build: bump version 0.4.1 → 0.5.0

Necessary for different optimizer runs

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.2.0
+current_version = 0.5.0
 commit = True
 tag = True
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)

.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@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/

.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@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
+  compatibility:
+    needs: style
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.7", "3.8", "3.9", "3.10"]
+        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"
+
+    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
+  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 }}

.pre-commit-config.yaml

@@ -3,7 +3,7 @@
 
 repos:
 - repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v4.0.1
+  rev: v4.1.0
   hooks:
   - id: trailing-whitespace
   - id: end-of-file-fixer
@@ -18,19 +18,19 @@ repos:
   - id: autoflake
 
 - repo: http://github.com/PyCQA/isort
-  rev: 5.8.0
+  rev: 5.10.1
   hooks:
   - id: isort
 
 - repo: https://github.com/pre-commit/mirrors-mypy
-  rev: v0.902
+  rev: v0.931
   hooks:
   - id: mypy
     files: prototorch
     additional_dependencies: [types-pkg_resources]
 
 - repo: https://github.com/pre-commit/mirrors-yapf
-  rev: v0.31.0
+  rev: v0.32.0
   hooks:
   - id: yapf
 
@@ -42,7 +42,7 @@ repos:
   - id: python-check-blanket-noqa
 
 - repo: https://github.com/asottile/pyupgrade
-  rev: v2.19.4
+  rev: v2.31.0
   hooks:
   - id: pyupgrade
 

.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)
@@ -36,6 +35,7 @@ be available for use in your Python environment as `prototorch.models`.
 - Soft Learning Vector Quantization (SLVQ)
 - Robust Soft Learning Vector Quantization (RSLVQ)
 - Probabilistic Learning Vector Quantization (PLVQ)
+- Median-LVQ
 
 ### Other
 
@@ -51,7 +51,6 @@ be available for use in your Python environment as `prototorch.models`.
 
 ## Planned models
 
-- Median-LVQ
 - Generalized Tangent Learning Vector Quantization (GTLVQ)
 - Self-Incremental Learning Vector Quantization (SILVQ)
 

docs/source/conf.py

@@ -23,7 +23,7 @@ author = "Jensun Ravichandran"
 
 # The full version, including alpha/beta/rc tags
 #
-release = "0.2.0"
+release = "0.5.0"
 
 # -- General configuration ---------------------------------------------------
 

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/glvq_iris.py

@@ -53,3 +53,13 @@ if __name__ == "__main__":
 
     # Training loop
     trainer.fit(model, train_loader)
+
+    # Manual save
+    trainer.save_checkpoint("./glvq_iris.ckpt")
+
+    # Load saved model
+    new_model = pt.models.GLVQ.load_from_checkpoint(
+        checkpoint_path="./glvq_iris.ckpt",
+        strict=False,
+    )
+    print(new_model)

examples/gmlvq_iris.py

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

examples/gmlvq_spiral.py

@@ -1,4 +1,4 @@
-"""GLVQ example using the spiral dataset."""
+"""GMLVQ example using the spiral dataset."""
 
 import argparse
 
@@ -66,7 +66,7 @@ if __name__ == "__main__":
         args,
         callbacks=[
             vis,
-            # es, # FIXME
+            es,
             pruning,
         ],
         terminate_on_nan=True,

examples/gtlvq_mnist.py

@@ -0,0 +1,104 @@
+"""GTLVQ example using the MNIST dataset."""
+
+import argparse
+
+import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from torchvision import transforms
+from torchvision.datasets import MNIST
+
+if __name__ == "__main__":
+    # Command-line arguments
+    parser = argparse.ArgumentParser()
+    parser = pl.Trainer.add_argparse_args(parser)
+    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 = 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)
+
+    # 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 = pt.models.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 = pt.models.VisImgComp(
+        data=train_ds,
+        num_columns=10,
+        show=False,
+        tensorboard=True,
+        random_data=100,
+        add_embedding=True,
+        embedding_data=200,
+        flatten_data=False,
+    )
+    pruning = pt.models.PruneLoserPrototypes(
+        threshold=0.01,
+        idle_epochs=1,
+        prune_quota_per_epoch=10,
+        frequency=1,
+        verbose=True,
+    )
+    es = pl.callbacks.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.from_argparse_args(
+        args,
+        callbacks=[
+            vis,
+            pruning,
+            # es,
+        ],
+        terminate_on_nan=True,
+        weights_summary=None,
+        accelerator="ddp",
+    )
+
+    # Training loop
+    trainer.fit(model, train_loader)

