2,
+        distribution={
+            "num_classes": 3,
+            "per_class": 2
+        },
+        proto_lr=0.01,
+        bb_lr=0.01,
+    )
+
+    # Initialize the model
+    model = GRLVQ(
+        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, 2)
+
+    # Callbacks
+    vis = VisSiameseGLVQ2D(data=train_ds)
+
+    # Setup trainer
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
+        callbacks=[
+            vis,
+        ],
+        max_epochs=5,
+        log_every_n_steps=1,
+        detect_anomaly=True,
+    )
+
+    # Training loop
+    trainer.fit(model, train_loader)
+
+    torch.save(model, "iris.pth")

examples/gtlvq_mnist.py

@@ -0,0 +1,119 @@
+"""GTLVQ example using the MNIST dataset."""
+
+import argparse
+import warnings
+
+import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from lightning_fabric.utilities.seed import seed_everything
+from prototorch.models import (
+    ImageGTLVQ,
+    PruneLoserPrototypes,
+    VisImgComp,
+)
+from pytorch_lightning.callbacks import EarlyStopping
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
+from torch.utils.data import DataLoader
+from torchvision import transforms
+from torchvision.datasets import MNIST
+
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
+warnings.filterwarnings("ignore", category=UserWarning)
+
+if __name__ == "__main__":
+    # Reproducibility
+    seed_everything(seed=4)
+
+    # Command-line arguments
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
+    args = parser.parse_args()
+
+    # Dataset
+    train_ds = MNIST(
+        "~/datasets",
+        train=True,
+        download=True,
+        transform=transforms.Compose([
+            transforms.ToTensor(),
+        ]),
+    )
+    test_ds = MNIST(
+        "~/datasets",
+        train=False,
+        download=True,
+        transform=transforms.Compose([
+            transforms.ToTensor(),
+        ]),
+    )
+
+    # Dataloaders
+    train_loader = DataLoader(train_ds, num_workers=0, batch_size=256)
+    test_loader = DataLoader(test_ds, num_workers=0, batch_size=256)
+
+    # Hyperparameters
+    num_classes = 10
+    prototypes_per_class = 1
+    hparams = dict(
+        input_dim=28 * 28,
+        latent_dim=28,
+        distribution=(num_classes, prototypes_per_class),
+        proto_lr=0.01,
+        bb_lr=0.01,
+    )
+
+    # Initialize the model
+    model = ImageGTLVQ(
+        hparams,
+        optimizer=torch.optim.Adam,
+        prototypes_initializer=pt.initializers.SMCI(train_ds),
+        #Use one batch of data for subspace initiator.
+        omega_initializer=pt.initializers.PCALinearTransformInitializer(
+            next(iter(train_loader))[0].reshape(256, 28 * 28)))
+
+    # Callbacks
+    vis = VisImgComp(
+        data=train_ds,
+        num_columns=10,
+        show=False,
+        tensorboard=True,
+        random_data=100,
+        add_embedding=True,
+        embedding_data=200,
+        flatten_data=False,
+    )
+    pruning = PruneLoserPrototypes(
+        threshold=0.01,
+        idle_epochs=1,
+        prune_quota_per_epoch=10,
+        frequency=1,
+        verbose=True,
+    )
+    es = EarlyStopping(
+        monitor="train_loss",
+        min_delta=0.001,
+        patience=15,
+        mode="min",
+        check_on_train_epoch_end=True,
+    )
+
+    # Setup trainer
+    # using GPUs here is strongly recommended!
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
+        callbacks=[
+            vis,
+            pruning,
+            es,
+        ],
+        max_epochs=1000,
+        log_every_n_steps=1,
+        detect_anomaly=True,
+    )
+
+    # Training loop
+    trainer.fit(model, train_loader)

examples/gtlvq_moons.py

@@ -0,0 +1,79 @@
+"""Localized-GTLVQ example using the Moons dataset."""
+
+import argparse
+import logging
+import warnings
+
+import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from lightning_fabric.utilities.seed import seed_everything
+from prototorch.models import GTLVQ, VisGLVQ2D
+from pytorch_lightning.callbacks import EarlyStopping
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
+from torch.utils.data import DataLoader
+
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
+warnings.filterwarnings("ignore", category=UserWarning)
+
+if __name__ == "__main__":
+    # Command-line arguments
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
+    args = parser.parse_args()
+
+    # Reproducibility
+    seed_everything(seed=2)
+
+    # Dataset
+    train_ds = pt.datasets.Moons(num_samples=300, noise=0.2, seed=42)
+
+    # Dataloaders
+    train_loader = DataLoader(
+        train_ds,
+        batch_size=256,
+        shuffle=True,
+    )
+
+    # Hyperparameters
+    # Latent_dim should be lower than input dim.
+    hparams = dict(distribution=[1, 3], input_dim=2, latent_dim=1)
+
+    # Initialize the model
+    model = GTLVQ(hparams,
+                  prototypes_initializer=pt.initializers.SMCI(train_ds))
+
+    # Compute intermediate input and output sizes
+    model.example_input_array = torch.zeros(4, 2)
+
+    # Summary
+    logging.info(model)
+
+    # Callbacks
+    vis = VisGLVQ2D(data=train_ds)
+    es = EarlyStopping(
+        monitor="train_acc",
+        min_delta=0.001,
+        patience=20,
+        mode="max",
+        verbose=False,
+        check_on_train_epoch_end=True,
+    )
+
+    # Setup trainer
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
+        callbacks=[
+            vis,
+            es,
+        ],
+        max_epochs=1000,
+        log_every_n_steps=1,
+        detect_anomaly=True,
+    )
+
+    # Training loop
+    trainer.fit(model, train_loader)

examples/knn_iris.py

@@ -1,52 +1,75 @@
 """k-NN example using the Iris dataset from scikit-learn."""
 
 import argparse
-
-import pytorch_lightning as pl
-import torch
-from sklearn.datasets import load_iris
+import logging
+import warnings
 
 import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from prototorch.models import KNN, VisGLVQ2D
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
+from sklearn.datasets import load_iris
+from sklearn.model_selection import train_test_split
+from torch.utils.data import DataLoader
+
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
 
 if __name__ == "__main__":
     # Command-line arguments
     parser = argparse.ArgumentParser()
-    parser = pl.Trainer.add_argparse_args(parser)
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
     args = parser.parse_args()
 
     # Dataset
-    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)
+    X, y = load_iris(return_X_y=True)
+    X = X[:, 0:3:2]
+
+    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)
 
     # Dataloaders
-    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=150)
+    train_loader = DataLoader(train_ds, batch_size=16)
+    test_loader = DataLoader(test_ds, batch_size=16)
 
     # Hyperparameters
     hparams = dict(k=5)
 
     # Initialize the model
-    model = pt.models.KNN(hparams, data=train_ds)
+    model = KNN(hparams, data=train_ds)
 
     # Compute intermediate input and output sizes
     model.example_input_array = torch.zeros(4, 2)
 
     # Summary
-    print(model)
+    logging.info(model)
 
     # Callbacks
-    vis = pt.models.VisGLVQ2D(
-        data=(x_train, y_train),
+    vis = VisGLVQ2D(
+        data=(X_train, y_train),
         resolution=200,
         block=True,
     )
 
     # Setup trainer
-    trainer = pl.Trainer.from_argparse_args(
-        args,
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
         max_epochs=1,
-        callbacks=[vis],
-        weights_summary="full",
+        callbacks=[
+            vis,
+        ],
+        log_every_n_steps=1,
+        detect_anomaly=True,
     )
 
     # Training loop
@@ -54,5 +77,8 @@ if __name__ == "__main__":
     trainer.fit(model, train_loader)
 
     # Recall
-    y_pred = model.predict(torch.tensor(x_train))
-    print(y_pred)
+    y_pred = model.predict(torch.tensor(X_train))
+    logging.info(y_pred)
+
+    # Test
+    trainer.test(model, dataloaders=test_loader)

examples/ksom_colors.py

@@ -1,29 +1,25 @@
 """Kohonen Self Organizing Map."""
 
 import argparse
-
-import pytorch_lightning as pl
-import torch
-from matplotlib import pyplot as plt
+import logging
+import warnings
 
 import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from lightning_fabric.utilities.seed import seed_everything
+from matplotlib import pyplot as plt
+from prototorch.models import KohonenSOM
+from prototorch.utils.colors import hex_to_rgb
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
+from torch.utils.data import DataLoader, TensorDataset
 
-
-def hex_to_rgb(hex_values):
-    for v in hex_values:
-        v = v.lstrip('#')
-        lv = len(v)
-        c = [int(v[i:i + lv // 3], 16) for i in range(0, lv, lv // 3)]
-        yield c
-
-
-def rgb_to_hex(rgb_values):
-    for v in rgb_values:
-        c = "%02x%02x%02x" % tuple(v)
-        yield c
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
+warnings.filterwarnings("ignore", category=UserWarning)
 
 
 class Vis2DColorSOM(pl.Callback):
+
     def __init__(self, data, title="ColorSOMe", pause_time=0.1):
         super().__init__()
         self.title = title
@@ -31,7 +27,7 @@ class Vis2DColorSOM(pl.Callback):
         self.data = data
         self.pause_time = pause_time
 
-    def on_epoch_end(self, trainer, pl_module):
+    def on_train_epoch_end(self, trainer, pl_module: KohonenSOM):
         ax = self.fig.gca()
         ax.cla()
         ax.set_title(self.title)
@@ -44,12 +40,14 @@ class Vis2DColorSOM(pl.Callback):
         d = pl_module.compute_distances(self.data)
         wp = pl_module.predict_from_distances(d)
         for i, iloc in enumerate(wp):
-            plt.text(iloc[1],
+            plt.text(
+                iloc[1],
                 iloc[0],
-                     cnames[i],
+                color_names[i],
                 ha="center",
                 va="center",
-                     bbox=dict(facecolor="white", alpha=0.5, lw=0))
+                bbox=dict(facecolor="white", alpha=0.5, lw=0),
+            )
 
         if trainer.current_epoch != trainer.max_epochs - 1:
             plt.pause(self.pause_time)
@@ -60,11 +58,12 @@ class Vis2DColorSOM(pl.Callback):
 if __name__ == "__main__":
     # Command-line arguments
     parser = argparse.ArgumentParser()
-    parser = pl.Trainer.add_argparse_args(parser)
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
     args = parser.parse_args()
 
     # Reproducibility
-    pl.utilities.seed.seed_everything(seed=42)
+    seed_everything(seed=42)
 
     # Prepare the data
     hex_colors = [
@@ -72,15 +71,15 @@ if __name__ == "__main__":
         "#00ff00", "#ff0000", "#00ffff", "#ff00ff", "#ffff00", "#ffffff",
         "#545454", "#7f7f7f", "#a8a8a8", "#808000", "#800080", "#ffa500"
     ]
-    cnames = [
+    color_names = [
         "black", "blue", "darkblue", "skyblue", "greyblue", "lilac", "green",
         "red", "cyan", "magenta", "yellow", "white", "darkgrey", "mediumgrey",
         "lightgrey", "olive", "purple", "orange"
     ]
     colors = list(hex_to_rgb(hex_colors))
     data = torch.Tensor(colors) / 255.0
-    train_ds = torch.utils.data.TensorDataset(data)
-    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=8)
+    train_ds = TensorDataset(data)
+    train_loader = DataLoader(train_ds, batch_size=8)
 
     # Hyperparameters
     hparams = dict(
@@ -91,26 +90,31 @@ if __name__ == "__main__":
     )
 
     # Initialize the model
-    model = pt.models.KohonenSOM(
+    model = KohonenSOM(
         hparams,
-        prototype_initializer=pt.components.Random(3),
+        prototypes_initializer=pt.initializers.RNCI(3),
     )
 
     # Compute intermediate input and output sizes
     model.example_input_array = torch.zeros(4, 3)
 
     # Model summary
-    print(model)
+    logging.info(model)
 
     # Callbacks
     vis = Vis2DColorSOM(data=data)
 
     # Setup trainer
-    trainer = pl.Trainer.from_argparse_args(
-        args,
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
         max_epochs=500,
-        callbacks=[vis],
-        weights_summary="full",
+        callbacks=[
+            vis,
+        ],
+        log_every_n_steps=1,
+        detect_anomaly=True,
     )
 
     # Training loop

examples/lgmlvq_moons.py

@@ -1,28 +1,36 @@
 """Localized-GMLVQ example using the Moons dataset."""
 
 import argparse
-
-import pytorch_lightning as pl
-import torch
+import logging
+import warnings
 
 import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from lightning_fabric.utilities.seed import seed_everything
+from prototorch.models import LGMLVQ, VisGLVQ2D
+from pytorch_lightning.callbacks import EarlyStopping
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
+from torch.utils.data import DataLoader
+
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
+warnings.filterwarnings("ignore", category=UserWarning)
 
 if __name__ == "__main__":
     # Command-line arguments
     parser = argparse.ArgumentParser()
-    parser = pl.Trainer.add_argparse_args(parser)
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
     args = parser.parse_args()
 
+    # Reproducibility
+    seed_everything(seed=2)
+
     # Dataset
     train_ds = pt.datasets.Moons(num_samples=300, noise=0.2, seed=42)
 
-    # Reproducibility
-    pl.utilities.seed.seed_everything(seed=2)
-
     # Dataloaders
-    train_loader = torch.utils.data.DataLoader(train_ds,
-                                               batch_size=256,
-                                               shuffle=True)
+    train_loader = DataLoader(train_ds, batch_size=256, shuffle=True)
 
     # Hyperparameters
     hparams = dict(
@@ -32,18 +40,20 @@ if __name__ == "__main__":
     )
 
     # Initialize the model
-    model = pt.models.LGMLVQ(hparams,
-                             prototype_initializer=pt.components.SMI(train_ds))
+    model = LGMLVQ(
+        hparams,
+        prototypes_initializer=pt.initializers.SMCI(train_ds),
+    )
 
     # Compute intermediate input and output sizes
     model.example_input_array = torch.zeros(4, 2)
 
     # Summary
-    print(model)
+    logging.info(model)
 
     # Callbacks
-    vis = pt.models.VisGLVQ2D(data=train_ds)
-    es = pl.callbacks.EarlyStopping(
+    vis = VisGLVQ2D(data=train_ds)
+    es = EarlyStopping(
         monitor="train_acc",
         min_delta=0.001,
         patience=20,
@@ -53,14 +63,17 @@ if __name__ == "__main__":
     )
 
     # Setup trainer
-    trainer = pl.Trainer.from_argparse_args(
-        args,
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
         callbacks=[
             vis,
             es,
         ],
-        weights_summary="full",
-        accelerator="ddp",
+        log_every_n_steps=1,
+        max_epochs=1000,
+        detect_anomaly=True,
     )
 
