masks -> ParameterList(requires_grad=False)

.bumpversion.cfg

@@ -1,13 +1,13 @@
 [bumpversion]
-current_version = 0.5.2
+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]

.github/workflows/examples.yml

@@ -6,20 +6,20 @@ name: examples
 on:
   push:
     paths:
-      - 'examples/**.py'
+      - "examples/**.py"
 jobs:
   cpu:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v2
-    - name: Set up Python 3.10
-      uses: actions/setup-python@v2
-      with:
-        python-version: "3.10"
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install .[all]
-    - name: Run examples
-      run: |
-        ./tests/test_examples.sh examples/
+      - 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

@@ -6,70 +6,70 @@ name: tests
 on:
   push:
   pull_request:
-    branches: [ master ]
+    branches: [master]
 
 jobs:
   style:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v2
-    - name: Set up Python 3.10
-      uses: actions/setup-python@v2
-      with:
-        python-version: "3.10"
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install .[all]
-    - uses: pre-commit/action@v2.0.3
+      - 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: ["3.7", "3.8", "3.9", "3.10"]
+        python-version: ["3.8", "3.9", "3.10", "3.11"]
         os: [ubuntu-latest, windows-latest]
         exclude:
-        - os: windows-latest
-          python-version: "3.7"
-        - os: windows-latest
-          python-version: "3.8"
-        - os: windows-latest
-          python-version: "3.9"
+          - 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@v2
-      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
+      - 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@v2
-    - name: Set up Python 3.10
-      uses: actions/setup-python@v2
-      with:
-        python-version: "3.10"
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install .[all]
-        pip install wheel
-    - name: Build package
-      run: python setup.py sdist bdist_wheel
-    - name: Publish a Python distribution to PyPI
-      uses: pypa/gh-action-pypi-publish@release/v1
-      with:
-        user: __token__
-        password: ${{ secrets.PYPI_API_TOKEN }}
+      - 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 }}

.pre-commit-config.yaml

@@ -2,52 +2,53 @@
 # See https://pre-commit.com/hooks.html for more hooks
 
 repos:
-- repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v4.2.0
-  hooks:
-  - id: trailing-whitespace
-  - id: end-of-file-fixer
-  - id: check-yaml
-  - id: check-added-large-files
-  - id: check-ast
-  - id: check-case-conflict
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.4.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-added-large-files
+      - id: check-ast
+      - id: check-case-conflict
 
-- repo: https://github.com/myint/autoflake
-  rev: v1.4
-  hooks:
-  - id: autoflake
+  - repo: https://github.com/myint/autoflake
+    rev: v2.1.1
+    hooks:
+      - id: autoflake
 
-- repo: http://github.com/PyCQA/isort
-  rev: 5.10.1
-  hooks:
-  - id: isort
+  - repo: http://github.com/PyCQA/isort
+    rev: 5.12.0
+    hooks:
+      - id: isort
 
-- repo: https://github.com/pre-commit/mirrors-mypy
-  rev: v0.950
-  hooks:
-  - id: mypy
-    files: prototorch
-    additional_dependencies: [types-pkg_resources]
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.3.0
+    hooks:
+      - id: mypy
+        files: prototorch
+        additional_dependencies: [types-pkg_resources]
 
-- repo: https://github.com/pre-commit/mirrors-yapf
-  rev: v0.32.0
-  hooks:
-  - id: yapf
+  - repo: https://github.com/pre-commit/mirrors-yapf
+    rev: v0.32.0
+    hooks:
+      - id: yapf
+        additional_dependencies: ["toml"]
 
-- repo: https://github.com/pre-commit/pygrep-hooks
-  rev: v1.9.0
-  hooks:
-  - id: python-use-type-annotations
-  - id: python-no-log-warn
-  - id: python-check-blanket-noqa
+  - repo: https://github.com/pre-commit/pygrep-hooks
+    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: v2.32.1
-  hooks:
-  - id: pyupgrade
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.7.0
+    hooks:
+      - id: pyupgrade
 