examples/gtlvq_moons.py

@@ -0,0 +1,63 @@
+"""Localized-GTLVQ example using the Moons dataset."""
+
+import argparse
+
+import prototorch as pt
+import pytorch_lightning as pl
+import torch
+
+if __name__ == "__main__":
+    # Command-line arguments
+    parser = argparse.ArgumentParser()
+    parser = pl.Trainer.add_argparse_args(parser)
+    args = parser.parse_args()
+
+    # Reproducibility
+    pl.utilities.seed.seed_everything(seed=2)
+
+    # Dataset
+    train_ds = pt.datasets.Moons(num_samples=300, noise=0.2, seed=42)
+
+    # Dataloaders
+    train_loader = torch.utils.data.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 = pt.models.GTLVQ(
+        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)
+
+    # Callbacks
+    vis = pt.models.VisGLVQ2D(data=train_ds)
+    es = pl.callbacks.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.from_argparse_args(
+        args,
+        callbacks=[
+            vis,
+            es,
+        ],
+        weights_summary="full",
+        accelerator="ddp",
+    )
+
+    # Training loop
+    trainer.fit(model, train_loader)

examples/knn_iris.py

@@ -2,11 +2,11 @@
 
 import argparse
 
+import prototorch as pt
 import pytorch_lightning as pl
 import torch
 from sklearn.datasets import load_iris
-
+from sklearn.model_selection import train_test_split
-import prototorch as pt
 
 if __name__ == "__main__":
     # Command-line arguments
@@ -15,12 +15,20 @@ if __name__ == "__main__":
     args = parser.parse_args()
 
     # Dataset
-    x_train, y_train = load_iris(return_X_y=True)
+    X, y = load_iris(return_X_y=True)
-    x_train = x_train[:, [0, 2]]
+    X = X[:, [0, 2]]
-    train_ds = pt.datasets.NumpyDataset(x_train, y_train)
+
+    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 = torch.utils.data.DataLoader(train_ds, batch_size=16)
+    test_loader = torch.utils.data.DataLoader(test_ds, batch_size=16)
 
     # Hyperparameters
     hparams = dict(k=5)
@@ -36,7 +44,7 @@ if __name__ == "__main__":
 
     # Callbacks
     vis = pt.models.VisGLVQ2D(
-        data=(x_train, y_train),
+        data=(X_train, y_train),
         resolution=200,
         block=True,
     )
@@ -54,5 +62,8 @@ if __name__ == "__main__":
     trainer.fit(model, train_loader)
 
     # Recall
-    y_pred = model.predict(torch.tensor(x_train))
+    y_pred = model.predict(torch.tensor(X_train))
     print(y_pred)
+
+    # Test
+    trainer.test(model, dataloaders=test_loader)

examples/ksom_colors.py

@@ -10,6 +10,7 @@ from prototorch.utils.colors import hex_to_rgb
 
 
 class Vis2DColorSOM(pl.Callback):
+
     def __init__(self, data, title="ColorSOMe", pause_time=0.1):
         super().__init__()
         self.title = title

examples/lvqmln_iris.py

@@ -8,6 +8,7 @@ import torch
 
 
 class Backbone(torch.nn.Module):
+
     def __init__(self, input_size=4, hidden_size=10, latent_size=2):
         super().__init__()
         self.input_size = input_size

examples/median_lvq_iris.py

@@ -0,0 +1,52 @@
+"""Median-LVQ example using the Iris dataset."""
+
+import argparse
+
+import prototorch as pt
+import pytorch_lightning as pl
+import torch
+
+if __name__ == "__main__":
+    # Command-line arguments
+    parser = argparse.ArgumentParser()
+    parser = pl.Trainer.add_argparse_args(parser)
+    args = parser.parse_args()
+
+    # Dataset
+    train_ds = pt.datasets.Iris(dims=[0, 2])
+
+    # Dataloaders
+    train_loader = torch.utils.data.DataLoader(
+        train_ds,
+        batch_size=len(train_ds),  # MedianLVQ cannot handle mini-batches
+    )
+
+    # Initialize the model
+    model = pt.models.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 = pt.models.VisGLVQ2D(data=train_ds)
+    es = pl.callbacks.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.from_argparse_args(
+        args,
+        callbacks=[vis, es],
+        weights_summary="full",
+    )
+
+    # Training loop
+    trainer.fit(model, train_loader)