     # Training loop

examples/liramlvq_tecator.py

@@ -1,90 +0,0 @@
-"""Limited Rank Matrix LVQ example using the Tecator dataset."""
-
-import argparse
-
-import matplotlib.pyplot as plt
-import pytorch_lightning as pl
-import torch
-
-import prototorch as pt
-
-
-def plot_matrix(matrix):
-    title = "Lambda matrix"
-    plt.figure(title)
-    plt.title(title)
-    plt.imshow(matrix, cmap="gray")
-    plt.axis("off")
-    plt.colorbar()
-    plt.show(block=True)
-
-
-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(root="~/datasets/", train=True)
-    test_ds = pt.datasets.Tecator(root="~/datasets/", train=False)
-
-    # Reproducibility
-    pl.utilities.seed.seed_everything(seed=10)
-
-    # Dataloaders
-    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=32)
-    test_loader = torch.utils.data.DataLoader(test_ds, batch_size=32)
-
-    # Hyperparameters
-    hparams = dict(
-        distribution={
-            "num_classes": 2,
-            "prototypes_per_class": 1
-        },
-        input_dim=100,
-        latent_dim=2,
-        proto_lr=0.0001,
-        bb_lr=0.0001,
-    )
-
-    # Initialize the model
-    model = pt.models.SiameseGMLVQ(
-        hparams,
-        # optimizer=torch.optim.SGD,
-        optimizer=torch.optim.Adam,
-        prototype_initializer=pt.components.SMI(train_ds),
-    )
-
-    # Summary
-    print(model)
-
-    # Callbacks
-    vis = pt.models.VisSiameseGLVQ2D(train_ds, border=0.1)
-    es = pl.callbacks.EarlyStopping(monitor="val_loss",
-                                    min_delta=0.001,
-                                    patience=50,
-                                    verbose=False,
-                                    mode="min")
-
-    # Setup trainer
-    trainer = pl.Trainer.from_argparse_args(
-        args,
-        callbacks=[vis, es],
-        weights_summary=None,
-    )
-
-    # Training loop
-    trainer.fit(model, train_loader, test_loader)
-
-    # Save the model
-    torch.save(model, "liramlvq_tecator.pt")
-
-    # Load a saved model
-    saved_model = torch.load("liramlvq_tecator.pt")
-
-    # Display the Lambda matrix
-    plot_matrix(saved_model.lambda_matrix)
-
-    # Testing
-    trainer.test(model, test_dataloaders=test_loader)

examples/lvqmln_iris.py

@@ -1,14 +1,26 @@
 """LVQMLN example using all four dimensions of the Iris dataset."""
 
 import argparse
-
-import pytorch_lightning as pl
-import torch
+import warnings
 
 import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from lightning_fabric.utilities.seed import seed_everything
+from prototorch.models import (
+    LVQMLN,
+    PruneLoserPrototypes,
+    VisSiameseGLVQ2D,
+)
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
+from torch.utils.data import DataLoader
+
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
+warnings.filterwarnings("ignore", category=UserWarning)
 
 
 class Backbone(torch.nn.Module):
+
     def __init__(self, input_size=4, hidden_size=10, latent_size=2):
         super().__init__()
         self.input_size = input_size
@@ -27,21 +39,22 @@ class Backbone(torch.nn.Module):
 if __name__ == "__main__":
     # Command-line arguments
     parser = argparse.ArgumentParser()
-    parser = pl.Trainer.add_argparse_args(parser)
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
     args = parser.parse_args()
 
     # Dataset
     train_ds = pt.datasets.Iris()
 
     # Reproducibility
-    pl.utilities.seed.seed_everything(seed=42)
+    seed_everything(seed=42)
 
     # Dataloaders
-    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=150)
+    train_loader = DataLoader(train_ds, batch_size=150)
 
     # Hyperparameters
     hparams = dict(
-        distribution=[1, 2, 2],
+        distribution=[3, 4, 5],
         proto_lr=0.001,
         bb_lr=0.001,
     )
@@ -50,28 +63,43 @@ if __name__ == "__main__":
     backbone = Backbone()
 
     # Initialize the model
-    model = pt.models.LVQMLN(
+    model = LVQMLN(
         hparams,
-        prototype_initializer=pt.components.SSI(train_ds, transform=backbone),
+        prototypes_initializer=pt.initializers.SSCI(
+            train_ds,
+            transform=backbone,
+        ),
         backbone=backbone,
     )
 
-    # Model summary
-    print(model)
-
     # Callbacks
-    vis = pt.models.VisSiameseGLVQ2D(
+    vis = VisSiameseGLVQ2D(
         data=train_ds,
         map_protos=False,
         border=0.1,
         resolution=500,
         axis_off=True,
     )
+    pruning = PruneLoserPrototypes(
+        threshold=0.01,
+        idle_epochs=20,
+        prune_quota_per_epoch=2,
+        frequency=10,
+        verbose=True,
+    )
 
     # Setup trainer
-    trainer = pl.Trainer.from_argparse_args(
-        args,
-        callbacks=[vis],
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
+        callbacks=[
+            vis,
+            pruning,
+        ],
+        log_every_n_steps=1,
+        max_epochs=1000,
+        detect_anomaly=True,
     )
 
     # Training loop

examples/median_lvq_iris.py

@@ -0,0 +1,71 @@
+"""Median-LVQ example using the Iris dataset."""
+
+import argparse
+import warnings
+
+import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from lightning_fabric.utilities.seed import seed_everything
+from prototorch.models import MedianLVQ, VisGLVQ2D
+from pytorch_lightning.callbacks import EarlyStopping
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
+from torch.utils.data import DataLoader
+
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
+warnings.filterwarnings("ignore", category=UserWarning)
+
+if __name__ == "__main__":
+    # Reproducibility
+    seed_everything(seed=4)
+    # Command-line arguments
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
+    args = parser.parse_args()
+
+    # Dataset
+    train_ds = pt.datasets.Iris(dims=[0, 2])
+
+    # Dataloaders
+    train_loader = DataLoader(
+        train_ds,
+        batch_size=len(train_ds),  # MedianLVQ cannot handle mini-batches
+    )
+
+    # Initialize the model
+    model = MedianLVQ(
+        hparams=dict(distribution=(3, 2), lr=0.01),
+        prototypes_initializer=pt.initializers.SSCI(train_ds),
+    )
+
+    # Compute intermediate input and output sizes
+    model.example_input_array = torch.zeros(4, 2)
+
+    # Callbacks
+    vis = VisGLVQ2D(data=train_ds)
+    es = EarlyStopping(
+        monitor="train_acc",
+        min_delta=0.01,
+        patience=5,
+        mode="max",
+        verbose=True,
+        check_on_train_epoch_end=True,
+    )
+
+    # Setup trainer
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
+        callbacks=[
+            vis,
+            es,
+        ],
+        max_epochs=1000,
+        log_every_n_steps=1,
+        detect_anomaly=True,
+    )
+
+    # Training loop
+    trainer.fit(model, train_loader)

examples/ng_iris.py

@@ -1,24 +1,35 @@
 """Neural Gas example using the Iris dataset."""
 
 import argparse
+import warnings
 
+import prototorch as pt
 import pytorch_lightning as pl
 import torch
+from lightning_fabric.utilities.seed import seed_everything
+from prototorch.models import NeuralGas, VisNG2D
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from sklearn.datasets import load_iris
 from sklearn.preprocessing import StandardScaler
 from torch.optim.lr_scheduler import ExponentialLR
+from torch.utils.data import DataLoader
 
-import prototorch as pt
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
+warnings.filterwarnings("ignore", category=UserWarning)
 
 if __name__ == "__main__":
+    # Reproducibility
+    seed_everything(seed=4)
+
     # Command-line arguments
     parser = argparse.ArgumentParser()
-    parser = pl.Trainer.add_argparse_args(parser)
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
     args = parser.parse_args()
 
     # Prepare and pre-process the dataset
     x_train, y_train = load_iris(return_X_y=True)
-    x_train = x_train[:, [0, 2]]
+    x_train = x_train[:, 0:3:2]
     scaler = StandardScaler()
     scaler.fit(x_train)
     x_train = scaler.transform(x_train)
@@ -26,7 +37,7 @@ if __name__ == "__main__":
     train_ds = pt.datasets.NumpyDataset(x_train, y_train)
 
     # Dataloaders
-    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=150)
+    train_loader = DataLoader(train_ds, batch_size=150)
 
     # Hyperparameters
     hparams = dict(
@@ -36,9 +47,9 @@ if __name__ == "__main__":
     )
 
     # Initialize the model
-    model = pt.models.NeuralGas(
+    model = NeuralGas(
         hparams,
-        prototype_initializer=pt.components.Zeros(2),
+        prototypes_initializer=pt.core.ZCI(2),
         lr_scheduler=ExponentialLR,
         lr_scheduler_kwargs=dict(gamma=0.99, verbose=False),
     )
@@ -46,17 +57,20 @@ if __name__ == "__main__":
     # Compute intermediate input and output sizes
     model.example_input_array = torch.zeros(4, 2)
 
-    # Model summary
-    print(model)
-
     # Callbacks
-    vis = pt.models.VisNG2D(data=train_ds)
+    vis = VisNG2D(data=train_ds)
 
     # Setup trainer
-    trainer = pl.Trainer.from_argparse_args(
-        args,
-        callbacks=[vis],
-        weights_summary="full",
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
+        callbacks=[
+            vis,
+        ],
+        max_epochs=1000,
+        log_every_n_steps=1,
+        detect_anomaly=True,
     )
 
     # Training loop

examples/rslvq_iris.py

@@ -1,64 +1,70 @@
 """RSLVQ example using the Iris dataset."""
 
 import argparse
-
-import pytorch_lightning as pl
-import torch
-from torchvision.transforms import Lambda
+import warnings
 
 import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from lightning_fabric.utilities.seed import seed_everything
+from prototorch.models import RSLVQ, VisGLVQ2D
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
+from torch.utils.data import DataLoader
+
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
+warnings.filterwarnings("ignore", category=UserWarning)
 
 if __name__ == "__main__":
     # Command-line arguments
     parser = argparse.ArgumentParser()
-    parser = pl.Trainer.add_argparse_args(parser)
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
     args = parser.parse_args()
 
     # Reproducibility
-    pl.utilities.seed.seed_everything(seed=42)
+    seed_everything(seed=42)
 
     # Dataset
     train_ds = pt.datasets.Iris(dims=[0, 2])
 
     # Dataloaders
-    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=64)
+    train_loader = DataLoader(train_ds, batch_size=64)
 
     # Hyperparameters
     hparams = dict(
         distribution=[2, 2, 3],
         proto_lr=0.05,
         lambd=0.1,
+        variance=1.0,
         input_dim=2,
         latent_dim=2,
         bb_lr=0.01,
     )
 
     # Initialize the model
-    model = pt.models.probabilistic.PLVQ(
+    model = RSLVQ(
         hparams,
         optimizer=torch.optim.Adam,
-        # prototype_initializer=pt.components.SMI(train_ds),
-        prototype_initializer=pt.components.SSI(train_ds, noise=0.2),
-        # prototype_initializer=pt.components.Zeros(2),
-        # prototype_initializer=pt.components.Ones(2, scale=2.0),
+        prototypes_initializer=pt.initializers.SSCI(train_ds, noise=0.2),
     )
 
     # Compute intermediate input and output sizes
     model.example_input_array = torch.zeros(4, 2)
 
-    # Summary
-    print(model)
-
     # Callbacks
-    vis = pt.models.VisSiameseGLVQ2D(data=train_ds)
+    vis = VisGLVQ2D(data=train_ds)
 
     # Setup trainer
-    trainer = pl.Trainer.from_argparse_args(
-        args,
-        callbacks=[vis],
-        terminate_on_nan=True,
-        weights_summary="full",
-        accelerator="ddp",
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
+        callbacks=[
+            vis,
+        ],
+        detect_anomaly=True,
+        max_epochs=100,
+        log_every_n_steps=1,
     )
 
     # Training loop

examples/siamese_glvq_iris.py

@@ -1,14 +1,22 @@
 """Siamese GLVQ example using all four dimensions of the Iris dataset."""
 
 import argparse
-
-import pytorch_lightning as pl
-import torch
+import warnings
 
 import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from lightning_fabric.utilities.seed import seed_everything
+from prototorch.models import SiameseGLVQ, VisSiameseGLVQ2D
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
+from torch.utils.data import DataLoader
+
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
+warnings.filterwarnings("ignore", category=UserWarning)
 
 
 class Backbone(torch.nn.Module):
+
     def __init__(self, input_size=4, hidden_size=10, latent_size=2):
         super().__init__()
         self.input_size = input_size
@@ -27,46 +35,50 @@ class Backbone(torch.nn.Module):
 if __name__ == "__main__":
     # Command-line arguments
     parser = argparse.ArgumentParser()
-    parser = pl.Trainer.add_argparse_args(parser)
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
     args = parser.parse_args()
 
     # Dataset
     train_ds = pt.datasets.Iris()
 
     # Reproducibility
-    pl.utilities.seed.seed_everything(seed=2)
+    seed_everything(seed=2)
 
     # Dataloaders
-    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=150)
+    train_loader = DataLoader(train_ds, batch_size=150)
 
     # Hyperparameters
     hparams = dict(
         distribution=[1, 2, 3],
-        proto_lr=0.01,
-        bb_lr=0.01,
+        lr=0.01,
     )
 
     # Initialize the backbone
     backbone = Backbone()
 
     # Initialize the model
-    model = pt.models.SiameseGLVQ(
+    model = SiameseGLVQ(
         hparams,
-        prototype_initializer=pt.components.SMI(train_ds),
+        prototypes_initializer=pt.initializers.SMCI(train_ds),
         backbone=backbone,
         both_path_gradients=False,
     )
 
-    # Model summary
-    print(model)
-
     # Callbacks
-    vis = pt.models.VisSiameseGLVQ2D(data=train_ds, border=0.1)
+    vis = VisSiameseGLVQ2D(data=train_ds, border=0.1)
 
     # Setup trainer
-    trainer = pl.Trainer.from_argparse_args(
-        args,
-        callbacks=[vis],
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
+        callbacks=[
+            vis,
+        ],
+        max_epochs=1000,
+        log_every_n_steps=1,
+        detect_anomaly=True,
     )
 