-- repo: https://github.com/si-cim/gitlint
-  rev: v0.15.2-unofficial
-  hooks:
-  - id: gitlint
-    args: [--contrib=CT1, --ignore=B6, --msg-filename]
+  - repo: https://github.com/si-cim/gitlint
+    rev: v0.15.2-unofficial
+    hooks:
+      - id: gitlint
+        args: [--contrib=CT1, --ignore=B6, --msg-filename]

docs/source/conf.py

@@ -23,7 +23,7 @@ author = "Jensun Ravichandran"
 
 # The full version, including alpha/beta/rc tags
 #
-release = "0.5.2"
+release = "0.7.1"
 
 # -- General configuration ---------------------------------------------------
 

examples/cbc_iris.py

@@ -1,12 +1,11 @@
 """CBC example using the Iris dataset."""
-
 import argparse
 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.seed import seed_everything
 from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from torch.utils.data import DataLoader
 
@@ -19,7 +18,8 @@ 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
@@ -53,8 +53,10 @@ 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,
         ],

examples/dynamic_pruning.py

@@ -7,13 +7,13 @@ 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.seed import seed_everything
 from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from torch.utils.data import DataLoader
 
@@ -26,7 +26,8 @@ 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
@@ -83,8 +84,10 @@ 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,

examples/glvq_iris.py

@@ -7,8 +7,8 @@ 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.seed import seed_everything
 from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from torch.optim.lr_scheduler import ExponentialLR
 from torch.utils.data import DataLoader
@@ -21,7 +21,8 @@ if __name__ == "__main__":
     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
@@ -55,8 +56,10 @@ if __name__ == "__main__":
     vis = VisGLVQ2D(data=train_ds)
 
     # 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,
         ],

examples/gmlvq_iris.py

@@ -6,8 +6,8 @@ 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.seed import seed_everything
 from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from torch.optim.lr_scheduler import ExponentialLR
 from torch.utils.data import DataLoader
@@ -22,7 +22,8 @@ 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
@@ -59,8 +60,10 @@ if __name__ == "__main__":
     vis = VisGMLVQ2D(data=train_ds)
 
     # 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,
         ],
@@ -71,3 +74,5 @@ if __name__ == "__main__":
 
     # Training loop
     trainer.fit(model, train_loader)
+
+    torch.save(model, "iris.pth")

examples/gmlvq_mnist.py

@@ -6,13 +6,13 @@ 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.seed import seed_everything
 from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from torch.utils.data import DataLoader
 from torchvision import transforms
@@ -26,7 +26,8 @@ if __name__ == "__main__":
     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
@@ -96,8 +97,10 @@ 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,

examples/gmlvq_spiral.py

@@ -6,13 +6,13 @@ 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.seed import seed_everything
 from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from torch.utils.data import DataLoader
 
@@ -25,7 +25,8 @@ 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
@@ -78,8 +79,10 @@ 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,

examples/gng_iris.py

@@ -7,8 +7,8 @@ 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.seed import seed_everything
 from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from torch.utils.data import DataLoader
 
@@ -18,7 +18,8 @@ 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
@@ -51,8 +52,10 @@ if __name__ == "__main__":
     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,
         ],

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

@@ -6,13 +6,13 @@ 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.seed import seed_everything
 from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from torch.utils.data import DataLoader
 from torchvision import transforms
@@ -27,7 +27,8 @@ 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
@@ -100,8 +101,10 @@ if __name__ == "__main__":
 
     # Setup trainer
     # using GPUs here is strongly recommended!
-    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,

examples/gtlvq_moons.py

@@ -7,9 +7,9 @@ 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.seed import seed_everything
 from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from torch.utils.data import DataLoader
 
@@ -19,7 +19,8 @@ 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
@@ -61,8 +62,10 @@ 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,

examples/knn_iris.py

@@ -18,7 +18,8 @@ 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
@@ -59,8 +60,10 @@ 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,
         max_epochs=1,
         callbacks=[
             vis,

examples/ksom_colors.py

@@ -7,10 +7,10 @@ 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.seed import seed_everything
 from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from torch.utils.data import DataLoader, TensorDataset
 