examples/siamese_glvq_iris.py

@@ -8,6 +8,7 @@ import torch
 
 
 class Backbone(torch.nn.Module):
+
     def __init__(self, input_size=4, hidden_size=10, latent_size=2):
         super().__init__()
         self.input_size = input_size

examples/siamese_gtlvq_iris.py

@@ -0,0 +1,73 @@
+"""Siamese GTLVQ example using all four dimensions of the Iris dataset."""
+
+import argparse
+
+import prototorch as pt
+import pytorch_lightning as pl
+import torch
+
+
+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 = pl.Trainer.add_argparse_args(parser)
+    args = parser.parse_args()
+
+    # Dataset
+    train_ds = pt.datasets.Iris()
+
+    # Reproducibility
+    pl.utilities.seed.seed_everything(seed=2)
+
+    # Dataloaders
+    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=150)
+
+    # Hyperparameters
+    hparams = dict(distribution=[1, 2, 3],
+                   proto_lr=0.01,
+                   bb_lr=0.01,
+                   input_dim=2,
+                   latent_dim=1)
+
+    # Initialize the backbone
+    backbone = Backbone(latent_size=hparams["input_dim"])
+
+    # Initialize the model
+    model = pt.models.SiameseGTLVQ(
+        hparams,
+        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)
+
+    # Setup trainer
+    trainer = pl.Trainer.from_argparse_args(
+        args,
+        callbacks=[vis],
+    )
+
+    # Training loop
+    trainer.fit(model, train_loader)

examples/warm_starting.py

@@ -37,7 +37,7 @@ if __name__ == "__main__":
 
     # Setup trainer for GNG
     trainer = pl.Trainer(
-        max_epochs=200,
+        max_epochs=100,
         callbacks=[es],
         weights_summary=None,
     )
@@ -71,11 +71,30 @@ if __name__ == "__main__":
 
     # Callbacks
     vis = pt.models.VisGLVQ2D(data=train_ds)
+    pruning = pt.models.PruneLoserPrototypes(
+        threshold=0.02,
+        idle_epochs=2,
+        prune_quota_per_epoch=5,
+        frequency=1,
+        verbose=True,
+    )
+    es = pl.callbacks.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.from_argparse_args(
         args,
-        callbacks=[vis],
+        callbacks=[
+            vis,
+            pruning,
+            es,
+        ],
         weights_summary="full",
         accelerator="ddp",
     )

prototorch/models/__init__.py

@@ -1,7 +1,5 @@
 """`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 (
@@ -10,17 +8,32 @@ from .glvq import (
     GLVQ21,
     GMLVQ,
     GRLVQ,
+    GTLVQ,
     LGMLVQ,
     LVQMLN,
     ImageGLVQ,
     ImageGMLVQ,
+    ImageGTLVQ,
     SiameseGLVQ,
     SiameseGMLVQ,
+    SiameseGTLVQ,
 )
 from .knn import KNN
-from .lvq import LVQ1, LVQ21, MedianLVQ
+from .lvq import (
-from .probabilistic import CELVQ, PLVQ, RSLVQ, SLVQ
+    LVQ1,
-from .unsupervised import GrowingNeuralGas, HeskesSOM, KohonenSOM, NeuralGas
+    LVQ21,
+    MedianLVQ,
+)
+from .probabilistic import (
+    CELVQ,
+    RSLVQ,
+    SLVQ,
+)
+from .unsupervised import (
+    GrowingNeuralGas,
+    KohonenSOM,
+    NeuralGas,
+)
 from .vis import *
 
-__version__ = "0.2.0"
+__version__ = "0.5.0"

prototorch/models/abstract.py

@@ -1,7 +1,5 @@
 """Abstract classes to be inherited by prototorch models."""
 