     # Training loop

examples/siamese_gtlvq_iris.py

@@ -0,0 +1,87 @@
+"""Siamese GTLVQ example using all four dimensions of the Iris dataset."""
+
+import argparse
+import warnings
+
+import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from lightning_fabric.utilities.seed import seed_everything
+from prototorch.models import SiameseGTLVQ, VisSiameseGLVQ2D
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
+from torch.utils.data import DataLoader
+
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
+warnings.filterwarnings("ignore", category=UserWarning)
+
+
+class Backbone(torch.nn.Module):
+
+    def __init__(self, input_size=4, hidden_size=10, latent_size=2):
+        super().__init__()
+        self.input_size = input_size
+        self.hidden_size = hidden_size
+        self.latent_size = latent_size
+        self.dense1 = torch.nn.Linear(self.input_size, self.hidden_size)
+        self.dense2 = torch.nn.Linear(self.hidden_size, self.latent_size)
+        self.activation = torch.nn.Sigmoid()
+
+    def forward(self, x):
+        x = self.activation(self.dense1(x))
+        out = self.activation(self.dense2(x))
+        return out
+
+
+if __name__ == "__main__":
+    # Command-line arguments
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
+    args = parser.parse_args()
+
+    # Dataset
+    train_ds = pt.datasets.Iris()
+
+    # Reproducibility
+    seed_everything(seed=2)
+
+    # Dataloaders
+    train_loader = DataLoader(train_ds, batch_size=150)
+
+    # Hyperparameters
+    hparams = dict(
+        distribution=[1, 2, 3],
+        lr=0.01,
+        input_dim=2,
+        latent_dim=1,
+    )
+
+    # Initialize the backbone
+    backbone = Backbone(latent_size=hparams["input_dim"])
+
+    # Initialize the model
+    model = SiameseGTLVQ(
+        hparams,
+        prototypes_initializer=pt.initializers.SMCI(train_ds),
+        backbone=backbone,
+        both_path_gradients=False,
+    )
+
+    # Callbacks
+    vis = VisSiameseGLVQ2D(data=train_ds, border=0.1)
+
+    # Setup trainer
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
+        callbacks=[
+            vis,
+        ],
+        max_epochs=1000,
+        log_every_n_steps=1,
+        detect_anomaly=True,
+    )
+
+    # Training loop
+    trainer.fit(model, train_loader)

examples/warm_starting.py

@@ -0,0 +1,129 @@
+"""Warm-starting GLVQ with prototypes from Growing Neural Gas."""
+
+import argparse
+import warnings
+
+import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from lightning_fabric.utilities.seed import seed_everything
+from prototorch.models import (
+    GLVQ,
+    KNN,
+    GrowingNeuralGas,
+    PruneLoserPrototypes,
+    VisGLVQ2D,
+)
+from pytorch_lightning.callbacks import EarlyStopping
+from pytorch_lightning.utilities.warnings import PossibleUserWarning
+from torch.optim.lr_scheduler import ExponentialLR
+from torch.utils.data import DataLoader
+
+warnings.filterwarnings("ignore", category=PossibleUserWarning)
+
+if __name__ == "__main__":
+
+    # Reproducibility
+    seed_everything(seed=4)
+    # Command-line arguments
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--gpus", type=int, default=0)
+    parser.add_argument("--fast_dev_run", type=bool, default=False)
+    args = parser.parse_args()
+
+    # Prepare the data
+    train_ds = pt.datasets.Iris(dims=[0, 2])
+    train_loader = DataLoader(train_ds, batch_size=64, num_workers=0)
+
+    # Initialize the gng
+    gng = GrowingNeuralGas(
+        hparams=dict(num_prototypes=5, insert_freq=2, lr=0.1),
+        prototypes_initializer=pt.initializers.ZCI(2),
+        lr_scheduler=ExponentialLR,
+        lr_scheduler_kwargs=dict(gamma=0.99, verbose=False),
+    )
+
+    # Callbacks
+    es = EarlyStopping(
+        monitor="loss",
+        min_delta=0.001,
+        patience=20,
+        mode="min",
+        verbose=False,
+        check_on_train_epoch_end=True,
+    )
+
+    # Setup trainer for GNG
+    trainer = pl.Trainer(
+        accelerator="cpu",
+        max_epochs=50 if args.fast_dev_run else
+        1000,  # 10 epochs fast dev run reproducible DIV error.
+        callbacks=[
+            es,
+        ],
+        log_every_n_steps=1,
+        detect_anomaly=True,
+    )
+
+    # Training loop
+    trainer.fit(gng, train_loader)
+
+    # Hyperparameters
+    hparams = dict(
+        distribution=[],
+        lr=0.01,
+    )
+
+    # Warm-start prototypes
+    knn = KNN(dict(k=1), data=train_ds)
+    prototypes = gng.prototypes
+    plabels = knn.predict(prototypes)
+
+    # Initialize the model
+    model = GLVQ(
+        hparams,
+        optimizer=torch.optim.Adam,
+        prototypes_initializer=pt.initializers.LCI(prototypes),
+        labels_initializer=pt.initializers.LLI(plabels),
+        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, 2)
+
+    # Callbacks
+    vis = VisGLVQ2D(data=train_ds)
+    pruning = PruneLoserPrototypes(
+        threshold=0.02,
+        idle_epochs=2,
+        prune_quota_per_epoch=5,
+        frequency=1,
+        verbose=True,
+    )
+    es = EarlyStopping(
+        monitor="train_loss",
+        min_delta=0.001,
+        patience=10,
+        mode="min",
+        verbose=True,
+        check_on_train_epoch_end=True,
+    )
+
+    # Setup trainer
+    trainer = pl.Trainer(
+        accelerator="cuda" if args.gpus else "cpu",
+        devices=args.gpus if args.gpus else "auto",
+        fast_dev_run=args.fast_dev_run,
+        callbacks=[
+            vis,
+            pruning,
+            es,
+        ],
+        max_epochs=1000,
+        log_every_n_steps=1,
+        detect_anomaly=True,
+    )
+
+    # Training loop
+    trainer.fit(model, train_loader)

prototorch/models/__init__.py

@@ -1,15 +0,0 @@
-"""`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 (GLVQ, GLVQ1, GLVQ21, GMLVQ, GRLVQ, LGMLVQ, LVQMLN,
-                   ImageGLVQ, ImageGMLVQ, SiameseGLVQ, SiameseGMLVQ)
-from .knn import KNN
-from .lvq import LVQ1, LVQ21, MedianLVQ
-from .probabilistic import CELVQ, PLVQ, RSLVQ, SLVQ
-from .unsupervised import GrowingNeuralGas, HeskesSOM, KohonenSOM, NeuralGas
-from .vis import *
-
-__version__ = "0.1.8"

prototorch/models/cbc.py

@@ -1,76 +0,0 @@
-import torch
-import torchmetrics
-
-from .abstract import ImagePrototypesMixin
-from .extras import (CosineSimilarity, MarginLoss, ReasoningLayer,
-                     euclidean_similarity, rescaled_cosine_similarity,
-                     shift_activation)
-from .glvq import SiameseGLVQ
-
-
-class CBC(SiameseGLVQ):
-    """Classification-By-Components."""
-    def __init__(self, hparams, margin=0.1, **kwargs):
-        super().__init__(hparams, **kwargs)
-        self.margin = margin
-        self.similarity_fn = kwargs.get("similarity_fn", euclidean_similarity)
-        num_components = self.components.shape[0]
-        self.reasoning_layer = ReasoningLayer(num_components=num_components,
-                                              num_classes=self.num_classes)
-        self.component_layer = self.proto_layer
-
-    @property
-    def components(self):
-        return self.prototypes
-
-    @property
-    def reasonings(self):
-        return self.reasoning_layer.reasonings.cpu()
-
-    def forward(self, x):
-        components, _ = self.component_layer()
-        latent_x = self.backbone(x)
-        self.backbone.requires_grad_(self.both_path_gradients)
-        latent_components = self.backbone(components)
-        self.backbone.requires_grad_(True)
-        detections = self.similarity_fn(latent_x, latent_components)
-        probs = self.reasoning_layer(detections)
-        return probs
-
-    def shared_step(self, batch, batch_idx, optimizer_idx=None):
-        x, y = batch
-        # x = x.view(x.size(0), -1)
-        y_pred = self(x)
-        num_classes = self.reasoning_layer.num_classes
-        y_true = torch.nn.functional.one_hot(y.long(), num_classes=num_classes)
-        loss = MarginLoss(self.margin)(y_pred, y_true).mean(dim=0)
-        return y_pred, loss
-
-    def training_step(self, batch, batch_idx, optimizer_idx=None):
-        y_pred, train_loss = self.shared_step(batch, batch_idx, optimizer_idx)
-        preds = torch.argmax(y_pred, dim=1)
-        accuracy = torchmetrics.functional.accuracy(preds.int(),
-                                                    batch[1].int())
-        self.log("train_acc",
-                 accuracy,
-                 on_step=False,
-                 on_epoch=True,
-                 prog_bar=True,
-                 logger=True)
-        return train_loss
-
-    def predict(self, x):
-        with torch.no_grad():
-            y_pred = self(x)
-            y_pred = torch.argmax(y_pred, dim=1)
-        return y_pred
-
-
-class ImageCBC(ImagePrototypesMixin, CBC):
-    """CBC model that constrains the components to the range [0, 1] by
-    clamping after updates.
-    """
-    def __init__(self, hparams, **kwargs):
-        super().__init__(hparams, **kwargs)
-        # Namespace hook
-        self.proto_layer = self.component_layer

prototorch/models/data.py

@@ -1,124 +0,0 @@
-"""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 pytorch_lightning as pl
-from torch.utils.data import DataLoader, Dataset, random_split
-from torchvision import transforms
-from torchvision.datasets import MNIST
-
-import prototorch as pt
-
-
-# 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

@@ -1,142 +0,0 @@
-"""prototorch.models.extras
-
-Modules not yet available in prototorch go here temporarily.
-
-"""
-
-import torch
-from prototorch.functions.distances import euclidean_distance
-from prototorch.functions.similarities import cosine_similarity
-
-
-def rescaled_cosine_similarity(x, y):
-    """Cosine Similarity rescaled to [0, 1]."""
-    similarities = cosine_similarity(x, y)
-    return (similarities + 1.0) / 2.0
-
-
-def shift_activation(x):
-    return (x + 1.0) / 2.0
-
-
-def euclidean_similarity(x, y, variance=1.0):
-    d = euclidean_distance(x, y)
-    return torch.exp(-(d * d) / (2 * variance))
-
-
-class ConnectionTopology(torch.nn.Module):
-    def __init__(self, agelimit, num_prototypes):
-        super().__init__()
-        self.agelimit = agelimit
-        self.num_prototypes = num_prototypes
-
-        self.cmat = torch.zeros((self.num_prototypes, self.num_prototypes))
-        self.age = torch.zeros_like(self.cmat)
-
-    def forward(self, d):
-        order = torch.argsort(d, dim=1)
-
-        for element in order:
-            i0, i1 = element[0], element[1]
-
-            self.cmat[i0][i1] = 1
-            self.cmat[i1][i0] = 1
-
-            self.age[i0][i1] = 0
-            self.age[i1][i0] = 0
-
-            self.age[i0][self.cmat[i0] == 1] += 1
-            self.age[i1][self.cmat[i1] == 1] += 1
-
-            self.cmat[i0][self.age[i0] > self.agelimit] = 0
-            self.cmat[i1][self.age[i1] > self.agelimit] = 0
-
-    def get_neighbors(self, position):
-        return torch.where(self.cmat[position])
-
-    def add_prototype(self):
-        new_cmat = torch.zeros([dim + 1 for dim in self.cmat.shape])
-        new_cmat[:-1, :-1] = self.cmat
-        self.cmat = new_cmat
-
-        new_age = torch.zeros([dim + 1 for dim in self.age.shape])
-        new_age[:-1, :-1] = self.age
-        self.age = new_age
-
-    def add_connection(self, a, b):
-        self.cmat[a][b] = 1
-        self.cmat[b][a] = 1
-
-        self.age[a][b] = 0
-        self.age[b][a] = 0
-
-    def remove_connection(self, a, b):
-        self.cmat[a][b] = 0
-        self.cmat[b][a] = 0
-
-        self.age[a][b] = 0
-        self.age[b][a] = 0
-
-    def extra_repr(self):
-        return f"(agelimit): ({self.agelimit})"
-
-
-class CosineSimilarity(torch.nn.Module):
-    def __init__(self, activation=shift_activation):
-        super().__init__()
-        self.activation = activation
-
-    def forward(self, x, y):
-        epsilon = torch.finfo(x.dtype).eps
-        normed_x = (x / x.pow(2).sum(dim=tuple(range(
-            1, x.ndim)), keepdim=True).clamp(min=epsilon).sqrt()).flatten(
-                start_dim=1)
-        normed_y = (y / y.pow(2).sum(dim=tuple(range(
-            1, y.ndim)), keepdim=True).clamp(min=epsilon).sqrt()).flatten(
-                start_dim=1)
-        # normed_x = (x / torch.linalg.norm(x, dim=1))
-        diss = torch.inner(normed_x, normed_y)
-        return self.activation(diss)
-
-
-class MarginLoss(torch.nn.modules.loss._Loss):
-    def __init__(self,
-                 margin=0.3,
-                 size_average=None,
-                 reduce=None,
-                 reduction="mean"):
-        super().__init__(size_average, reduce, reduction)
-        self.margin = margin
-
-    def forward(self, input_, target):
-        dp = torch.sum(target * input_, dim=-1)
-        dm = torch.max(input_ - target, dim=-1).values
-        return torch.nn.functional.relu(dm - dp + self.margin)
-
-
-class ReasoningLayer(torch.nn.Module):
-    def __init__(self, num_components, num_classes, num_replicas=1):
-        super().__init__()
-        self.num_replicas = num_replicas
-        self.num_classes = num_classes
-        probabilities_init = torch.zeros(2, 1, num_components,
-                                         self.num_classes)
-        probabilities_init.uniform_(0.4, 0.6)
-        # TODO Use `self.register_parameter("param", Paramater(param))` instead
-        self.reasoning_probabilities = torch.nn.Parameter(probabilities_init)
-
-    @property
-    def reasonings(self):
-        pk = self.reasoning_probabilities[0]
-        nk = (1 - pk) * self.reasoning_probabilities[1]
-        ik = 1 - pk - nk
-        img = torch.cat([pk, nk, ik], dim=0).permute(1, 0, 2)
-        return img.unsqueeze(1)
-
-    def forward(self, detections):
-        pk = self.reasoning_probabilities[0].clamp(0, 1)
-        nk = (1 - pk) * self.reasoning_probabilities[1].clamp(0, 1)
-        numerator = (detections @ (pk - nk)) + nk.sum(1)
-        probs = numerator / (pk + nk).sum(1)
-        probs = probs.squeeze(0)
-        return probs

prototorch/models/knn.py

@@ -1,38 +0,0 @@
-"""ProtoTorch KNN model."""
-
-import warnings
-
-from prototorch.components import LabeledComponents
-from prototorch.modules import KNNC
-
-from .abstract import SupervisedPrototypeModel
-
-
-class KNN(SupervisedPrototypeModel):
-    """K-Nearest-Neighbors classification algorithm."""
-    def __init__(self, hparams, **kwargs):
-        super().__init__(hparams, **kwargs)
-
-        # Default hparams
-        self.hparams.setdefault("k", 1)
-
-        data = kwargs.get("data", None)
-        if data is None:
-            raise ValueError("KNN requires data, but was not provided!")
-
-        # Layers
-        self.proto_layer = LabeledComponents(initialized_components=data)
-        self.competition_layer = KNNC(k=self.hparams.k)
-
-    def training_step(self, train_batch, batch_idx, optimizer_idx=None):
-        return 1  # skip training step
-
-    def on_train_batch_start(self,
-                             train_batch,
-                             batch_idx,
-                             dataloader_idx=None):
-        warnings.warn("k-NN has no training, skipping!")
-        return -1
-
-    def configure_optimizers(self):
-        return None