@@ -58,7 +58,8 @@ 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
@@ -104,8 +105,10 @@ if __name__ == "__main__":
     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,

examples/lgmlvq_moons.py

@@ -7,9 +7,9 @@ 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.seed import seed_everything
 from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from torch.utils.data import DataLoader
 
@@ -19,7 +19,8 @@ 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
@@ -62,8 +63,10 @@ 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,

examples/lvqmln_iris.py

@@ -6,12 +6,12 @@ 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.seed import seed_everything
 from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from torch.utils.data import DataLoader
 
@@ -39,7 +39,8 @@ 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
@@ -88,8 +89,10 @@ 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,

examples/median_lvq_iris.py

@@ -6,9 +6,9 @@ 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.seed import seed_everything
 from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from torch.utils.data import DataLoader
 
@@ -20,7 +20,8 @@ if __name__ == "__main__":
     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
@@ -53,8 +54,10 @@ 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,

examples/ng_iris.py

@@ -6,8 +6,8 @@ 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.seed import seed_everything
 from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from sklearn.datasets import load_iris
 from sklearn.preprocessing import StandardScaler
@@ -23,7 +23,8 @@ 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()
 
     # Prepare and pre-process the dataset
@@ -60,8 +61,10 @@ if __name__ == "__main__":
     vis = VisNG2D(data=train_ds)
 
     # 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,
         ],

examples/rslvq_iris.py

@@ -6,8 +6,8 @@ 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.seed import seed_everything
 from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from torch.utils.data import DataLoader
 
@@ -17,7 +17,8 @@ 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
@@ -54,8 +55,10 @@ if __name__ == "__main__":
     vis = VisGLVQ2D(data=train_ds)
 
     # 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,
         ],

examples/siamese_glvq_iris.py

@@ -6,8 +6,8 @@ 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.seed import seed_everything
 from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from torch.utils.data import DataLoader
 
@@ -35,7 +35,8 @@ 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
@@ -50,8 +51,7 @@ if __name__ == "__main__":
     # Hyperparameters
     hparams = dict(
         distribution=[1, 2, 3],
-        proto_lr=0.01,
-        bb_lr=0.01,
+        lr=0.01,
     )
 
     # Initialize the backbone
@@ -69,8 +69,10 @@ if __name__ == "__main__":
     vis = VisSiameseGLVQ2D(data=train_ds, border=0.1)
 
     # 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,
         ],

examples/siamese_gtlvq_iris.py

@@ -6,8 +6,8 @@ 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.seed import seed_everything
 from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from torch.utils.data import DataLoader
 
@@ -35,7 +35,8 @@ 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
@@ -50,8 +51,7 @@ if __name__ == "__main__":
     # Hyperparameters
     hparams = dict(
         distribution=[1, 2, 3],
-        proto_lr=0.01,
-        bb_lr=0.01,
+        lr=0.01,
         input_dim=2,
         latent_dim=1,
     )
@@ -71,8 +71,10 @@ if __name__ == "__main__":
     vis = VisSiameseGLVQ2D(data=train_ds, border=0.1)
 
     # 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,
         ],

examples/warm_starting.py

@@ -6,6 +6,7 @@ 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,
@@ -14,7 +15,6 @@ from prototorch.models import (
     VisGLVQ2D,
 )
 from pytorch_lightning.callbacks import EarlyStopping
-from pytorch_lightning.utilities.seed import seed_everything
 from pytorch_lightning.utilities.warnings import PossibleUserWarning
 from torch.optim.lr_scheduler import ExponentialLR
 from torch.utils.data import DataLoader
@@ -27,7 +27,8 @@ if __name__ == "__main__":
     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 the data
@@ -54,7 +55,9 @@ if __name__ == "__main__":
 
     # Setup trainer for GNG
     trainer = pl.Trainer(
-        max_epochs=1000,
+        accelerator="cpu",
+        max_epochs=50 if args.fast_dev_run else
+        1000,  # 10 epochs fast dev run reproducible DIV error.
         callbacks=[
             es,
         ],
@@ -108,8 +111,10 @@ 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,