-from typing import Final, final
-
 import pytorch_lightning as pl
 import torch
 import torchmetrics
@@ -9,25 +7,14 @@ import torchmetrics
 from ..core.competitions import WTAC
 from ..core.components import Components, LabeledComponents
 from ..core.distances import euclidean_distance
-from ..core.initializers import LabelsInitializer
+from ..core.initializers import LabelsInitializer, ZerosCompInitializer
 from ..core.pooling import stratified_min_pooling
 from ..nn.wrappers import LambdaLayer
 
 
-class ProtoTorchMixin(object):
-    pass
-
-
 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__()
 
@@ -42,6 +29,34 @@ 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):
+        self.trainer.strategy.setup_optimizers(self.trainer)
+
+    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__(hparams, **kwargs)
+
         distance_fn = kwargs.get("distance_fn", euclidean_distance)
         self.distance_layer = LambdaLayer(distance_fn)
 
@@ -58,33 +73,19 @@ 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):
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -97,7 +98,7 @@ class UnsupervisedPrototypeModel(PrototypeModel):
             )
 
     def compute_distances(self, x):
-        protos = self.proto_layer()
+        protos = self.proto_layer().type_as(x)
         distances = self.distance_layer(x, protos)
         return distances
 
@@ -107,19 +108,33 @@ class UnsupervisedPrototypeModel(PrototypeModel):
 
 
 class SupervisedPrototypeModel(PrototypeModel):
-    def __init__(self, hparams, **kwargs):
+
+    def __init__(self, hparams, skip_proto_layer=False, **kwargs):
         super().__init__(hparams, **kwargs)
 
         # Layers
+        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,
+                    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
@@ -137,14 +152,14 @@ class SupervisedPrototypeModel(PrototypeModel):
 
     def forward(self, x):
         distances = self.compute_distances(x)
-        plabels = self.proto_layer.labels
+        _, plabels = self.proto_layer()
         winning = stratified_min_pooling(distances, plabels)
-        y_pred = torch.nn.functional.softmin(winning)
+        y_pred = torch.nn.functional.softmin(winning, dim=1)
         return y_pred
 
     def predict_from_distances(self, distances):
         with torch.no_grad():
-            plabels = self.proto_layer.labels
+            _, plabels = self.proto_layer()
             y_pred = self.competition_layer(distances, plabels)
         return y_pred
 
@@ -166,12 +181,25 @@ class SupervisedPrototypeModel(PrototypeModel):
                  prog_bar=True,
                  logger=True)
 
+    def test_step(self, batch, batch_idx):
+        x, targets = batch
+
+        preds = self.predict(x)
+        accuracy = torchmetrics.functional.accuracy(preds.int(), targets.int())
+
+        self.log("test_acc", accuracy)
+
+
+class ProtoTorchMixin(object):
+    """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):
         raise NotImplementedError
@@ -179,7 +207,7 @@ class NonGradientMixin(ProtoTorchMixin):
 
 class ImagePrototypesMixin(ProtoTorchMixin):
     """Mixin for models with image prototypes."""
-    @final
+
     def on_train_batch_end(self, outputs, batch, batch_idx, dataloader_idx):
         """Constrain the components to the range [0, 1] by clamping after updates."""
         self.proto_layer.components.data.clamp_(0.0, 1.0)

prototorch/models/callbacks.py

@@ -11,6 +11,7 @@ from .extras import ConnectionTopology
 
 
 class PruneLoserPrototypes(pl.Callback):
+
     def __init__(self,
                  threshold=0.01,
                  idle_epochs=10,
@@ -55,7 +56,7 @@ class PruneLoserPrototypes(pl.Callback):
                 distribution = dict(zip(labels.tolist(), counts.tolist()))
                 if self.verbose:
                     print(f"Re-adding pruned prototypes...")
-                    print(f"{distribution=}")
+                    print(f"distribution={distribution}")
                 pl_module.add_prototypes(
                     distribution=distribution,
                     components_initializer=self.prototypes_initializer)
@@ -67,6 +68,7 @@ class PruneLoserPrototypes(pl.Callback):
 