prototorch/models/lvq.py

@@ -1,68 +0,0 @@
-"""LVQ models that are optimized using non-gradient methods."""
-
-from prototorch.functions.losses import _get_dp_dm
-
-from .abstract import NonGradientMixin
-from .glvq import GLVQ
-
-
-class LVQ1(NonGradientMixin, GLVQ):
-    """Learning Vector Quantization 1."""
-    def training_step(self, train_batch, batch_idx, optimizer_idx=None):
-        protos = self.proto_layer.components
-        plabels = self.proto_layer.component_labels
-
-        x, y = train_batch
-        dis = self.compute_distances(x)
-        # TODO Vectorized implementation
-
-        for xi, yi in zip(x, y):
-            d = self.compute_distances(xi.view(1, -1))
-            preds = self.competition_layer(d, plabels)
-            w = d.argmin(1)
-            if yi == preds:
-                shift = xi - protos[w]
-            else:
-                shift = protos[w] - xi
-            updated_protos = protos + 0.0
-            updated_protos[w] = protos[w] + (self.hparams.lr * shift)
-            self.proto_layer.load_state_dict({"_components": updated_protos},
-                                             strict=False)
-
-        # Logging
-        self.log_acc(dis, y, tag="train_acc")
-
-        return None
-
-
-class LVQ21(NonGradientMixin, GLVQ):
-    """Learning Vector Quantization 2.1."""
-    def training_step(self, train_batch, batch_idx, optimizer_idx=None):
-        protos = self.proto_layer.components
-        plabels = self.proto_layer.component_labels
-
-        x, y = train_batch
-        dis = self.compute_distances(x)
-        # TODO Vectorized implementation
-
-        for xi, yi in zip(x, y):
-            xi = xi.view(1, -1)
-            yi = yi.view(1, )
-            d = self.compute_distances(xi)
-            (_, wp), (_, wn) = _get_dp_dm(d, yi, plabels, with_indices=True)
-            shiftp = xi - protos[wp]
-            shiftn = protos[wn] - xi
-            updated_protos = protos + 0.0
-            updated_protos[wp] = protos[wp] + (self.hparams.lr * shiftp)
-            updated_protos[wn] = protos[wn] + (self.hparams.lr * shiftn)
-            self.proto_layer.load_state_dict({"_components": updated_protos},
-                                             strict=False)
-
-        # Logging
-        self.log_acc(dis, y, tag="train_acc")
-
-        return None
-
-
-class MedianLVQ(NonGradientMixin, GLVQ):
-    """Median LVQ"""

pyproject.toml

@@ -0,0 +1,90 @@
+
+[project]
+name = "prototorch-models"
+version = "0.7.1"
+description = "Pre-packaged prototype-based machine learning models using ProtoTorch and PyTorch-Lightning."
+authors = [
+    { name = "Jensun Ravichandran", email = "jjensun@gmail.com" },
+    { name = "Alexander Engelsberger", email = "engelsbe@hs-mittweida.de" },
+]
+dependencies = ["lightning>=2.0.0", "prototorch>=0.7.5"]
+requires-python = ">=3.8"
+readme = "README.md"
+license = { text = "MIT" }
+classifiers = [
+    "Development Status :: 2 - Pre-Alpha",
+    "Environment :: Plugins",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Education",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: MIT License",
+    "Natural Language :: English",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Software Development :: Libraries",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+]
+
+[project.urls]
+Homepage = "https://github.com/si-cim/prototorch_models"
+Downloads = "https://github.com/si-cim/prototorch_models.git"
+
+[project.optional-dependencies]
+dev = ["bumpversion", "pre-commit", "yapf", "toml"]
+examples = ["matplotlib", "scikit-learn"]
+ci = ["pytest", "pre-commit"]
+docs = [
+    "recommonmark",
+    "nbsphinx",
+    "sphinx",
+    "sphinx_rtd_theme",
+    "sphinxcontrib-bibtex",
+    "sphinxcontrib-katex",
+    "ipykernel",
+]
+all = [
+    "bumpversion",
+    "pre-commit",
+    "yapf",
+    "toml",
+    "pytest",
+    "matplotlib",
+    "scikit-learn",
+    "recommonmark",
+    "nbsphinx",
+    "sphinx",
+    "sphinx_rtd_theme",
+    "sphinxcontrib-bibtex",
+    "sphinxcontrib-katex",
+    "ipykernel",
+]
+
+[build-system]
+requires = ["setuptools>=61", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[tool.yapf]
+based_on_style = "pep8"
+spaces_before_comment = 2
+split_before_logical_operator = true
+
+[tool.pylint]
+disable = ["too-many-arguments", "too-few-public-methods", "fixme"]
+
+[tool.isort]
+profile = "hug"
+src_paths = ["isort", "test"]
+multi_line_output = 3
+include_trailing_comma = true
+force_grid_wrap = 3
+use_parentheses = true
+line_length = 79
+
+[tool.mypy]
+explicit_package_bases = true
+namespace_packages = true

setup.py

@@ -1,93 +0,0 @@
-"""
-
- ######
- #     # #####   ####  #####  ####  #####  ####  #####   ####  #    #
- #     # #    # #    #   #   #    #   #   #    # #    # #    # #    #
- ######  #    # #    #   #   #    #   #   #    # #    # #      ######
- #       #####  #    #   #   #    #   #   #    # #####  #      #    #
- #       #   #  #    #   #   #    #   #   #    # #   #  #    # #    #
- #       #    #  ####    #    ####    #    ####  #    #  ####  #    #Plugin
-
-ProtoTorch models Plugin Package
-"""
-from pkg_resources import safe_name
-from setuptools import find_namespace_packages, setup
-
-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", "r") as fh:
-    long_description = fh.read()
-
-INSTALL_REQUIRES = [
-    "prototorch>=0.5.0,<0.6.0",
-    "pytorch_lightning>=1.3.5",
-    "torchmetrics",
-]
-CLI = [
-    "jsonargparse",
-]
-DEV = [
-    "bumpversion",
-    "pre-commit",
-]
-DOCS = [
-    "recommonmark",
-    "sphinx",
-    "nbsphinx",
-    "sphinx_rtd_theme",
-    "sphinxcontrib-katex",
-    "sphinxcontrib-bibtex",
-]
-EXAMPLES = [
-    "matplotlib",
-    "scikit-learn",
-]
-TESTS = [
-    "codecov",
-    "pytest",
-]
-ALL = CLI + DEV + DOCS + EXAMPLES + TESTS
-
-setup(
-    name=safe_name("prototorch_" + PLUGIN_NAME),
-    version="0.1.8",
-    description="Pre-packaged prototype-based "
-    "machine learning models using ProtoTorch and PyTorch-Lightning.",
-    long_description=long_description,
-    long_description_content_type="text/markdown",
-    author="Alexander Engelsberger",
-    author_email="engelsbe@hs-mittweida.de",
-    url=PROJECT_URL,
-    download_url=DOWNLOAD_URL,
-    license="MIT",
-    python_requires=">=3.9",
-    install_requires=INSTALL_REQUIRES,
-    extras_require={
-        "dev": DEV,
-        "examples": EXAMPLES,
-        "tests": TESTS,
-        "all": ALL,
-    },
-    classifiers=[
-        "Development Status :: 2 - Pre-Alpha",
-        "Environment :: Plugins",
-        "Intended Audience :: Developers",
-        "Intended Audience :: Education",
-        "Intended Audience :: Science/Research",
-        "License :: OSI Approved :: MIT License",
-        "Natural Language :: English",
-        "Programming Language :: Python :: 3.9",
-        "Operating System :: OS Independent",
-        "Topic :: Scientific/Engineering :: Artificial Intelligence",
-        "Topic :: Software Development :: Libraries",
-        "Topic :: Software Development :: Libraries :: Python Modules",
-    ],
-    entry_points={
-        "prototorch.plugins": f"{PLUGIN_NAME} = prototorch.{PLUGIN_NAME}"
-    },
-    packages=find_namespace_packages(include=["prototorch.*"]),
-    zip_safe=False,
-)

src/prototorch/models/__init__.py

@@ -0,0 +1,39 @@
+"""`models` plugin for the `prototorch` package."""
+
+from .callbacks import PrototypeConvergence, PruneLoserPrototypes
+from .cbc import CBC, ImageCBC
+from .glvq import (
+    GLVQ,
+    GLVQ1,
+    GLVQ21,
+    GMLVQ,
+    GRLVQ,
+    GTLVQ,
+    LGMLVQ,
+    LVQMLN,
+    ImageGLVQ,
+    ImageGMLVQ,
+    ImageGTLVQ,
+    SiameseGLVQ,
+    SiameseGMLVQ,
+    SiameseGTLVQ,
+)
+from .knn import KNN
+from .lvq import (
+    LVQ1,
+    LVQ21,
+    MedianLVQ,
+)
+from .probabilistic import (
+    CELVQ,
+    RSLVQ,
+    SLVQ,
+)
+from .unsupervised import (
+    GrowingNeuralGas,
+    KohonenSOM,
+    NeuralGas,
+)
+from .vis import *
+
+__version__ = "0.7.1"

src/prototorch/models/abstract.py

@@ -1,29 +1,29 @@
 """Abstract classes to be inherited by prototorch models."""
 
-from typing import Final, final
+import logging
 
 import pytorch_lightning as pl
 import torch
+import torch.nn.functional as F
 import torchmetrics
-from prototorch.components import Components, LabeledComponents
-from prototorch.functions.distances import euclidean_distance
-from prototorch.modules import WTAC, LambdaLayer
-
-
-class ProtoTorchMixin(object):
-    pass
+from prototorch.core.competitions import WTAC
+from prototorch.core.components import (
+    AbstractComponents,
+    Components,
+    LabeledComponents,
+)
+from prototorch.core.distances import euclidean_distance
+from prototorch.core.initializers import (
+    LabelsInitializer,
+    ZerosCompInitializer,
+)
+from prototorch.core.pooling import stratified_min_pooling
+from prototorch.nn.wrappers import LambdaLayer
 
 
 class ProtoTorchBolt(pl.LightningModule):
     """All ProtoTorch models are ProtoTorch Bolts."""
-    def __repr__(self):
-        surep = super().__repr__()
-        indented = "".join([f"\t{line}\n" for line in surep.splitlines()])
-        wrapped = f"ProtoTorch Bolt(\n{indented})"
-        return wrapped
 
-
-class PrototypeModel(ProtoTorchBolt):
     def __init__(self, hparams, **kwargs):
         super().__init__()
 
@@ -38,8 +38,40 @@ class PrototypeModel(ProtoTorchBolt):
         self.lr_scheduler = kwargs.get("lr_scheduler", None)
         self.lr_scheduler_kwargs = kwargs.get("lr_scheduler_kwargs", dict())
 
+    def configure_optimizers(self):
+        optimizer = self.optimizer(self.parameters(), lr=self.hparams["lr"])
+        if self.lr_scheduler is not None:
+            scheduler = self.lr_scheduler(optimizer,
+                                          **self.lr_scheduler_kwargs)
+            sch = {
+                "scheduler": scheduler,
+                "interval": "step",
+            }  # called after each training step
+            return [optimizer], [sch]
+        else:
+            return optimizer
+
+    def reconfigure_optimizers(self):
+        if self.trainer:
+            self.trainer.strategy.setup_optimizers(self.trainer)
+        else:
+            logging.warning("No trainer to reconfigure optimizers!")
+
+    def __repr__(self):
+        surep = super().__repr__()
+        indented = "".join([f"\t{line}\n" for line in surep.splitlines()])
+        wrapped = f"ProtoTorch Bolt(\n{indented})"
+        return wrapped
+
+
+class PrototypeModel(ProtoTorchBolt):
+    proto_layer: AbstractComponents
+
+    def __init__(self, hparams, **kwargs):
+        super().__init__(hparams, **kwargs)
+
         distance_fn = kwargs.get("distance_fn", euclidean_distance)
-        self.distance_layer = LambdaLayer(distance_fn)
+        self.distance_layer = LambdaLayer(distance_fn, name="distance_fn")
 
     @property
     def num_prototypes(self):
@@ -54,48 +86,33 @@ class PrototypeModel(ProtoTorchBolt):
         """Only an alias for the prototypes."""
         return self.prototypes
 
-    def configure_optimizers(self):
-        optimizer = self.optimizer(self.parameters(), lr=self.hparams.lr)
-        if self.lr_scheduler is not None:
-            scheduler = self.lr_scheduler(optimizer,
-                                          **self.lr_scheduler_kwargs)
-            sch = {
-                "scheduler": scheduler,
-                "interval": "step",
-            }  # called after each training step
-            return [optimizer], [sch]
-        else:
-            return optimizer
-
-    @final
-    def reconfigure_optimizers(self):
-        self.trainer.accelerator_backend.setup_optimizers(self.trainer)
-
     def add_prototypes(self, *args, **kwargs):
         self.proto_layer.add_components(*args, **kwargs)
+        self.hparams["distribution"] = self.proto_layer.distribution
         self.reconfigure_optimizers()
 
     def remove_prototypes(self, indices):
         self.proto_layer.remove_components(indices)
+        self.hparams["distribution"] = self.proto_layer.distribution
         self.reconfigure_optimizers()
 
 
 class UnsupervisedPrototypeModel(PrototypeModel):
+    proto_layer: Components
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
         # Layers
-        prototype_initializer = kwargs.get("prototype_initializer", None)
-        initialized_prototypes = kwargs.get("initialized_prototypes", None)
-        if prototype_initializer is not None or initialized_prototypes is not None:
+        prototypes_initializer = kwargs.get("prototypes_initializer", None)
+        if prototypes_initializer is not None:
             self.proto_layer = Components(
-                self.hparams.num_prototypes,
-                initializer=prototype_initializer,
-                initialized_components=initialized_prototypes,
+                self.hparams["num_prototypes"],
+                initializer=prototypes_initializer,
             )
 
     def compute_distances(self, x):
-        protos = self.proto_layer()
+        protos = self.proto_layer().type_as(x)
         distances = self.distance_layer(x, protos)
         return distances
 
@@ -105,27 +122,43 @@ class UnsupervisedPrototypeModel(PrototypeModel):
 
 
 class SupervisedPrototypeModel(PrototypeModel):
-    def __init__(self, hparams, **kwargs):
+    proto_layer: LabeledComponents
+
+    def __init__(self, hparams, skip_proto_layer=False, **kwargs):
         super().__init__(hparams, **kwargs)
 
         # Layers
-        prototype_initializer = kwargs.get("prototype_initializer", None)
-        initialized_prototypes = kwargs.get("initialized_prototypes", None)
-        if prototype_initializer is not None or initialized_prototypes is not None:
+        distribution = hparams.get("distribution", None)
+        prototypes_initializer = kwargs.get("prototypes_initializer", None)
+        labels_initializer = kwargs.get("labels_initializer",
+                                        LabelsInitializer())
+        if not skip_proto_layer:
+            # when subclasses do not need a customized prototype layer
+            if prototypes_initializer is not None:
+                # when building a new model
                 self.proto_layer = LabeledComponents(
-                distribution=self.hparams.distribution,
-                initializer=prototype_initializer,
-                initialized_components=initialized_prototypes,
+                    distribution=distribution,
+                    components_initializer=prototypes_initializer,
+                    labels_initializer=labels_initializer,
+                )
+                proto_shape = self.proto_layer.components.shape[1:]
+                self.hparams["initialized_proto_shape"] = proto_shape
+            else:
+                # when restoring a checkpointed model
+                self.proto_layer = LabeledComponents(
+                    distribution=distribution,
+                    components_initializer=ZerosCompInitializer(
+                        self.hparams["initialized_proto_shape"]),
                 )
         self.competition_layer = WTAC()
 
     @property
     def prototype_labels(self):
-        return self.proto_layer.component_labels.detach().cpu()
+        return self.proto_layer.labels.detach().cpu()
 
     @property
     def num_classes(self):
-        return len(self.proto_layer.distribution)
+        return self.proto_layer.num_classes
 
     def compute_distances(self, x):
         protos, _ = self.proto_layer()
@@ -134,15 +167,14 @@ class SupervisedPrototypeModel(PrototypeModel):
 
     def forward(self, x):
         distances = self.compute_distances(x)
-        y_pred = self.predict_from_distances(distances)
-        # TODO
-        y_pred = torch.eye(self.num_classes, device=self.device)[
-            y_pred.long()]  # depends on labels {0,...,num_classes}
+        _, plabels = self.proto_layer()
+        winning = stratified_min_pooling(distances, plabels)
+        y_pred = F.softmin(winning, dim=1)
         return y_pred
 
     def predict_from_distances(self, distances):
         with torch.no_grad():
-            plabels = self.proto_layer.component_labels
+            _, plabels = self.proto_layer()
             y_pred = self.competition_layer(distances, plabels)
         return y_pred
 