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.cfg

@@ -1,23 +0,0 @@
-[yapf]
-based_on_style = pep8
-spaces_before_comment = 2
-split_before_logical_operator = true
-
-[pylint]
-disable =
-	too-many-arguments,
-	too-few-public-methods,
-	fixme,
-
-
-[pycodestyle]
-max-line-length = 79
-
-[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

setup.py

@@ -1,99 +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>=0.7.3",
-    "pytorch_lightning>=1.6.0",
-    "torchmetrics",
-    "protobuf<3.20.0",
-]
-CLI = [
-    "jsonargparse",
-]
-DEV = [
-    "bumpversion",
-    "pre-commit",
-]
-DOCS = [
-    "recommonmark",
-    "sphinx",
-    "nbsphinx",
-    "ipykernel",
-    "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="0.5.2",
-    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=">=3.7",
-    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",
-        "Programming Language :: Python :: 3.10",
-        "Programming Language :: Python :: 3.9",
-        "Programming Language :: Python :: 3.8",
-        "Programming Language :: Python :: 3.7",
-        "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

@@ -36,4 +36,4 @@ from .unsupervised import (
 )
 from .vis import *
 
-__version__ = "0.5.2"
+__version__ = "0.7.1"

src/prototorch/models/abstract.py

@@ -71,7 +71,7 @@ class PrototypeModel(ProtoTorchBolt):
         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):
@@ -186,26 +186,37 @@ 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,
-                 accuracy,
-                 on_step=False,
-                 on_epoch=True,
-                 prog_bar=True,
-                 logger=True)
+        self.log(
+            tag,
+            accuracy,
+            on_step=False,
+            on_epoch=True,
+            prog_bar=True,
+            logger=True,
+        )
 
     def test_step(self, batch, batch_idx):
         x, targets = batch
 
         preds = self.predict(x)
-        accuracy = torchmetrics.functional.accuracy(preds.int(), targets.int())
+        accuracy = torchmetrics.functional.accuracy(
+            preds.int(),
+            targets.int(),
+            "multiclass",
+            num_classes=self.num_classes,
+        )
 
         self.log("test_acc", accuracy)
 
 
-class ProtoTorchMixin(object):
+class ProtoTorchMixin:
     """All mixins are ProtoTorchMixins."""
 
 
@@ -216,7 +227,7 @@ class NonGradientMixin(ProtoTorchMixin):
         super().__init__(*args, **kwargs)
         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
 
 

src/prototorch/models/cbc.py

@@ -44,7 +44,7 @@ class CBC(SiameseGLVQ):
         probs = self.competition_layer(detections, reasonings)
         return probs
 
-    def shared_step(self, batch, batch_idx, optimizer_idx=None):
+    def shared_step(self, batch, batch_idx):
         x, y = batch
         y_pred = self(x)
         num_classes = self.num_classes
@@ -52,17 +52,23 @@ class CBC(SiameseGLVQ):
         loss = self.loss(y_pred, y_true).mean()
         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)
+    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())
-        self.log("train_acc",
-                 accuracy,
-                 on_step=False,
-                 on_epoch=True,
-                 prog_bar=True,
-                 logger=True)
+        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):

src/prototorch/models/extras.py

@@ -39,7 +39,7 @@ def ltangent_distance(x, y, omegas):
     :param `torch.tensor` omegas: Three dimensional matrix
     :rtype: `torch.tensor`
     """
-    x, y = [arr.view(arr.size(0), -1) for arr in (x, y)]
+    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

src/prototorch/models/glvq.py

@@ -1,13 +1,15 @@
 """Models based on the GLVQ framework."""
 
 import torch
+from numpy.typing import NDArray
 from prototorch.core.competitions import wtac
 from prototorch.core.distances import (
+    ML_omega_distance,
     lomega_distance,
     omega_distance,
     squared_euclidean_distance,
 )
-from prototorch.core.initializers import EyeLinearTransformInitializer
+from prototorch.core.initializers import LLTI, EyeLinearTransformInitializer
 from prototorch.core.losses import (
     GLVQLoss,
     lvq1_loss,
@@ -15,7 +17,7 @@ from prototorch.core.losses import (
 )
 from prototorch.core.transforms import LinearTransform
 from prototorch.nn.wrappers import LambdaLayer, LossLayer
-from torch.nn.parameter import Parameter
+from torch.nn import Parameter, ParameterList
 