 
 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
@@ -89,6 +91,7 @@ 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
@@ -134,4 +137,4 @@ 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)

prototorch/models/cbc.py

@@ -13,8 +13,9 @@ from .glvq import SiameseGLVQ
 
 class CBC(SiameseGLVQ):
     """Classification-By-Components."""
+
     def __init__(self, hparams, **kwargs):
-        super().__init__(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)
@@ -48,7 +49,7 @@ class CBC(SiameseGLVQ):
         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(dim=0)
+        loss = self.loss(y_pred, y_true).mean()
         return y_pred, loss
 
     def training_step(self, batch, batch_idx, optimizer_idx=None):

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

@@ -15,7 +15,46 @@ def rank_scaled_gaussian(distances, lambd):
     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
@@ -25,6 +64,7 @@ class GaussianPrior(torch.nn.Module):
 
 
 class RankScaledGaussianPrior(torch.nn.Module):
+
     def __init__(self, lambd):
         super().__init__()
         self.lambd = lambd
@@ -34,6 +74,7 @@ class RankScaledGaussianPrior(torch.nn.Module):
 
 
 class ConnectionTopology(torch.nn.Module):
+
     def __init__(self, agelimit, num_prototypes):
         super().__init__()
         self.agelimit = agelimit

prototorch/models/glvq.py

@@ -4,29 +4,44 @@ import torch
 from torch.nn.parameter import Parameter
 
 from ..core.competitions import wtac
-from ..core.distances import lomega_distance, omega_distance, squared_euclidean_distance
+from ..core.distances import (
-from ..core.initializers import EyeTransformInitializer
+    lomega_distance,
-from ..core.losses import glvq_loss, lvq1_loss, lvq21_loss
+    omega_distance,
-from ..nn.activations import get_activation
+    squared_euclidean_distance,
+)
+from ..core.initializers import EyeLinearTransformInitializer
+from ..core.losses import (
+    GLVQLoss,
+    lvq1_loss,
+    lvq21_loss,
+)
+from ..core.transforms import LinearTransform
 from ..nn.wrappers import LambdaLayer, LossLayer
 from .abstract import ImagePrototypesMixin, SupervisedPrototypeModel
+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,
+        )
+
+    # 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(
@@ -54,10 +69,8 @@ class GLVQ(SupervisedPrototypeModel):
     def shared_step(self, batch, batch_idx, optimizer_idx=None):
         x, y = batch
         out = self.compute_distances(x)
-        plabels = self.proto_layer.labels
+        _, plabels = self.proto_layer()
-        mu = self.loss(out, y, prototype_labels=plabels)
+        loss = self.loss(out, y, plabels)
-        batch_loss = self.transfer_layer(mu, beta=self.hparams.transfer_beta)
-        loss = batch_loss.sum(dim=0)
         return out, loss
 
     def training_step(self, batch, batch_idx, optimizer_idx=None):
@@ -99,6 +112,7 @@ class SiameseGLVQ(GLVQ):
     transformation pipeline are only learned from the inputs.
 
     """
+
     def __init__(self,
                  hparams,
                  backbone=torch.nn.Identity(),
@@ -113,7 +127,8 @@ class SiameseGLVQ(GLVQ):
         proto_opt = self.optimizer(self.proto_layer.parameters(),
                                    lr=self.hparams.proto_lr)
         # Only add a backbone optimizer if backbone has trainable parameters
-        if (bb_params := list(self.backbone.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:
@@ -132,9 +147,13 @@ class SiameseGLVQ(GLVQ):
         protos, _ = self.proto_layer()
         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
 
@@ -164,6 +183,7 @@ class LVQMLN(SiameseGLVQ):
     rather in the embedding space.
 
     """
+
     def compute_distances(self, x):
         latent_protos, _ = self.proto_layer()
         latent_x = self.backbone(x)
@@ -179,6 +199,7 @@ class GRLVQ(SiameseGLVQ):
     TODO Make a RelevanceLayer. `bb_lr` is ignored otherwise.
 
     """
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -204,22 +225,27 @@ 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,
+        omega_initializer = kwargs.get("omega_initializer",
+                                       EyeLinearTransformInitializer())
+        self.backbone = LinearTransform(
+            self.hparams.input_dim,
             self.hparams.latent_dim,
-                                        bias=False)
+            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)
+        omega = self.backbone.weight  # (input_dim, latent_dim)
-        lam = omega.T @ omega
+        lam = omega @ omega.T
         return lam.detach().cpu()
 
 
@@ -230,13 +256,14 @@ class GMLVQ(GLVQ):
     function. This makes it easier to implement a localized variant.
 