@@ -154,31 +186,57 @@ class SupervisedPrototypeModel(PrototypeModel):
 
     def log_acc(self, distances, targets, tag):
         preds = self.predict_from_distances(distances)
-        accuracy = torchmetrics.functional.accuracy(preds.int(), targets.int())
-        # `.int()` because FloatTensors are assumed to be class probabilities
+        accuracy = torchmetrics.functional.accuracy(
+            preds.int(),
+            targets.int(),
+            "multiclass",
+            num_classes=self.num_classes,
+        )
 
-        self.log(tag,
+        self.log(
+            tag,
             accuracy,
             on_step=False,
             on_epoch=True,
             prog_bar=True,
-                 logger=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(),
+            "multiclass",
+            num_classes=self.num_classes,
+        )
+
+        self.log("test_acc", accuracy)
+
+
+class ProtoTorchMixin:
+    """All mixins are ProtoTorchMixins."""
 
 
 class NonGradientMixin(ProtoTorchMixin):
     """Mixin for custom non-gradient optimization."""
+
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
-        self.automatic_optimization: Final = False
+        self.automatic_optimization = False
 
-    def training_step(self, train_batch, batch_idx, optimizer_idx=None):
+    def training_step(self, train_batch, batch_idx):
         raise NotImplementedError
 
 
 class ImagePrototypesMixin(ProtoTorchMixin):
     """Mixin for models with image prototypes."""
-    @final
-    def on_train_batch_end(self, outputs, batch, batch_idx, dataloader_idx):
+    proto_layer: Components
+    components: torch.Tensor
+
+    def on_train_batch_end(self, outputs, batch, batch_idx):
         """Constrain the components to the range [0, 1] by clamping after updates."""
         self.proto_layer.components.data.clamp_(0.0, 1.0)
 

src/prototorch/models/callbacks.py

@@ -1,32 +1,39 @@
 """Lightning Callbacks."""
 
 import logging
+from typing import TYPE_CHECKING
 
 import pytorch_lightning as pl
 import torch
-from prototorch.components import Components
+from prototorch.core.initializers import LiteralCompInitializer
 
 from .extras import ConnectionTopology
 
+if TYPE_CHECKING:
+    from prototorch.models import GLVQ, GrowingNeuralGas
+
 
 class PruneLoserPrototypes(pl.Callback):
-    def __init__(self,
+
+    def __init__(
+        self,
         threshold=0.01,
         idle_epochs=10,
         prune_quota_per_epoch=-1,
         frequency=1,
         replace=False,
-                 initializer=None,
-                 verbose=False):
+        prototypes_initializer=None,
+        verbose=False,
+    ):
         self.threshold = threshold  # minimum win ratio
         self.idle_epochs = idle_epochs  # epochs to wait before pruning
         self.prune_quota_per_epoch = prune_quota_per_epoch
         self.frequency = frequency
         self.replace = replace
         self.verbose = verbose
-        self.initializer = initializer
+        self.prototypes_initializer = prototypes_initializer
 
-    def on_epoch_end(self, trainer, pl_module):
+    def on_train_epoch_end(self, trainer, pl_module: "GLVQ"):
         if (trainer.current_epoch + 1) < self.idle_epochs:
             return None
         if (trainer.current_epoch + 1) % self.frequency:
@@ -41,40 +48,44 @@ class PruneLoserPrototypes(pl.Callback):
             prune_labels = prune_labels[:self.prune_quota_per_epoch]
 
         if len(to_prune) > 0:
-            if self.verbose:
-                print(f"\nPrototype win ratios: {ratios}")
-                print(f"Pruning prototypes at: {to_prune}")
-                print(f"Corresponding labels are: {prune_labels.tolist()}")
+            logging.debug(f"\nPrototype win ratios: {ratios}")
+            logging.debug(f"Pruning prototypes at: {to_prune}")
+            logging.debug(f"Corresponding labels are: {prune_labels.tolist()}")
+
             cur_num_protos = pl_module.num_prototypes
             pl_module.remove_prototypes(indices=to_prune)
+
             if self.replace:
                 labels, counts = torch.unique(prune_labels,
                                               sorted=True,
                                               return_counts=True)
                 distribution = dict(zip(labels.tolist(), counts.tolist()))
-                if self.verbose:
-                    print(f"Re-adding pruned prototypes...")
-                    print(f"{distribution=}")
-                pl_module.add_prototypes(distribution=distribution,
-                                         initializer=self.initializer)
+
+                logging.info(f"Re-adding pruned prototypes...")
+                logging.debug(f"distribution={distribution}")
+
+                pl_module.add_prototypes(
+                    distribution=distribution,
+                    components_initializer=self.prototypes_initializer)
             new_num_protos = pl_module.num_prototypes
-            if self.verbose:
-                print(f"`num_prototypes` changed from {cur_num_protos} "
+
+            logging.info(f"`num_prototypes` changed from {cur_num_protos} "
                          f"to {new_num_protos}.")
         return True
 
 
 class PrototypeConvergence(pl.Callback):
+
     def __init__(self, min_delta=0.01, idle_epochs=10, verbose=False):
         self.min_delta = min_delta
         self.idle_epochs = idle_epochs  # epochs to wait
         self.verbose = verbose
 
-    def on_epoch_end(self, trainer, pl_module):
+    def on_train_epoch_end(self, trainer, pl_module):
         if (trainer.current_epoch + 1) < self.idle_epochs:
             return None
-        if self.verbose:
-            print("Stopping...")
+
+        logging.info("Stopping...")
         # TODO
         return True
 
@@ -87,16 +98,21 @@ class GNGCallback(pl.Callback):
     Based on "A Growing Neural Gas Network Learns Topologies" by Bernd Fritzke.
 
     """
+
     def __init__(self, reduction=0.1, freq=10):
         self.reduction = reduction
         self.freq = freq
 
-    def on_epoch_end(self, trainer: pl.Trainer, pl_module):
+    def on_train_epoch_end(
+        self,
+        trainer: pl.Trainer,
+        pl_module: "GrowingNeuralGas",
+    ):
         if (trainer.current_epoch + 1) % self.freq == 0:
             # Get information
             errors = pl_module.errors
             topology: ConnectionTopology = pl_module.topology_layer
-            components: Components = pl_module.proto_layer.components
+            components = pl_module.proto_layer.components
 
             # Insertion point
             worst = torch.argmax(errors)
@@ -116,7 +132,9 @@ class GNGCallback(pl.Callback):
 
             # Add component
             pl_module.proto_layer.add_components(
-                initialized_components=new_component.unsqueeze(0))
+                1,
+                initializer=LiteralCompInitializer(new_component.unsqueeze(0)),
+            )
 
             # Adjust Topology
             topology.add_prototype()
@@ -131,4 +149,4 @@ class GNGCallback(pl.Callback):
             pl_module.errors[
                 worst_neighbor] = errors[worst_neighbor] * self.reduction
 
-            trainer.accelerator_backend.setup_optimizers(trainer)
+            trainer.strategy.setup_optimizers(trainer)

src/prototorch/models/cbc.py

@@ -0,0 +1,84 @@
+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 .abstract import ImagePrototypesMixin
+from .glvq import SiameseGLVQ
+
+
+class CBC(SiameseGLVQ):
+    """Classification-By-Components."""
+
+    def __init__(self, hparams, **kwargs):
+        super().__init__(hparams, skip_proto_layer=True, **kwargs)
+
+        similarity_fn = kwargs.get("similarity_fn", euclidean_similarity)
+        components_initializer = kwargs.get("components_initializer", None)
+        reasonings_initializer = kwargs.get("reasonings_initializer",
+                                            RandomReasoningsInitializer())
+        self.components_layer = ReasoningComponents(
+            self.hparams.distribution,
+            components_initializer=components_initializer,
+            reasonings_initializer=reasonings_initializer,
+        )
+        self.similarity_layer = LambdaLayer(similarity_fn)
+        self.competition_layer = CBCC()
+
+        # Namespace hook
+        self.proto_layer = self.components_layer
+
+        self.loss = MarginLoss(self.hparams.margin)
+
+    def forward(self, x):
+        components, reasonings = self.components_layer()
+        latent_x = self.backbone(x)
+        self.backbone.requires_grad_(self.both_path_gradients)
+        latent_components = self.backbone(components)
+        self.backbone.requires_grad_(True)
+        detections = self.similarity_layer(latent_x, latent_components)
+        probs = self.competition_layer(detections, reasonings)
+        return probs
+
+    def shared_step(self, batch, batch_idx):
+        x, y = batch
+        y_pred = self(x)
+        num_classes = self.num_classes
+        y_true = torch.nn.functional.one_hot(y.long(), num_classes=num_classes)
+        loss = self.loss(y_pred, y_true).mean()
+        return y_pred, loss
+
+    def training_step(self, batch, batch_idx):
+        y_pred, train_loss = self.shared_step(batch, batch_idx)
+        preds = torch.argmax(y_pred, dim=1)
+        accuracy = torchmetrics.functional.accuracy(
+            preds.int(),
+            batch[1].int(),
+            "multiclass",
+            num_classes=self.num_classes,
+        )
+        self.log(
+            "train_acc",
+            accuracy,
+            on_step=False,
+            on_epoch=True,
+            prog_bar=True,
+            logger=True,
+        )
+        return train_loss
+
+    def predict(self, x):
+        with torch.no_grad():
+            y_pred = self(x)
+            y_pred = torch.argmax(y_pred, dim=1)
+        return y_pred
+
+
+class ImageCBC(ImagePrototypesMixin, CBC):
+    """CBC model that constrains the components to the range [0, 1] by
+    clamping after updates.
+    """

src/prototorch/models/extras.py

@@ -0,0 +1,130 @@
+"""prototorch.models.extras
+
+Modules not yet available in prototorch go here temporarily.
+
+"""
+
+import torch
+from prototorch.core.similarities import gaussian
+
+
+def rank_scaled_gaussian(distances, lambd):
+    order = torch.argsort(distances, dim=1)
+    ranks = torch.argsort(order, dim=1)
+    return torch.exp(-torch.exp(-ranks / lambd) * distances)
+
+
+def orthogonalization(tensors):
+    """Orthogonalization via polar decomposition """
+    u, _, v = torch.svd(tensors, compute_uv=True)
+    u_shape = tuple(list(u.shape))
+    v_shape = tuple(list(v.shape))
+
+    # reshape to (num x N x M)
+    u = torch.reshape(u, (-1, u_shape[-2], u_shape[-1]))
+    v = torch.reshape(v, (-1, v_shape[-2], v_shape[-1]))
+
+    out = u @ v.permute([0, 2, 1])
+
+    out = torch.reshape(out, u_shape[:-1] + (v_shape[-2], ))
+
+    return out
+
+
+def ltangent_distance(x, y, omegas):
+    r"""Localized Tangent distance.
+    Compute Orthogonal Complement: math:`\bm P_k = \bm I - \Omega_k \Omega_k^T`
+    Compute Tangent Distance: math:`{\| \bm P \bm x - \bm P_k \bm y_k \|}_2`
+
+    :param `torch.tensor` omegas: Three dimensional matrix
+    :rtype: `torch.tensor`
+    """
+    x, y = (arr.view(arr.size(0), -1) for arr in (x, y))
+    p = torch.eye(omegas.shape[-2], device=omegas.device) - torch.bmm(
+        omegas, omegas.permute([0, 2, 1]))
+    projected_x = x @ p
+    projected_y = torch.diagonal(y @ p).T
+    expanded_y = torch.unsqueeze(projected_y, dim=1)
+    batchwise_difference = expanded_y - projected_x
+    differences_squared = batchwise_difference**2
+    distances = torch.sqrt(torch.sum(differences_squared, dim=2))
+    distances = distances.permute(1, 0)
+    return distances
+
+
+class GaussianPrior(torch.nn.Module):
+
+    def __init__(self, variance):
+        super().__init__()
+        self.variance = variance
+
+    def forward(self, distances):
+        return gaussian(distances, self.variance)
+
+
+class RankScaledGaussianPrior(torch.nn.Module):
+
+    def __init__(self, lambd):
+        super().__init__()
+        self.lambd = lambd
+
+    def forward(self, distances):
+        return rank_scaled_gaussian(distances, self.lambd)
+
+
+class ConnectionTopology(torch.nn.Module):
+
+    def __init__(self, agelimit, num_prototypes):
+        super().__init__()
+        self.agelimit = agelimit
+        self.num_prototypes = num_prototypes
+
+        self.cmat = torch.zeros((self.num_prototypes, self.num_prototypes))
+        self.age = torch.zeros_like(self.cmat)
+
+    def forward(self, d):
+        order = torch.argsort(d, dim=1)
+
+        for element in order:
+            i0, i1 = element[0], element[1]
+
+            self.cmat[i0][i1] = 1
+            self.cmat[i1][i0] = 1
+
+            self.age[i0][i1] = 0
+            self.age[i1][i0] = 0
+
+            self.age[i0][self.cmat[i0] == 1] += 1
+            self.age[i1][self.cmat[i1] == 1] += 1
+
+            self.cmat[i0][self.age[i0] > self.agelimit] = 0
+            self.cmat[i1][self.age[i1] > self.agelimit] = 0
+
+    def get_neighbors(self, position):
+        return torch.where(self.cmat[position])
+
+    def add_prototype(self):
+        new_cmat = torch.zeros([dim + 1 for dim in self.cmat.shape])
+        new_cmat[:-1, :-1] = self.cmat
+        self.cmat = new_cmat
+
+        new_age = torch.zeros([dim + 1 for dim in self.age.shape])
+        new_age[:-1, :-1] = self.age
+        self.age = new_age
+
+    def add_connection(self, a, b):
+        self.cmat[a][b] = 1
+        self.cmat[b][a] = 1
+
+        self.age[a][b] = 0
+        self.age[b][a] = 0
+
+    def remove_connection(self, a, b):
+        self.cmat[a][b] = 0
+        self.cmat[b][a] = 0
+
+        self.age[a][b] = 0
+        self.age[b][a] = 0
+
+    def extra_repr(self):
+        return f"(agelimit): ({self.agelimit})"

src/prototorch/models/glvq.py

@@ -1,44 +1,54 @@
 """Models based on the GLVQ framework."""
 
 import torch
-from prototorch.functions.activations import get_activation
-from prototorch.functions.competitions import wtac
-from prototorch.functions.distances import (lomega_distance, omega_distance,
-                                            squared_euclidean_distance)
-from prototorch.functions.helper import get_flat
-from prototorch.functions.losses import glvq_loss, lvq1_loss, lvq21_loss
-from prototorch.components import LinearMapping
-from prototorch.modules import LambdaLayer, LossLayer
+from prototorch.core.competitions import wtac
+from prototorch.core.distances import (
+    lomega_distance,
+    omega_distance,
+    squared_euclidean_distance,
+)
+from prototorch.core.initializers import EyeLinearTransformInitializer
+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 ImagePrototypesMixin, SupervisedPrototypeModel
+from .extras import ltangent_distance, orthogonalization
 
 
 class GLVQ(SupervisedPrototypeModel):
     """Generalized Learning Vector Quantization."""
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
         # Default hparams
+        self.hparams.setdefault("margin", 0.0)
         self.hparams.setdefault("transfer_fn", "identity")
         self.hparams.setdefault("transfer_beta", 10.0)
 