 from .abstract import ImagePrototypesMixin, SupervisedPrototypeModel
 from .extras import ltangent_distance, orthogonalization
@@ -45,36 +47,38 @@ class GLVQ(SupervisedPrototypeModel):
 
     def initialize_prototype_win_ratios(self):
         self.register_buffer(
-            "prototype_win_ratios",
-            torch.zeros(self.num_prototypes, device=self.device))
+            "prototype_win_ratios", torch.zeros(self.num_prototypes, device=self.device)
+        )
 
     def on_train_epoch_start(self):
         self.initialize_prototype_win_ratios()
 
     def log_prototype_win_ratios(self, distances):
         batch_size = len(distances)
-        prototype_wc = torch.zeros(self.num_prototypes,
-                                   dtype=torch.long,
-                                   device=self.device)
-        wi, wc = torch.unique(distances.min(dim=-1).indices,
-                              sorted=True,
-                              return_counts=True)
+        prototype_wc = torch.zeros(
+            self.num_prototypes, dtype=torch.long, device=self.device
+        )
+        wi, wc = torch.unique(
+            distances.min(dim=-1).indices, sorted=True, return_counts=True
+        )
         prototype_wc[wi] = wc
         prototype_wr = prototype_wc / batch_size
-        self.prototype_win_ratios = torch.vstack([
-            self.prototype_win_ratios,
-            prototype_wr,
-        ])
+        self.prototype_win_ratios = torch.vstack(
+            [
+                self.prototype_win_ratios,
+                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()
         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")
@@ -99,10 +103,6 @@ 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.
@@ -113,39 +113,17 @@ class SiameseGLVQ(GLVQ):
 
     """
 
-    def __init__(self,
-                 hparams,
-                 backbone=torch.nn.Identity(),
-                 both_path_gradients=False,
-                 **kwargs):
+    def __init__(
+        self, hparams, backbone=torch.nn.Identity(), both_path_gradients=False, **kwargs
+    ):
         distance_fn = kwargs.pop("distance_fn", squared_euclidean_distance)
         super().__init__(hparams, distance_fn=distance_fn, **kwargs)
         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
-        bb_params = list(self.backbone.parameters())
-        if (bb_params):
-            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 = [arr.view(arr.size(0), -1) for arr in (x, protos)]
+        x, protos = (arr.view(arr.size(0), -1) for arr in (x, protos))
         latent_x = self.backbone(x)
 
         bb_grad = any([el.requires_grad for el in self.backbone.parameters()])
@@ -199,6 +177,7 @@ class GRLVQ(SiameseGLVQ):
     TODO Make a RelevanceLayer. `bb_lr` is ignored otherwise.
 
     """
+
     _relevances: torch.Tensor
 
     def __init__(self, hparams, **kwargs):
@@ -209,8 +188,10 @@ class GRLVQ(SiameseGLVQ):
         self.register_parameter("_relevances", Parameter(relevances))
 
         # Override the backbone
-        self.backbone = LambdaLayer(lambda x: x @ torch.diag(self._relevances),
-                                    name="relevance scaling")
+        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):
@@ -231,8 +212,9 @@ class SiameseGMLVQ(SiameseGLVQ):
         super().__init__(hparams, **kwargs)
 
         # Override the backbone
-        omega_initializer = kwargs.get("omega_initializer",
-                                       EyeLinearTransformInitializer())
+        omega_initializer = kwargs.get(
+            "omega_initializer", EyeLinearTransformInitializer()
+        )
         self.backbone = LinearTransform(
             self.hparams["input_dim"],
             self.hparams["latent_dim"],
@@ -250,6 +232,49 @@ class SiameseGMLVQ(SiameseGLVQ):
         return lam.detach().cpu()
 