     """
+
     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",
-                                       EyeTransformInitializer())
+                                       EyeLinearTransformInitializer())
         omega = omega_initializer.generate(self.hparams.input_dim,
                                            self.hparams.latent_dim)
         self.register_parameter("_omega", Parameter(omega))
@@ -247,6 +274,12 @@ class GMLVQ(GLVQ):
     def omega_matrix(self):
         return self._omega.detach().cpu()
 
+    @property
+    def lambda_matrix(self):
+        omega = self._omega.detach()  # (input_dim, latent_dim)
+        lam = omega @ omega.T
+        return lam.detach().cpu()
+
     def compute_distances(self, x):
         protos, _ = self.proto_layer()
         distances = self.distance_layer(x, protos, self._omega)
@@ -258,6 +291,7 @@ class GMLVQ(GLVQ):
 
 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)
@@ -272,8 +306,48 @@ class LGMLVQ(GMLVQ):
         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, dataloader_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)
@@ -282,6 +356,7 @@ 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)
@@ -304,3 +379,18 @@ 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, dataloader_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))

prototorch/models/knn.py

@@ -4,15 +4,19 @@ import warnings
 
 from ..core.competitions import KNNC
 from ..core.components import LabeledComponents
-from ..core.initializers import LiteralCompInitializer, LiteralLabelsInitializer
+from ..core.initializers import (
+    LiteralCompInitializer,
+    LiteralLabelsInitializer,
+)
 from ..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, **kwargs)
+        super().__init__(hparams, skip_proto_layer=True, **kwargs)
 
         # Default hparams
         self.hparams.setdefault("k", 1)
@@ -24,7 +28,7 @@ class KNN(SupervisedPrototypeModel):
 
         # Layers
         self.proto_layer = LabeledComponents(
-            distribution=[],
+            distribution=len(data) * [1],
             components_initializer=LiteralCompInitializer(data),
             labels_initializer=LiteralLabelsInitializer(targets))
         self.competition_layer = KNNC(k=self.hparams.k)

prototorch/models/lvq.py

@@ -1,16 +1,17 @@
 """LVQ models that are optimized using non-gradient methods."""
 
 from ..core.losses import _get_dp_dm
+from ..nn.activations import get_activation
+from ..nn.wrappers import LambdaLayer
 from .abstract import NonGradientMixin
 from .glvq import GLVQ
 
 
 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.labels
 
+    def training_step(self, train_batch, batch_idx, optimizer_idx=None):
+        protos, plables = self.proto_layer()
         x, y = train_batch
         dis = self.compute_distances(x)
         # TODO Vectorized implementation
@@ -28,8 +29,8 @@ class LVQ1(NonGradientMixin, GLVQ):
             self.proto_layer.load_state_dict({"_components": updated_protos},
                                              strict=False)
 
-        print(f"{dis=}")
+        print(f"dis={dis}")
-        print(f"{y=}")
+        print(f"y={y}")
         # Logging
         self.log_acc(dis, y, tag="train_acc")
 
@@ -38,9 +39,9 @@ class LVQ1(NonGradientMixin, GLVQ):
 
 class LVQ21(NonGradientMixin, GLVQ):
     """Learning Vector Quantization 2.1."""
+
     def training_step(self, train_batch, batch_idx, optimizer_idx=None):
-        protos = self.proto_layer.components
+        protos, plabels = self.proto_layer()
-        plabels = self.proto_layer.labels
 
         x, y = train_batch
         dis = self.compute_distances(x)
@@ -66,4 +67,61 @@ class LVQ21(NonGradientMixin, GLVQ):
 
 
 class MedianLVQ(NonGradientMixin, GLVQ):
-    """Median LVQ"""
+    """Median LVQ
+
+    # TODO Avoid computing distances over and over
+
+    """
+
+    def __init__(self, hparams, verbose=True, **kwargs):
+        self.verbose = verbose
+        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, optimizer_idx=None):
+        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:
+                    if self.verbose:
+                        print(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

prototorch/models/probabilistic.py

@@ -11,6 +11,7 @@ from .glvq import GLVQ, SiameseGMLVQ
 
 class CELVQ(GLVQ):
     """Cross-Entropy Learning Vector Quantization."""
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -20,15 +21,16 @@ class CELVQ(GLVQ):
     def shared_step(self, batch, batch_idx, optimizer_idx=None):
         x, y = batch
         out = self.compute_distances(x)  # [None, num_protos]
-        plabels = self.proto_layer.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)
 