-        # Layers
-        transfer_fn = get_activation(self.hparams.transfer_fn)
-        self.transfer_layer = LambdaLayer(transfer_fn)
-
         # Loss
-        self.loss = LossLayer(glvq_loss)
+        self.loss = GLVQLoss(
+            margin=self.hparams["margin"],
+            transfer_fn=self.hparams["transfer_fn"],
+            beta=self.hparams["transfer_beta"],
+        )
 
-        # Prototype metrics
-        self.initialize_prototype_win_ratios()
+    # def on_save_checkpoint(self, checkpoint):
+    #     if "prototype_win_ratios" in checkpoint["state_dict"]:
+    #         del checkpoint["state_dict"]["prototype_win_ratios"]
 
     def initialize_prototype_win_ratios(self):
         self.register_buffer(
             "prototype_win_ratios",
             torch.zeros(self.num_prototypes, device=self.device))
 
-    def on_epoch_start(self):
+    def on_train_epoch_start(self):
         self.initialize_prototype_win_ratios()
 
     def log_prototype_win_ratios(self, distances):
@@ -56,17 +66,15 @@ class GLVQ(SupervisedPrototypeModel):
             prototype_wr,
         ])
 
-    def shared_step(self, batch, batch_idx, optimizer_idx=None):
+    def shared_step(self, batch, batch_idx):
         x, y = batch
         out = self.compute_distances(x)
-        plabels = self.proto_layer.component_labels
-        mu = self.loss(out, y, prototype_labels=plabels)
-        batch_loss = self.transfer_layer(mu, beta=self.hparams.transfer_beta)
-        loss = batch_loss.sum(dim=0)
+        _, plabels = self.proto_layer()
+        loss = self.loss(out, y, plabels)
         return out, loss
 
-    def training_step(self, batch, batch_idx, optimizer_idx=None):
-        out, train_loss = self.shared_step(batch, batch_idx, optimizer_idx)
+    def training_step(self, batch, batch_idx):
+        out, train_loss = self.shared_step(batch, batch_idx)
         self.log_prototype_win_ratios(out)
         self.log("train_loss", train_loss)
         self.log_acc(out, batch[-1], tag="train_acc")
@@ -91,10 +99,6 @@ class GLVQ(SupervisedPrototypeModel):
             test_loss += batch_loss.item()
         self.log("test_loss", test_loss)
 
-    # TODO
-    # def predict_step(self, batch, batch_idx, dataloader_idx=None):
-    #     pass
-
 
 class SiameseGLVQ(GLVQ):
     """GLVQ in a Siamese setting.
@@ -104,6 +108,7 @@ class SiameseGLVQ(GLVQ):
     transformation pipeline are only learned from the inputs.
 
     """
+
     def __init__(self,
                  hparams,
                  backbone=torch.nn.Identity(),
@@ -114,32 +119,17 @@ class SiameseGLVQ(GLVQ):
         self.backbone = backbone
         self.both_path_gradients = both_path_gradients
 
-    def configure_optimizers(self):
-        proto_opt = self.optimizer(self.proto_layer.parameters(),
-                                   lr=self.hparams.proto_lr)
-        # Only add a backbone optimizer if backbone has trainable parameters
-        if (bb_params := list(self.backbone.parameters())):
-            bb_opt = self.optimizer(bb_params, lr=self.hparams.bb_lr)
-            optimizers = [proto_opt, bb_opt]
-        else:
-            optimizers = [proto_opt]
-        if self.lr_scheduler is not None:
-            schedulers = []
-            for optimizer in optimizers:
-                scheduler = self.lr_scheduler(optimizer,
-                                              **self.lr_scheduler_kwargs)
-                schedulers.append(scheduler)
-            return optimizers, schedulers
-        else:
-            return optimizers
-
     def compute_distances(self, x):
         protos, _ = self.proto_layer()
-        x, protos = get_flat(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)
+
+        bb_grad = any([el.requires_grad for el in self.backbone.parameters()])
+
+        self.backbone.requires_grad_(bb_grad and self.both_path_gradients)
         latent_protos = self.backbone(protos)
-        self.backbone.requires_grad_(True)
+        self.backbone.requires_grad_(bb_grad)
+
         distances = self.distance_layer(latent_x, latent_protos)
         return distances
 
@@ -169,6 +159,7 @@ class LVQMLN(SiameseGLVQ):
     rather in the embedding space.
 
     """
+
     def compute_distances(self, x):
         latent_protos, _ = self.proto_layer()
         latent_x = self.backbone(x)
@@ -184,17 +175,22 @@ class GRLVQ(SiameseGLVQ):
     TODO Make a RelevanceLayer. `bb_lr` is ignored otherwise.
 
     """
+    _relevances: torch.Tensor
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
         # Additional parameters
-        relevances = torch.ones(self.hparams.input_dim, device=self.device)
+        relevances = torch.ones(self.hparams["input_dim"], device=self.device)
         self.register_parameter("_relevances", Parameter(relevances))
 
         # Override the backbone
-        self.backbone = LambdaLayer(lambda x: x @ torch.diag(self._relevances),
+        self.backbone = LambdaLayer(self._apply_relevances,
                                     name="relevance scaling")
 
+    def _apply_relevances(self, x):
+        return x @ torch.diag(self._relevances)
+
     @property
     def relevance_profile(self):
         return self._relevances.detach().cpu()
@@ -209,22 +205,27 @@ class SiameseGMLVQ(SiameseGLVQ):
     Implemented as a Siamese network with a linear transformation backbone.
 
     """
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
         # Override the backbone
-        self.backbone = torch.nn.Linear(self.hparams.input_dim,
-                                        self.hparams.latent_dim,
-                                        bias=False)
+        omega_initializer = kwargs.get("omega_initializer",
+                                       EyeLinearTransformInitializer())
+        self.backbone = LinearTransform(
+            self.hparams["input_dim"],
+            self.hparams["latent_dim"],
+            initializer=omega_initializer,
+        )
 
     @property
     def omega_matrix(self):
-        return self.backbone.weight.detach().cpu()
+        return self.backbone.weights
 
     @property
     def lambda_matrix(self):
-        omega = self.backbone.weight  # (latent_dim, input_dim)
-        lam = omega.T @ omega
+        omega = self.backbone.weights  # (input_dim, latent_dim)
+        lam = omega @ omega.T
         return lam.detach().cpu()
 
 
@@ -235,27 +236,31 @@ class GMLVQ(GLVQ):
     function. This makes it easier to implement a localized variant.
 
     """
+
+    # Parameters
+    _omega: torch.Tensor
+
     def __init__(self, hparams, **kwargs):
         distance_fn = kwargs.pop("distance_fn", omega_distance)
         super().__init__(hparams, distance_fn=distance_fn, **kwargs)
 
         # Additional parameters
-        omega_initializer = kwargs.get("omega_initializer", None)
-        initialized_omega = kwargs.get("initialized_omega", None)
-        if omega_initializer is not None or initialized_omega is not None:
-            self.omega_layer = LinearMapping(
-                mapping_shape=(self.hparams.input_dim, self.hparams.latent_dim),
-                initializer=omega_initializer,
-                initialized_linearmapping=initialized_omega,
-            )
-
-        self.register_parameter("_omega", Parameter(self.omega_layer.mapping))
-        self.backbone = LambdaLayer(lambda x: x @ self._omega, name = "omega matrix")
+        omega_initializer = kwargs.get("omega_initializer",
+                                       EyeLinearTransformInitializer())
+        omega = omega_initializer.generate(self.hparams["input_dim"],
+                                           self.hparams["latent_dim"])
+        self.register_parameter("_omega", Parameter(omega))
 
     @property
     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)
@@ -264,27 +269,10 @@ class GMLVQ(GLVQ):
     def extra_repr(self):
         return f"(omega): (shape: {tuple(self._omega.shape)})"
 
-    def predict_latent(self, x, map_protos=True):
-        """Predict `x` assuming it is already embedded in the latent space.
-
-        Only the prototypes are embedded in the latent space using the
-        backbone.
- 
-        """
-        self.eval()
-        with torch.no_grad():
-            protos, plabels = self.proto_layer()
-            if map_protos:
-                protos = self.backbone(protos)
-            d = squared_euclidean_distance(x, protos)
-            y_pred = wtac(d, plabels)
-        return y_pred
-
-
-
 
 class LGMLVQ(GMLVQ):
     """Localized and Generalized Matrix Learning Vector Quantization."""
+
     def __init__(self, hparams, **kwargs):
         distance_fn = kwargs.pop("distance_fn", lomega_distance)
         super().__init__(hparams, distance_fn=distance_fn, **kwargs)
@@ -292,15 +280,59 @@ class LGMLVQ(GMLVQ):
         # Re-register `_omega` to override the one from the super class.
         omega = torch.randn(
             self.num_prototypes,
-            self.hparams.input_dim,
-            self.hparams.latent_dim,
+            self.hparams["input_dim"],
+            self.hparams["latent_dim"],
             device=self.device,
         )
         self.register_parameter("_omega", Parameter(omega))
 
 
+class GTLVQ(LGMLVQ):
+    """Localized and Generalized Tangent Learning Vector Quantization."""
+
+    def __init__(self, hparams, **kwargs):
+        distance_fn = kwargs.pop("distance_fn", ltangent_distance)
+        super().__init__(hparams, distance_fn=distance_fn, **kwargs)
+
+        omega_initializer = kwargs.get("omega_initializer")
+
+        if omega_initializer is not None:
+            subspace = omega_initializer.generate(
+                self.hparams["input_dim"],
+                self.hparams["latent_dim"],
+            )
+            omega = torch.repeat_interleave(
+                subspace.unsqueeze(0),
+                self.num_prototypes,
+                dim=0,
+            )
+        else:
+            omega = torch.rand(
+                self.num_prototypes,
+                self.hparams["input_dim"],
+                self.hparams["latent_dim"],
+                device=self.device,
+            )
+
+        # Re-register `_omega` to override the one from the super class.
+        self.register_parameter("_omega", Parameter(omega))
+
+    def on_train_batch_end(self, outputs, batch, batch_idx):
+        with torch.no_grad():
+            self._omega.copy_(orthogonalization(self._omega))
+
+
+class SiameseGTLVQ(SiameseGLVQ, GTLVQ):
+    """Generalized Tangent Learning Vector Quantization.
+
+    Implemented as a Siamese network with a linear transformation backbone.
+
+    """
+
+
 class GLVQ1(GLVQ):
     """Generalized Learning Vector Quantization 1."""
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
         self.loss = LossLayer(lvq1_loss)
@@ -309,6 +341,7 @@ class GLVQ1(GLVQ):
 
 class GLVQ21(GLVQ):
     """Generalized Learning Vector Quantization 2.1."""
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
         self.loss = LossLayer(lvq21_loss)
@@ -331,3 +364,18 @@ class ImageGMLVQ(ImagePrototypesMixin, GMLVQ):
     after updates.
 
     """
+
+
+class ImageGTLVQ(ImagePrototypesMixin, GTLVQ):
+    """GTLVQ for training on image data.
+
+    GTLVQ model that constrains the prototypes to the range [0, 1] by clamping
+    after updates.
+
+    """
+
+    def on_train_batch_end(self, outputs, batch, batch_idx):
+        """Constrain the components to the range [0, 1] by clamping after updates."""
+        self.proto_layer.components.data.clamp_(0.0, 1.0)
+        with torch.no_grad():
+            self._omega.copy_(orthogonalization(self._omega))

src/prototorch/models/knn.py

@@ -0,0 +1,45 @@
+"""ProtoTorch KNN model."""
+
+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 .abstract import SupervisedPrototypeModel
+
+
+class KNN(SupervisedPrototypeModel):
+    """K-Nearest-Neighbors classification algorithm."""
+
+    def __init__(self, hparams, **kwargs):
+        super().__init__(hparams, skip_proto_layer=True, **kwargs)
+
+        # Default hparams
+        self.hparams.setdefault("k", 1)
+
+        data = kwargs.get("data", None)
+        if data is None:
+            raise ValueError("KNN requires data, but was not provided!")
+        data, targets = parse_data_arg(data)
+
+        # Layers
+        self.proto_layer = LabeledComponents(
+            distribution=len(data) * [1],
+            components_initializer=LiteralCompInitializer(data),
+            labels_initializer=LiteralLabelsInitializer(targets))
+        self.competition_layer = KNNC(k=self.hparams.k)
+
+    def training_step(self, train_batch, batch_idx):
+        return 1  # skip training step
+
+    def on_train_batch_start(self, train_batch, batch_idx):
+        warnings.warn("k-NN has no training, skipping!")
+        return -1
+
+    def configure_optimizers(self):
+        return None

src/prototorch/models/lvq.py

@@ -0,0 +1,128 @@
+"""LVQ models that are optimized using non-gradient methods."""
+
+import logging
+
+from prototorch.core.losses import _get_dp_dm
+from prototorch.nn.activations import get_activation
+from prototorch.nn.wrappers import LambdaLayer
+
+from .abstract import NonGradientMixin
+from .glvq import GLVQ
+
+
+class LVQ1(NonGradientMixin, GLVQ):
+    """Learning Vector Quantization 1."""
+
+    def training_step(self, train_batch, batch_idx):
+        protos, plables = self.proto_layer()
+        x, y = train_batch
+        dis = self.compute_distances(x)
+        # TODO Vectorized implementation
+
+        for xi, yi in zip(x, y):
+            d = self.compute_distances(xi.view(1, -1))
+            preds = self.competition_layer(d, plabels)
+            w = d.argmin(1)
+            if yi == preds:
+                shift = xi - protos[w]
+            else:
+                shift = protos[w] - xi
+            updated_protos = protos + 0.0
+            updated_protos[w] = protos[w] + (self.hparams.lr * shift)
+            self.proto_layer.load_state_dict({"_components": updated_protos},
+                                             strict=False)
+
+        logging.debug(f"dis={dis}")
+        logging.debug(f"y={y}")
+        # Logging
+        self.log_acc(dis, y, tag="train_acc")
+
+        return None
+
+
+class LVQ21(NonGradientMixin, GLVQ):
+    """Learning Vector Quantization 2.1."""
+
+    def training_step(self, train_batch, batch_idx):
+        protos, plabels = self.proto_layer()
+
+        x, y = train_batch
+        dis = self.compute_distances(x)
+        # TODO Vectorized implementation
+
+        for xi, yi in zip(x, y):
+            xi = xi.view(1, -1)
+            yi = yi.view(1, )
+            d = self.compute_distances(xi)
+            (_, wp), (_, wn) = _get_dp_dm(d, yi, plabels, with_indices=True)
+            shiftp = xi - protos[wp]
+            shiftn = protos[wn] - xi
+            updated_protos = protos + 0.0
+            updated_protos[wp] = protos[wp] + (self.hparams.lr * shiftp)
+            updated_protos[wn] = protos[wn] + (self.hparams.lr * shiftn)
+            self.proto_layer.load_state_dict({"_components": updated_protos},
+                                             strict=False)
+
+        # Logging
+        self.log_acc(dis, y, tag="train_acc")
+
+        return None
+
+
+class MedianLVQ(NonGradientMixin, GLVQ):
+    """Median LVQ
+
+    # TODO Avoid computing distances over and over
+
+    """
+
+    def __init__(self, hparams, **kwargs):
+        super().__init__(hparams, **kwargs)
+
+        self.transfer_layer = LambdaLayer(
+            get_activation(self.hparams.transfer_fn))
+
+    def _f(self, x, y, protos, plabels):
+        d = self.distance_layer(x, protos)
+        dp, dm = _get_dp_dm(d, y, plabels)
+        mu = (dp - dm) / (dp + dm)
+        invmu = -1.0 * mu
+        f = self.transfer_layer(invmu, beta=self.hparams.transfer_beta) + 1.0
+        return f
+
+    def expectation(self, x, y, protos, plabels):
+        f = self._f(x, y, protos, plabels)
+        gamma = f / f.sum()
+        return gamma
+
+    def lower_bound(self, x, y, protos, plabels, gamma):
+        f = self._f(x, y, protos, plabels)
+        lower_bound = (gamma * f.log()).sum()
+        return lower_bound
+
+    def training_step(self, train_batch, batch_idx):
+        protos, plabels = self.proto_layer()
+
+        x, y = train_batch
+        dis = self.compute_distances(x)
+
+        for i, _ in enumerate(protos):
+            # Expectation step
+            gamma = self.expectation(x, y, protos, plabels)
+            lower_bound = self.lower_bound(x, y, protos, plabels, gamma)
+
+            # Maximization step
+            _protos = protos + 0
+            for k, xk in enumerate(x):
+                _protos[i] = xk
+                _lower_bound = self.lower_bound(x, y, _protos, plabels, gamma)
+                if _lower_bound > lower_bound:
+                    logging.debug(f"Updating prototype {i} to data {k}...")
+                    self.proto_layer.load_state_dict({"_components": _protos},
+                                                     strict=False)
+                    break
+
+        # Logging
+        self.log_acc(dis, y, tag="train_acc")
+
+        return None

src/prototorch/models/probabilistic.py

@@ -1,50 +1,60 @@
 """Probabilistic GLVQ methods"""
 
 import torch
-from prototorch.functions.losses import nllr_loss, rslvq_loss
-from prototorch.functions.pooling import (stratified_min_pooling,
-                                          stratified_sum_pooling)
-from prototorch.functions.transforms import (GaussianPrior,
-                                             RankScaledGaussianPrior)
-from prototorch.modules import LambdaLayer, LossLayer
+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 LossLayer
 