 
+class GMLMLVQ(GLVQ):
+    """Generalized Multi-Layer Matrix Learning Vector Quantization.
+    Masks are applied to the omega layers to achieve sparsity and constrain
+    learning to certain items of each omega.
+
+    Implemented as a regular GLVQ network that simply uses a different distance
+    function. This makes it easier to implement a localized variant.
+    """
+
+    # Parameters
+    _omegas: list[torch.Tensor]
+    masks: list[torch.Tensor]
+
+    def __init__(self, hparams, **kwargs):
+        distance_fn = kwargs.pop("distance_fn", ML_omega_distance)
+        super().__init__(hparams, distance_fn=distance_fn, **kwargs)
+
+        # Additional parameters
+        self._masks = ParameterList(
+            [Parameter(mask, requires_grad=False) for mask in kwargs.get("masks")]
+        )
+        self._omegas = ParameterList([LLTI(mask).generate(1, 1) for mask in self._masks])
+
+    @property
+    def omega_matrices(self):
+        return [_omega.detach().cpu() for _omega in self._omegas]
+
+    @property
+    def lambda_matrix(self):
+        # TODO update to respective lambda calculation rules.
+        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._omegas, self._masks)
+        return distances
+
+    def extra_repr(self):
+        return f"(omegas): (shapes: {[tuple(_omega.shape) for _omega in self._omegas]})"
+
+
 class GMLVQ(GLVQ):
     """Generalized Matrix Learning Vector Quantization.
 
@@ -266,13 +291,13 @@ class GMLVQ(GLVQ):
         super().__init__(hparams, distance_fn=distance_fn, **kwargs)
 
         # Additional parameters
-        omega_initializer = kwargs.get("omega_initializer",
-                                       EyeLinearTransformInitializer())
-        omega = omega_initializer.generate(self.hparams["input_dim"],
-                                           self.hparams["latent_dim"])
+        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))
-        self.backbone = LambdaLayer(lambda x: x @ self._omega,
-                                    name="omega matrix")
 
     @property
     def omega_matrix(self):

src/prototorch/models/knn.py

@@ -34,7 +34,7 @@ class KNN(SupervisedPrototypeModel):
             labels_initializer=LiteralLabelsInitializer(targets))
         self.competition_layer = KNNC(k=self.hparams.k)
 
-    def training_step(self, train_batch, batch_idx, optimizer_idx=None):
+    def training_step(self, train_batch, batch_idx):
         return 1  # skip training step
 
     def on_train_batch_start(self, train_batch, batch_idx):

src/prototorch/models/lvq.py

@@ -13,7 +13,7 @@ from .glvq import GLVQ
 class LVQ1(NonGradientMixin, GLVQ):
     """Learning Vector Quantization 1."""
 
-    def training_step(self, train_batch, batch_idx, optimizer_idx=None):
+    def training_step(self, train_batch, batch_idx):
         protos, plables = self.proto_layer()
         x, y = train_batch
         dis = self.compute_distances(x)
@@ -43,7 +43,7 @@ class LVQ1(NonGradientMixin, GLVQ):
 class LVQ21(NonGradientMixin, GLVQ):
     """Learning Vector Quantization 2.1."""
 
-    def training_step(self, train_batch, batch_idx, optimizer_idx=None):
+    def training_step(self, train_batch, batch_idx):
         protos, plabels = self.proto_layer()
 
         x, y = train_batch
@@ -100,7 +100,7 @@ class MedianLVQ(NonGradientMixin, GLVQ):
         lower_bound = (gamma * f.log()).sum()
         return lower_bound
 
-    def training_step(self, train_batch, batch_idx, optimizer_idx=None):
+    def training_step(self, train_batch, batch_idx):
         protos, plabels = self.proto_layer()
 
         x, y = train_batch

src/prototorch/models/probabilistic.py

@@ -21,7 +21,7 @@ class CELVQ(GLVQ):
         # 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()
@@ -63,7 +63,7 @@ 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()
@@ -123,7 +123,7 @@ class PLVQ(ProbabilisticLVQ, SiameseGMLVQ):
         self.loss = torch.nn.KLDivLoss()
 
     # FIXME
-    # def training_step(self, batch, batch_idx, optimizer_idx=None):
+    # def training_step(self, batch, batch_idx):
     #     x, y = batch
     #     y_pred = self(x)
     #     batch_loss = self.loss(y_pred, y)

src/prototorch/models/unsupervised.py

@@ -63,7 +63,7 @@ class KohonenSOM(NonGradientMixin, UnsupervisedPrototypeModel):
             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)
 

tests/test_models.py

@@ -1,195 +1,193 @@
 """prototorch.models test suite."""
 