@@ -54,26 +56,38 @@ class ProbabilisticLVQ(GLVQ):
     def training_step(self, batch, batch_idx, optimizer_idx=None):
         x, y = batch
         out = self.forward(x)
-        plabels = self.proto_layer.labels
+        _, plabels = self.proto_layer()
         batch_loss = self.loss(out, y, plabels)
-        loss = batch_loss.sum(dim=0)
+        loss = batch_loss.sum()
         return loss
 
 
 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):
@@ -81,10 +95,15 @@ 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()
 
     # FIXME
@@ -92,5 +111,5 @@ class PLVQ(ProbabilisticLVQ, SiameseGMLVQ):
     #     x, y = batch
     #     y_pred = self(x)
     #     batch_loss = self.loss(y_pred, y)
-    #     loss = batch_loss.sum(dim=0)
+    #     loss = batch_loss.sum()
     #     return loss

prototorch/models/unsupervised.py

@@ -18,6 +18,7 @@ class KohonenSOM(NonGradientMixin, UnsupervisedPrototypeModel):
     TODO Allow non-2D grids
 
     """
+
     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
@@ -53,12 +54,14 @@ 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},
+        self.proto_layer.load_state_dict(
-                                         strict=False)
+            {"_components": updated_protos},
+            strict=False,
+        )
 
     def training_epoch_end(self, training_step_outputs):
         self._sigma = self.hparams.sigma * np.exp(
@@ -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)
 
@@ -85,12 +90,12 @@ 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.topology_layer = ConnectionTopology(
-            agelimit=self.hparams.agelimit,
+            agelimit=self.hparams.age_limit,
             num_prototypes=self.hparams.num_prototypes,
         )
 
@@ -110,6 +115,7 @@ class NeuralGas(UnsupervisedPrototypeModel):
 
 
 class GrowingNeuralGas(NeuralGas):
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -132,7 +138,7 @@ class GrowingNeuralGas(NeuralGas):
         mask[torch.arange(len(mask)), winner] = 1.0
         dp = d * mask
 
-        self.errors += torch.sum(dp * dp, dim=0)
+        self.errors += torch.sum(dp * dp)
         self.errors *= self.hparams.step_reduction
 
         self.topology_layer(d)
@@ -141,6 +147,8 @@ class GrowingNeuralGas(NeuralGas):
 
     def configure_callbacks(self):
         return [
-            GNGCallback(reduction=self.hparams.insert_reduction,
+            GNGCallback(
-                        freq=self.hparams.insert_freq)
+                reduction=self.hparams.insert_reduction,
+                freq=self.hparams.insert_freq,
+            )
         ]

prototorch/models/vis.py

@@ -7,14 +7,19 @@ import torchvision
 from matplotlib import pyplot as plt
 from torch.utils.data import DataLoader, Dataset
 
+from ..utils.colors import get_colors, get_legend_handles
 from ..utils.utils import mesh2d
 
 
 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,
@@ -27,6 +32,7 @@ class Vis2DAbstract(pl.Callback):
                  block=False):
         super().__init__()
 
+        if data:
             if isinstance(data, Dataset):
                 x, y = next(iter(DataLoader(data, batch_size=len(data))))
             elif isinstance(data, torch.utils.data.DataLoader):
@@ -43,8 +49,14 @@ 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
@@ -63,14 +75,12 @@ 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(self.xlabel)
-            ax.set_xlabel("Data dimension 1")
+        ax.set_ylabel(self.ylabel)
-        if ylabel:
-            ax.set_ylabel("Data dimension 2")
         if self.axis_off:
             ax.axis("off")
         return ax
@@ -113,42 +123,44 @@ class Vis2DAbstract(pl.Callback):
             else:
                 plt.show(block=self.block)
 
+    def on_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()
 