+from .extras import GaussianPrior, RankScaledGaussianPrior
 from .glvq import GLVQ, SiameseGMLVQ
 
 
 class CELVQ(GLVQ):
     """Cross-Entropy Learning Vector Quantization."""
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
         # Loss
         self.loss = torch.nn.CrossEntropyLoss()
 
-    def shared_step(self, batch, batch_idx, optimizer_idx=None):
+    def shared_step(self, batch, batch_idx):
         x, y = batch
         out = self.compute_distances(x)  # [None, num_protos]
-        plabels = self.proto_layer.component_labels
+        _, plabels = self.proto_layer()
         winning = stratified_min_pooling(out, plabels)  # [None, num_classes]
         probs = -1.0 * winning
         batch_loss = self.loss(probs, y.long())
-        loss = batch_loss.sum(dim=0)
+        loss = batch_loss.sum()
         return out, loss
 
 
 class ProbabilisticLVQ(GLVQ):
+
     def __init__(self, hparams, rejection_confidence=0.0, **kwargs):
         super().__init__(hparams, **kwargs)
 
-        self.conditional_distribution = None
         self.rejection_confidence = rejection_confidence
+        self._conditional_distribution = None
 
     def forward(self, x):
         distances = self.compute_distances(x)
+
         conditional = self.conditional_distribution(distances)
         prior = (1. / self.num_prototypes) * torch.ones(self.num_prototypes,
                                                         device=self.device)
         posterior = conditional * prior
+
         plabels = self.proto_layer._labels
-        y_pred = stratified_sum_pooling(posterior, plabels)
+        if isinstance(plabels, torch.LongTensor) or isinstance(
+                plabels, torch.cuda.LongTensor):  # type: ignore
+            y_pred = stratified_sum_pooling(posterior, plabels)  # type: ignore
+        else:
+            raise ValueError("Labels must be LongTensor.")
+
         return y_pred
 
     def predict(self, x):
@@ -53,29 +63,47 @@ class ProbabilisticLVQ(GLVQ):
         prediction[confidence < self.rejection_confidence] = -1
         return prediction
 
-    def training_step(self, batch, batch_idx, optimizer_idx=None):
+    def training_step(self, batch, batch_idx):
         x, y = batch
         out = self.forward(x)
-        plabels = self.proto_layer.component_labels
+        _, plabels = self.proto_layer()
         batch_loss = self.loss(out, y, plabels)
-        loss = batch_loss.sum(dim=0)
+        loss = batch_loss.sum()
         return loss
 
+    def conditional_distribution(self, distances):
+        """Conditional distribution of distances."""
+        if self._conditional_distribution is None:
+            raise ValueError("Conditional distribution is not set.")
+        return self._conditional_distribution(distances)
+
 
 class SLVQ(ProbabilisticLVQ):
     """Soft Learning Vector Quantization."""
+
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
+
+        # Default hparams
+        self.hparams.setdefault("variance", 1.0)
+        variance = self.hparams.get("variance")
+
+        self._conditional_distribution = GaussianPrior(variance)
         self.loss = LossLayer(nllr_loss)
-        self.conditional_distribution = GaussianPrior(self.hparams.variance)
 
 
 class RSLVQ(ProbabilisticLVQ):
     """Robust Soft Learning Vector Quantization."""
+
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
+
+        # Default hparams
+        self.hparams.setdefault("variance", 1.0)
+        variance = self.hparams.get("variance")
+
+        self._conditional_distribution = GaussianPrior(variance)
         self.loss = LossLayer(rslvq_loss)
-        self.conditional_distribution = GaussianPrior(self.hparams.variance)
 
 
 class PLVQ(ProbabilisticLVQ, SiameseGMLVQ):
@@ -83,17 +111,21 @@ class PLVQ(ProbabilisticLVQ, SiameseGMLVQ):
 
     TODO: Use Backbone LVQ instead
     """
+
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
-        self.conditional_distribution = RankScaledGaussianPrior(
-            self.hparams.lambd)
+
+        # Default hparams
+        self.hparams.setdefault("lambda", 1.0)
+        lam = self.hparams.get("lambda", 1.0)
+
+        self.conditional_distribution = RankScaledGaussianPrior(lam)
         self.loss = torch.nn.KLDivLoss()
 
-    def training_step(self, batch, batch_idx, optimizer_idx=None):
-        x, y = batch
-        out = self.forward(x)
-        y_dist = torch.nn.functional.one_hot(
-            y.long(), num_classes=self.num_classes).float()
-        batch_loss = self.loss(out, y_dist)
-        loss = batch_loss.sum(dim=0)
-        return loss
+    # FIXME
+    # def training_step(self, batch, batch_idx):
+    #     x, y = batch
+    #     y_pred = self(x)
+    #     batch_loss = self.loss(y_pred, y)
+    #     loss = batch_loss.sum()
+    #     return loss

src/prototorch/models/unsupervised.py

@@ -2,10 +2,9 @@
 
 import numpy as np
 import torch
-from prototorch.functions.competitions import wtac
-from prototorch.functions.distances import squared_euclidean_distance
-from prototorch.modules import LambdaLayer
-from prototorch.modules.losses import NeuralGasEnergy
+from prototorch.core.competitions import wtac
+from prototorch.core.distances import squared_euclidean_distance
+from prototorch.core.losses import NeuralGasEnergy
 
 from .abstract import NonGradientMixin, UnsupervisedPrototypeModel
 from .callbacks import GNGCallback
@@ -18,6 +17,8 @@ class KohonenSOM(NonGradientMixin, UnsupervisedPrototypeModel):
     TODO Allow non-2D grids
 
     """
+    _grid: torch.Tensor
+
     def __init__(self, hparams, **kwargs):
         h, w = hparams.get("shape")
         # Ignore `num_prototypes`
@@ -34,7 +35,7 @@ class KohonenSOM(NonGradientMixin, UnsupervisedPrototypeModel):
 
         # Additional parameters
         x, y = torch.arange(h), torch.arange(w)
-        grid = torch.stack(torch.meshgrid(x, y), dim=-1)
+        grid = torch.stack(torch.meshgrid(x, y, indexing="ij"), dim=-1)
         self.register_buffer("_grid", grid)
         self._sigma = self.hparams.sigma
         self._lr = self.hparams.lr
@@ -53,14 +54,16 @@ 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.components
+        protos = self.proto_layer()
         diff = x.unsqueeze(dim=1) - protos
         delta = self._lr * self.hparams.alpha * nh.unsqueeze(-1) * diff
         updated_protos = protos + delta.sum(dim=0)
-        self.proto_layer.load_state_dict({"_components": updated_protos},
-                                         strict=False)
+        self.proto_layer.load_state_dict(
+            {"_components": updated_protos},
+            strict=False,
+        )
 
-    def training_epoch_end(self, training_step_outputs):
+    def on_training_epoch_end(self, training_step_outputs):
         self._sigma = self.hparams.sigma * np.exp(
             -self.current_epoch / self.trainer.max_epochs)
 
@@ -69,6 +72,7 @@ class KohonenSOM(NonGradientMixin, UnsupervisedPrototypeModel):
 
 
 class HeskesSOM(UnsupervisedPrototypeModel):
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -78,6 +82,7 @@ class HeskesSOM(UnsupervisedPrototypeModel):
 
 
 class NeuralGas(UnsupervisedPrototypeModel):
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -85,13 +90,13 @@ class NeuralGas(UnsupervisedPrototypeModel):
         self.save_hyperparameters(hparams)
 
         # Default hparams
-        self.hparams.setdefault("agelimit", 10)
+        self.hparams.setdefault("age_limit", 10)
         self.hparams.setdefault("lm", 1)
 
-        self.energy_layer = NeuralGasEnergy(lm=self.hparams.lm)
+        self.energy_layer = NeuralGasEnergy(lm=self.hparams["lm"])
         self.topology_layer = ConnectionTopology(
-            agelimit=self.hparams.agelimit,
-            num_prototypes=self.hparams.num_prototypes,
+            agelimit=self.hparams["age_limit"],
+            num_prototypes=self.hparams["num_prototypes"],
         )
 
     def training_step(self, train_batch, batch_idx):
@@ -104,12 +109,10 @@ class NeuralGas(UnsupervisedPrototypeModel):
         self.log("loss", loss)
         return loss
 
-    # def training_epoch_end(self, training_step_outputs):
-    #     print(f"{self.trainer.lr_schedulers}")
-    #     print(f"{self.trainer.lr_schedulers[0]['scheduler'].optimizer}")
-
 
 class GrowingNeuralGas(NeuralGas):
+    errors: torch.Tensor
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -118,7 +121,10 @@ class GrowingNeuralGas(NeuralGas):
         self.hparams.setdefault("insert_reduction", 0.1)
         self.hparams.setdefault("insert_freq", 10)
 
-        errors = torch.zeros(self.hparams.num_prototypes, device=self.device)
+        errors = torch.zeros(
+            self.hparams["num_prototypes"],
+            device=self.device,
+        )
         self.register_buffer("errors", errors)
 
     def training_step(self, train_batch, _batch_idx):
@@ -132,8 +138,8 @@ class GrowingNeuralGas(NeuralGas):
         mask[torch.arange(len(mask)), winner] = 1.0
         dp = d * mask
 
-        self.errors += torch.sum(dp * dp, dim=0)
-        self.errors *= self.hparams.step_reduction
+        self.errors += torch.sum(dp * dp)
+        self.errors *= self.hparams["step_reduction"]
 
         self.topology_layer(d)
         self.log("loss", loss)
@@ -141,6 +147,8 @@ class GrowingNeuralGas(NeuralGas):
 
     def configure_callbacks(self):
         return [
-            GNGCallback(reduction=self.hparams.insert_reduction,
-                        freq=self.hparams.insert_freq)
+            GNGCallback(
+                reduction=self.hparams["insert_reduction"],
+                freq=self.hparams["insert_freq"],
+            )
         ]

src/prototorch/models/vis.py

@@ -1,18 +1,28 @@
 """Visualization Callbacks."""
 
+import warnings
+from typing import Sized
+
 import numpy as np
 import pytorch_lightning as pl
 import torch
 import torchvision
 from matplotlib import pyplot as plt
+from prototorch.utils.colors import get_colors, get_legend_handles
+from prototorch.utils.utils import mesh2d
+from pytorch_lightning.loggers import TensorBoardLogger
 from torch.utils.data import DataLoader, Dataset
 
 
 class Vis2DAbstract(pl.Callback):
+
     def __init__(self,
-                 data,
+                 data=None,
                  title="Prototype Visualization",
                  cmap="viridis",
+                 xlabel="Data dimension 1",
+                 ylabel="Data dimension 2",
+                 legend_labels=None,
                  border=0.1,
                  resolution=100,
                  flatten_data=True,
@@ -25,9 +35,15 @@ class Vis2DAbstract(pl.Callback):
                  block=False):
         super().__init__()
 
+        if data:
             if isinstance(data, Dataset):
+                if isinstance(data, Sized):
                     x, y = next(iter(DataLoader(data, batch_size=len(data))))
-        elif isinstance(data, torch.utils.data.DataLoader):
+                else:
+                    # TODO: Add support for non-sized datasets
+                    raise NotImplementedError(
+                        "Data must be a dataset with a __len__ method.")
+            elif isinstance(data, DataLoader):
                 x = torch.tensor([])
                 y = torch.tensor([])
                 for x_b, y_b in data:
@@ -41,8 +57,14 @@ class Vis2DAbstract(pl.Callback):
 
             self.x_train = x
             self.y_train = y
+        else:
+            self.x_train = None
+            self.y_train = None
 
         self.title = title
+        self.xlabel = xlabel
+        self.ylabel = ylabel
+        self.legend_labels = legend_labels
         self.fig = plt.figure(self.title)
         self.cmap = cmap
         self.border = border
@@ -61,35 +83,17 @@ class Vis2DAbstract(pl.Callback):
                 return False
         return True
 
-    def setup_ax(self, xlabel=None, ylabel=None):
+    def setup_ax(self):
         ax = self.fig.gca()
         ax.cla()
         ax.set_title(self.title)
-        if xlabel:
-            ax.set_xlabel("Data dimension 1")
-        if ylabel:
-            ax.set_ylabel("Data dimension 2")
+        ax.set_xlabel(self.xlabel)
+        ax.set_ylabel(self.ylabel)
         if self.axis_off:
             ax.axis("off")
         return ax
 
-    def get_mesh_input(self, x):
-        x_shift = self.border * np.ptp(x[:, 0])
-        y_shift = self.border * np.ptp(x[:, 1])
-        x_min, x_max = x[:, 0].min() - x_shift, x[:, 0].max() + x_shift
-        y_min, y_max = x[:, 1].min() - y_shift, x[:, 1].max() + y_shift
-        xx, yy = np.meshgrid(np.linspace(x_min, x_max, self.resolution),
-                             np.linspace(y_min, y_max, self.resolution))
-        mesh_input = np.c_[xx.ravel(), yy.ravel()]
-        return mesh_input, xx, yy
-
-    def perform_pca_2D(self, data):
-        (_, eigVal, eigVec) = torch.pca_lowrank(data, q=2)
-        return data @ eigVec
-
-    def plot_data(self, ax, x, y, pca=False):
-        if pca:
-            x = self.perform_pca_2D(x)
+    def plot_data(self, ax, x, y):
         ax.scatter(
             x[:, 0],
             x[:, 1],
@@ -100,9 +104,7 @@ class Vis2DAbstract(pl.Callback):
             s=30,
         )
 