-import prototorch as pt
-import pytest
-import torch
+import prototorch.models
 
 
 def test_glvq_model_build():
-    model = pt.models.GLVQ(
+    model = prototorch.models.GLVQ(
         {"distribution": (3, 2)},
-        prototypes_initializer=pt.initializers.RNCI(2),
+        prototypes_initializer=prototorch.initializers.RNCI(2),
     )
 
 
 def test_glvq1_model_build():
-    model = pt.models.GLVQ1(
+    model = prototorch.models.GLVQ1(
         {"distribution": (3, 2)},
-        prototypes_initializer=pt.initializers.RNCI(2),
+        prototypes_initializer=prototorch.initializers.RNCI(2),
     )
 
 
 def test_glvq21_model_build():
-    model = pt.models.GLVQ1(
+    model = prototorch.models.GLVQ1(
         {"distribution": (3, 2)},
-        prototypes_initializer=pt.initializers.RNCI(2),
+        prototypes_initializer=prototorch.initializers.RNCI(2),
     )
 
 
 def test_gmlvq_model_build():
-    model = pt.models.GMLVQ(
+    model = prototorch.models.GMLVQ(
         {
             "distribution": (3, 2),
             "input_dim": 2,
             "latent_dim": 2,
         },
-        prototypes_initializer=pt.initializers.RNCI(2),
+        prototypes_initializer=prototorch.initializers.RNCI(2),
     )
 
 
 def test_grlvq_model_build():
-    model = pt.models.GRLVQ(
+    model = prototorch.models.GRLVQ(
         {
             "distribution": (3, 2),
             "input_dim": 2,
         },
-        prototypes_initializer=pt.initializers.RNCI(2),
+        prototypes_initializer=prototorch.initializers.RNCI(2),
     )
 
 
 def test_gtlvq_model_build():
-    model = pt.models.GTLVQ(
+    model = prototorch.models.GTLVQ(
         {
             "distribution": (3, 2),
             "input_dim": 4,
             "latent_dim": 2,
         },
-        prototypes_initializer=pt.initializers.RNCI(2),
+        prototypes_initializer=prototorch.initializers.RNCI(2),
     )
 
 
 def test_lgmlvq_model_build():
-    model = pt.models.LGMLVQ(
+    model = prototorch.models.LGMLVQ(
         {
             "distribution": (3, 2),
             "input_dim": 4,
             "latent_dim": 2,
         },
-        prototypes_initializer=pt.initializers.RNCI(2),
+        prototypes_initializer=prototorch.initializers.RNCI(2),
     )
 
 
 def test_image_glvq_model_build():
-    model = pt.models.ImageGLVQ(
+    model = prototorch.models.ImageGLVQ(
         {"distribution": (3, 2)},
-        prototypes_initializer=pt.initializers.RNCI(16),
+        prototypes_initializer=prototorch.initializers.RNCI(16),
     )
 
 
 def test_image_gmlvq_model_build():
-    model = pt.models.ImageGMLVQ(
+    model = prototorch.models.ImageGMLVQ(
         {
             "distribution": (3, 2),
             "input_dim": 16,
             "latent_dim": 2,
         },
-        prototypes_initializer=pt.initializers.RNCI(16),
+        prototypes_initializer=prototorch.initializers.RNCI(16),
     )
 
 
 def test_image_gtlvq_model_build():
-    model = pt.models.ImageGMLVQ(
+    model = prototorch.models.ImageGMLVQ(
         {
             "distribution": (3, 2),
             "input_dim": 16,
             "latent_dim": 2,
         },
-        prototypes_initializer=pt.initializers.RNCI(16),
+        prototypes_initializer=prototorch.initializers.RNCI(16),
     )
 
 
 def test_siamese_glvq_model_build():
-    model = pt.models.SiameseGLVQ(
+    model = prototorch.models.SiameseGLVQ(
         {"distribution": (3, 2)},
-        prototypes_initializer=pt.initializers.RNCI(4),
+        prototypes_initializer=prototorch.initializers.RNCI(4),
     )
 