 
 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",
+        ax = self.setup_ax()
-                           ylabel="Data dimension 2")
-        self.plot_data(ax, x_train, y_train)
         self.plot_protos(ax, protos, plabels)
-        x = np.vstack((x_train, protos))
+        if x_train is not None:
-        mesh_input, xx, yy = mesh2d(x, self.border, self.resolution)
+            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):
+    def visualize(self, pl_module):
-        if not self.precheck(trainer):
-            return True
-
         protos = pl_module.prototypes
         plabels = pl_module.prototype_labels
         x_train, y_train = self.x_train, self.y_train
@@ -175,18 +187,42 @@ 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, ev_proj=True, **kwargs):
+        super().__init__(*args, **kwargs)
+        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 = torch.Tensor(x_train).to(device)
+            x_train = x_train @ u
+            x_train = x_train.cpu().detach()
+        if self.show_protos:
+            with torch.no_grad():
+                protos = torch.Tensor(protos).to(device)
+                protos = protos @ u
+                protos = protos.cpu().detach()
+        ax = self.setup_ax()
+        self.plot_data(ax, x_train, y_train)
+        if self.show_protos:
+            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",
+        ax = self.setup_ax()
-                           ylabel="Data dimension 2")
         self.plot_data(ax, x_train, y_train)
         self.plot_protos(ax, protos, "w")
         x = np.vstack((x_train, protos))
@@ -198,20 +234,15 @@ class VisCBC2D(Vis2DAbstract):
 
         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",
+        ax = self.setup_ax()
-                           ylabel="Data dimension 2")
         self.plot_data(ax, x_train, y_train)
         self.plot_protos(ax, protos, "w")
 
@@ -225,10 +256,27 @@ 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,
@@ -251,8 +299,6 @@ class VisImgComp(Vis2DAbstract):
                                    size=self.embedding_data,
                                    replace=False)
             data = self.x_train[ind]
-            # print(f"{data.shape=}")
-            # print(f"{self.y_train[ind].shape=}")
             tb.add_embedding(data.view(len(ind), -1),
                              label_img=data,
                              global_step=None,
@@ -283,14 +329,9 @@ class VisImgComp(Vis2DAbstract):
             dataformats=self.dataformats,
         )
 
-    def on_epoch_end(self, trainer, pl_module):
+    def visualize(self, pl_module):
-        if not self.precheck(trainer):
-            return True
-
         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)

setup.cfg

@@ -1,8 +1,23 @@
-[isort]
-profile = hug
-src_paths = isort, test
-
 [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

@@ -22,8 +22,8 @@ with open("README.md", "r") as fh:
     long_description = fh.read()
 
 INSTALL_REQUIRES = [
-    "prototorch>=0.6.0",
+    "prototorch>=0.7.3",
-    "pytorch_lightning>=1.3.5",
+    "pytorch_lightning>=1.6.0",
     "torchmetrics",
 ]
 CLI = [
@@ -37,6 +37,7 @@ DOCS = [
     "recommonmark",
     "sphinx",
     "nbsphinx",
+    "ipykernel",
     "sphinx_rtd_theme",
     "sphinxcontrib-katex",
     "sphinxcontrib-bibtex",
@@ -53,7 +54,7 @@ ALL = CLI + DEV + DOCS + EXAMPLES + TESTS
 
 setup(
     name=safe_name("prototorch_" + PLUGIN_NAME),
-    version="0.2.0",
+    version="0.5.0",
     description="Pre-packaged prototype-based "
     "machine learning models using ProtoTorch and PyTorch-Lightning.",
     long_description=long_description,
@@ -63,7 +64,7 @@ setup(
     url=PROJECT_URL,
     download_url=DOWNLOAD_URL,
     license="MIT",
-    python_requires=">=3.9",
+    python_requires=">=3.7",
     install_requires=INSTALL_REQUIRES,
     extras_require={
         "dev": DEV,
@@ -79,7 +80,10 @@ setup(
         "Intended Audience :: Science/Research",
         "License :: OSI Approved :: MIT License",
         "Natural Language :: English",
+        "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",

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

@@ -1,11 +1,27 @@
 #! /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 &> run_log.txt
+    export DISPLAY= && python $example --fast_dev_run 1 --gpus $gpu &> run_log.txt
     if [[ $? -ne 0 ]]; then
         echo "FAILED!!"
         cat run_log.txt

tests/test_models.py

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