-    def plot_protos(self, ax, protos, plabels, pca=False):
-        if pca:
-            protos = self.perform_pca_2D(protos)
+    def plot_protos(self, ax, protos, plabels):
         ax.scatter(
             protos[:, 0],
             protos[:, 1],
@@ -129,42 +131,47 @@ class Vis2DAbstract(pl.Callback):
             else:
                 plt.show(block=self.block)
 
+    def on_train_epoch_end(self, trainer, pl_module):
+        if not self.precheck(trainer):
+            return True
+        self.visualize(pl_module)
+        self.log_and_display(trainer, pl_module)
+
     def on_train_end(self, trainer, pl_module):
         plt.close()
 
+    def visualize(self, pl_module):
+        raise NotImplementedError
+
 
 class VisGLVQ2D(Vis2DAbstract):
-    def on_epoch_end(self, trainer, pl_module):
-        if not self.precheck(trainer):
-            return True
 
+    def visualize(self, pl_module):
         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)
+        ax = self.setup_ax()
         self.plot_protos(ax, protos, plabels)
-        x = np.vstack((x_train, protos))
-        mesh_input, xx, yy = self.get_mesh_input(x)
+        if x_train is not None:
+            self.plot_data(ax, x_train, y_train)
+            mesh_input, xx, yy = mesh2d(np.vstack([x_train, protos]),
+                                        self.border, self.resolution)
+        else:
+            mesh_input, xx, yy = mesh2d(protos, 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)
-
 
 class VisSiameseGLVQ2D(Vis2DAbstract):
+
     def __init__(self, *args, map_protos=True, **kwargs):
         super().__init__(*args, **kwargs)
         self.map_protos = map_protos
 
-    def on_epoch_end(self, trainer, pl_module):
-        if not self.precheck(trainer):
-            return True
-
+    def visualize(self, pl_module):
         protos = pl_module.prototypes
         plabels = pl_module.prototype_labels
         x_train, y_train = self.x_train, self.y_train
@@ -181,9 +188,9 @@ class VisSiameseGLVQ2D(Vis2DAbstract):
         if self.show_protos:
             self.plot_protos(ax, protos, plabels)
             x = np.vstack((x_train, protos))
-            mesh_input, xx, yy = self.get_mesh_input(x)
+            mesh_input, xx, yy = mesh2d(x, self.border, self.resolution)
         else:
-            mesh_input, xx, yy = self.get_mesh_input(x_train)
+            mesh_input, xx, yy = mesh2d(x_train, self.border, self.resolution)
         _components = pl_module.proto_layer._components
         mesh_input = torch.Tensor(mesh_input).type_as(_components)
         y_pred = pl_module.predict_latent(mesh_input,
@@ -191,87 +198,62 @@ class VisSiameseGLVQ2D(Vis2DAbstract):
         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 VisGMLVQ2D(Vis2DAbstract):
-    def __init__(self, *args, map_protos=True, **kwargs):
+
+    def __init__(self, *args, ev_proj=True, **kwargs):
         super().__init__(*args, **kwargs)
-        self.map_protos = map_protos
-
-    def on_epoch_end(self, trainer, pl_module):
-        if not self.precheck(trainer):
-            return True
+        self.ev_proj = ev_proj
 
+    def visualize(self, pl_module):
         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 = pl_module.backbone(torch.Tensor(x_train).to(device))
+            x_train = torch.Tensor(x_train).to(device)
+            x_train = x_train @ u
             x_train = x_train.cpu().detach()
-        if self.map_protos:
+        if self.show_protos:
             with torch.no_grad():
-                protos = pl_module.backbone(torch.Tensor(protos).to(device))
+                protos = torch.Tensor(protos).to(device)
+                protos = protos @ u
                 protos = protos.cpu().detach()
         ax = self.setup_ax()
-        if x_train.shape[1] > 2:
-            self.plot_data(ax, x_train, y_train, pca=True)
-        else:
-            self.plot_data(ax, x_train, y_train, pca=False)
+        self.plot_data(ax, x_train, y_train)
         if self.show_protos:
-            if protos.shape[1] > 2:
-                self.plot_protos(ax, protos, plabels, pca=True)
-            else:
-                self.plot_protos(ax, protos, plabels, pca=False)
-        ### something to work on: meshgrid with pca
-        #    x = np.vstack((x_train, protos))
-        #    mesh_input, xx, yy = self.get_mesh_input(x)
-        #else:
-        #    mesh_input, xx, yy = self.get_mesh_input(x_train)
-        #_components = pl_module.proto_layer._components
-        #mesh_input = torch.Tensor(mesh_input).type_as(_components)
-        #y_pred = pl_module.predict_latent(mesh_input,
-        #                                  map_protos=self.map_protos)
-        #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)
+            self.plot_protos(ax, protos, plabels)
 
 
 class VisCBC2D(Vis2DAbstract):
-    def on_epoch_end(self, trainer, pl_module):
-        if not self.precheck(trainer):
-            return True
 
+    def visualize(self, pl_module):
         x_train, y_train = self.x_train, self.y_train
         protos = pl_module.components
-        ax = self.setup_ax(xlabel="Data dimension 1",
-                           ylabel="Data dimension 2")
+        ax = self.setup_ax()
         self.plot_data(ax, x_train, y_train)
         self.plot_protos(ax, protos, "w")
         x = np.vstack((x_train, protos))
-        mesh_input, xx, yy = self.get_mesh_input(x)
-        _components = pl_module.component_layer._components
+        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.precheck(trainer):
-            return True
 
+    def visualize(self, pl_module):
         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(xlabel="Data dimension 1",
-                           ylabel="Data dimension 2")
+        ax = self.setup_ax()
         self.plot_data(ax, x_train, y_train)
         self.plot_protos(ax, protos, "w")
 
@@ -285,10 +267,27 @@ class VisNG2D(Vis2DAbstract):
                         "k-",
                     )
 
-        self.log_and_display(trainer, pl_module)
+
+class VisSpectralProtos(Vis2DAbstract):
+
+    def visualize(self, pl_module):
+        protos = pl_module.prototypes
+        plabels = pl_module.prototype_labels
+        ax = self.setup_ax()
+        colors = get_colors(vmax=max(plabels), vmin=min(plabels))
+        for p, pl in zip(protos, plabels):
+            ax.plot(p, c=colors[int(pl)])
+        if self.legend_labels:
+            handles = get_legend_handles(
+                colors,
+                self.legend_labels,
+                marker="lines",
+            )
+            ax.legend(handles=handles)
 
 
 class VisImgComp(Vis2DAbstract):
+
     def __init__(self,
                  *args,
                  random_data=0,
@@ -304,32 +303,45 @@ class VisImgComp(Vis2DAbstract):
         self.add_embedding = add_embedding
         self.embedding_data = embedding_data
 
-    def on_train_start(self, trainer, pl_module):
+    def on_train_start(self, _, pl_module):
+        if isinstance(pl_module.logger, TensorBoardLogger):
             tb = pl_module.logger.experiment
+
+            # Add embedding
             if self.add_embedding:
+                if self.x_train is not None and self.y_train is not None:
                     ind = np.random.choice(len(self.x_train),
                                            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,
                                      tag="Data Embedding",
                                      metadata=self.y_train[ind],
                                      metadata_header=None)
+                else:
+                    raise ValueError("No data for add embedding flag")
 
+            # Random Data
             if self.random_data:
+                if self.x_train is not None:
                     ind = np.random.choice(len(self.x_train),
                                            size=self.random_data,
                                            replace=False)
                     data = self.x_train[ind]
-            grid = torchvision.utils.make_grid(data, nrow=self.num_columns)
+                    grid = torchvision.utils.make_grid(data,
+                                                       nrow=self.num_columns)
                     tb.add_image(tag="Data",
                                  img_tensor=grid,
                                  global_step=None,
                                  dataformats=self.dataformats)
+                else:
+                    raise ValueError("No data for random data flag")
+
+        else:
+            warnings.warn(
+                f"TensorBoardLogger is required, got {type(pl_module.logger)}")
 
     def add_to_tensorboard(self, trainer, pl_module):
         tb = pl_module.logger.experiment
@@ -343,14 +355,9 @@ class VisImgComp(Vis2DAbstract):
             dataformats=self.dataformats,
         )
 
-    def on_epoch_end(self, trainer, pl_module):
-        if not self.precheck(trainer):
-            return True
-
+    def visualize(self, pl_module):
         if self.show:
             components = pl_module.components
             grid = torchvision.utils.make_grid(components,
                                                nrow=self.num_columns)
             plt.imshow(grid.permute((1, 2, 0)).cpu(), cmap=self.cmap)
-
-        self.log_and_display(trainer, pl_module)

tests/test_.py

@@ -1,14 +0,0 @@
-"""prototorch.models test suite."""
-
-import unittest
-
-
-class TestDummy(unittest.TestCase):
-    def setUp(self):
-        pass
-
-    def test_dummy(self):
-        pass
-
-    def tearDown(self):
-        pass

tests/test_examples.sh

@@ -1,17 +1,35 @@
 #! /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 $1 -maxdepth 1 -name "*.py")
+for example in $(find $path -maxdepth 1 -name "*.py")
 do
     echo  -n "$x" $example '... '
-    export DISPLAY= && python $example --fast_dev_run 1 &> /dev/null
+    export DISPLAY= && python $example --fast_dev_run 1 --gpus $gpu &> run_log.txt
     if [[ $? -ne 0 ]]; then
         echo "FAILED!!"
+        cat run_log.txt
         failed=1
     else
         echo "SUCCESS!"
     fi
+    rm run_log.txt
 done
 
 exit $failed

tests/test_models.py

@@ -0,0 +1,193 @@
+"""prototorch.models test suite."""
+
+import prototorch.models
+
+
+def test_glvq_model_build():
+    model = prototorch.models.GLVQ(
+        {"distribution": (3, 2)},
+        prototypes_initializer=prototorch.initializers.RNCI(2),
+    )
+
+
+def test_glvq1_model_build():
+    model = prototorch.models.GLVQ1(
+        {"distribution": (3, 2)},
+        prototypes_initializer=prototorch.initializers.RNCI(2),
+    )
+
+
+def test_glvq21_model_build():
+    model = prototorch.models.GLVQ1(
+        {"distribution": (3, 2)},
+        prototypes_initializer=prototorch.initializers.RNCI(2),
+    )
+
+
+def test_gmlvq_model_build():
+    model = prototorch.models.GMLVQ(
+        {
+            "distribution": (3, 2),
+            "input_dim": 2,
+            "latent_dim": 2,
+        },
+        prototypes_initializer=prototorch.initializers.RNCI(2),
+    )
+
+
+def test_grlvq_model_build():
+    model = prototorch.models.GRLVQ(
+        {
+            "distribution": (3, 2),
+            "input_dim": 2,
+        },
+        prototypes_initializer=prototorch.initializers.RNCI(2),
+    )
+
+
+def test_gtlvq_model_build():
+    model = prototorch.models.GTLVQ(
+        {
+            "distribution": (3, 2),
+            "input_dim": 4,
+            "latent_dim": 2,
+        },
+        prototypes_initializer=prototorch.initializers.RNCI(2),
+    )
+
+
+def test_lgmlvq_model_build():
+    model = prototorch.models.LGMLVQ(
+        {
+            "distribution": (3, 2),
+            "input_dim": 4,
+            "latent_dim": 2,
+        },
+        prototypes_initializer=prototorch.initializers.RNCI(2),
+    )
+
+
+def test_image_glvq_model_build():
+    model = prototorch.models.ImageGLVQ(
+        {"distribution": (3, 2)},
+        prototypes_initializer=prototorch.initializers.RNCI(16),
+    )
+
+
+def test_image_gmlvq_model_build():
+    model = prototorch.models.ImageGMLVQ(
+        {
+            "distribution": (3, 2),
+            "input_dim": 16,
+            "latent_dim": 2,
+        },
+        prototypes_initializer=prototorch.initializers.RNCI(16),
+    )
+
+
+def test_image_gtlvq_model_build():
+    model = prototorch.models.ImageGMLVQ(
+        {
+            "distribution": (3, 2),
+            "input_dim": 16,
+            "latent_dim": 2,
+        },
+        prototypes_initializer=prototorch.initializers.RNCI(16),
+    )
+
+
+def test_siamese_glvq_model_build():
+    model = prototorch.models.SiameseGLVQ(
+        {"distribution": (3, 2)},
+        prototypes_initializer=prototorch.initializers.RNCI(4),
+    )
+
+
+def test_siamese_gmlvq_model_build():
+    model = prototorch.models.SiameseGMLVQ(
+        {
+            "distribution": (3, 2),
+            "input_dim": 4,
+            "latent_dim": 2,
+        },
+        prototypes_initializer=prototorch.initializers.RNCI(4),
+    )
+
+
+def test_siamese_gtlvq_model_build():
+    model = prototorch.models.SiameseGTLVQ(
+        {
+            "distribution": (3, 2),
+            "input_dim": 4,
+            "latent_dim": 2,
+        },
+        prototypes_initializer=prototorch.initializers.RNCI(4),
+    )
+
+
+def test_knn_model_build():
+    train_ds = prototorch.datasets.Iris(dims=[0, 2])
+    model = prototorch.models.KNN(dict(k=3), data=train_ds)
+
+
+def test_lvq1_model_build():
+    model = prototorch.models.LVQ1(
+        {"distribution": (3, 2)},
+        prototypes_initializer=prototorch.initializers.RNCI(2),
+    )
+
+
+def test_lvq21_model_build():
+    model = prototorch.models.LVQ21(
+        {"distribution": (3, 2)},
+        prototypes_initializer=prototorch.initializers.RNCI(2),
+    )
+
+
+def test_median_lvq_model_build():
+    model = prototorch.models.MedianLVQ(
+        {"distribution": (3, 2)},
+        prototypes_initializer=prototorch.initializers.RNCI(2),
+    )
+
+
+def test_celvq_model_build():
+    model = prototorch.models.CELVQ(
+        {"distribution": (3, 2)},
+        prototypes_initializer=prototorch.initializers.RNCI(2),
+    )
+
+
+def test_rslvq_model_build():
+    model = prototorch.models.RSLVQ(
+        {"distribution": (3, 2)},
+        prototypes_initializer=prototorch.initializers.RNCI(2),
+    )
+
+
+def test_slvq_model_build():
+    model = prototorch.models.SLVQ(
+        {"distribution": (3, 2)},
+        prototypes_initializer=prototorch.initializers.RNCI(2),
+    )
+
+
+def test_growing_neural_gas_model_build():
+    model = prototorch.models.GrowingNeuralGas(
+        {"num_prototypes": 5},
+        prototypes_initializer=prototorch.initializers.RNCI(2),
+    )
+
+
+def test_kohonen_som_model_build():
+    model = prototorch.models.KohonenSOM(
+        {"shape": (3, 2)},
+        prototypes_initializer=prototorch.initializers.RNCI(2),
+    )
+
+
+def test_neural_gas_model_build():
+    model = prototorch.models.NeuralGas(
+        {"num_prototypes": 5},
+        prototypes_initializer=prototorch.initializers.RNCI(2),
+    )