 
 def test_siamese_gmlvq_model_build():
-    model = pt.models.SiameseGMLVQ(
+    model = prototorch.models.SiameseGMLVQ(
         {
             "distribution": (3, 2),
             "input_dim": 4,
             "latent_dim": 2,
         },
-        prototypes_initializer=pt.initializers.RNCI(4),
+        prototypes_initializer=prototorch.initializers.RNCI(4),
     )
 
 
 def test_siamese_gtlvq_model_build():
-    model = pt.models.SiameseGTLVQ(
+    model = prototorch.models.SiameseGTLVQ(
         {
             "distribution": (3, 2),
             "input_dim": 4,
             "latent_dim": 2,
         },
-        prototypes_initializer=pt.initializers.RNCI(4),
+        prototypes_initializer=prototorch.initializers.RNCI(4),
     )
 
 
 def test_knn_model_build():
-    train_ds = pt.datasets.Iris(dims=[0, 2])
-    model = pt.models.KNN(dict(k=3), data=train_ds)
+    train_ds = prototorch.datasets.Iris(dims=[0, 2])
+    model = prototorch.models.KNN(dict(k=3), data=train_ds)
 
 
 def test_lvq1_model_build():
-    model = pt.models.LVQ1(
+    model = prototorch.models.LVQ1(
         {"distribution": (3, 2)},
-        prototypes_initializer=pt.initializers.RNCI(2),
+        prototypes_initializer=prototorch.initializers.RNCI(2),
     )
 
 
 def test_lvq21_model_build():
-    model = pt.models.LVQ21(
+    model = prototorch.models.LVQ21(
         {"distribution": (3, 2)},
-        prototypes_initializer=pt.initializers.RNCI(2),
+        prototypes_initializer=prototorch.initializers.RNCI(2),
     )
 
 
 def test_median_lvq_model_build():
-    model = pt.models.MedianLVQ(
+    model = prototorch.models.MedianLVQ(
         {"distribution": (3, 2)},
-        prototypes_initializer=pt.initializers.RNCI(2),
+        prototypes_initializer=prototorch.initializers.RNCI(2),
     )
 
 
 def test_celvq_model_build():
-    model = pt.models.CELVQ(
+    model = prototorch.models.CELVQ(
         {"distribution": (3, 2)},
-        prototypes_initializer=pt.initializers.RNCI(2),
+        prototypes_initializer=prototorch.initializers.RNCI(2),
     )
 
 
 def test_rslvq_model_build():
-    model = pt.models.RSLVQ(
+    model = prototorch.models.RSLVQ(
         {"distribution": (3, 2)},
-        prototypes_initializer=pt.initializers.RNCI(2),
+        prototypes_initializer=prototorch.initializers.RNCI(2),
     )
 
 
 def test_slvq_model_build():
-    model = pt.models.SLVQ(
+    model = prototorch.models.SLVQ(
         {"distribution": (3, 2)},
-        prototypes_initializer=pt.initializers.RNCI(2),
+        prototypes_initializer=prototorch.initializers.RNCI(2),
     )
 
 
 def test_growing_neural_gas_model_build():
-    model = pt.models.GrowingNeuralGas(
+    model = prototorch.models.GrowingNeuralGas(
         {"num_prototypes": 5},
-        prototypes_initializer=pt.initializers.RNCI(2),
+        prototypes_initializer=prototorch.initializers.RNCI(2),
     )
 
 
 def test_kohonen_som_model_build():
-    model = pt.models.KohonenSOM(
+    model = prototorch.models.KohonenSOM(
         {"shape": (3, 2)},
-        prototypes_initializer=pt.initializers.RNCI(2),
+        prototypes_initializer=prototorch.initializers.RNCI(2),
     )
 
 
 def test_neural_gas_model_build():
-    model = pt.models.NeuralGas(
+    model = prototorch.models.NeuralGas(
         {"num_prototypes": 5},
-        prototypes_initializer=pt.initializers.RNCI(2),
+        prototypes_initializer=prototorch.initializers.RNCI(2),
     )