refactor: minor changes in probabilistic.py

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.4.1
+current_version = 0.2.0
 commit = True
 tag = True
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)

.codacy.yml

@@ -0,0 +1,15 @@
+# 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

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

.github/workflows/examples.yml

@@ -1,25 +0,0 @@
-# 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 3.9
-      uses: actions/setup-python@v2
-      with:
-        python-version: 3.9
-    - 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

@@ -1,73 +0,0 @@
-# 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 3.9
-      uses: actions/setup-python@v2
-      with:
-        python-version: 3.9
-    - 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"]
-        os: [ubuntu-latest, windows-latest]
-        exclude:
-        - os: windows-latest
-          python-version: "3.7"
-        - os: windows-latest
-          python-version: "3.8"
-
-    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 3.9
-      uses: actions/setup-python@v2
-      with:
-        python-version: "3.9"
-    - 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: v4.1.0
+  rev: v4.0.1
   hooks:
   - id: trailing-whitespace
   - id: end-of-file-fixer
@@ -18,19 +18,19 @@ repos:
   - id: autoflake
 
 - repo: http://github.com/PyCQA/isort
-  rev: 5.10.1
+  rev: 5.8.0
   hooks:
   - id: isort
 
 - repo: https://github.com/pre-commit/mirrors-mypy
-  rev: v0.931
+  rev: v0.902
   hooks:
   - id: mypy
     files: prototorch
     additional_dependencies: [types-pkg_resources]
 
 - repo: https://github.com/pre-commit/mirrors-yapf
-  rev: v0.32.0
+  rev: v0.31.0
   hooks:
   - id: yapf
 
@@ -42,7 +42,7 @@ repos:
   - id: python-check-blanket-noqa
 
 - repo: https://github.com/asottile/pyupgrade
-  rev: v2.31.0
+  rev: v2.19.4
   hooks:
   - id: pyupgrade
 

.travis.yml

@@ -0,0 +1,25 @@
+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

@@ -1,5 +1,6 @@
 # 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)

docs/source/conf.py

@@ -23,7 +23,7 @@ author = "Jensun Ravichandran"
 
 # The full version, including alpha/beta/rc tags
 #
-release = "0.4.1"
+release = "0.2.0"
 
 # -- General configuration ---------------------------------------------------
 

examples/binnam_tecator.py

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

examples/binnam_xor.py

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

examples/cli/README.md

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

examples/cli/gmlvq.py

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

examples/cli/gmlvq.yaml

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

examples/glvq_spiral.py

@@ -1,4 +1,4 @@
-"""GMLVQ example using the spiral dataset."""
+"""GLVQ example using the spiral dataset."""
 
 import argparse
 

examples/gmlvq_iris.py

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

examples/gtlvq_mnist.py

@@ -1,104 +0,0 @@
-"""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

@@ -1,63 +0,0 @@
-"""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

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

examples/ksom_colors.py

@@ -10,7 +10,6 @@ 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

@@ -8,7 +8,6 @@ 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_glvq_iris.py

@@ -8,7 +8,6 @@ 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

@@ -1,73 +0,0 @@
-"""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)

prototorch/models/__init__.py

@@ -1,5 +1,7 @@
 """`models` plugin for the `prototorch` package."""
 
+from importlib.metadata import PackageNotFoundError, version
+
 from .callbacks import PrototypeConvergence, PruneLoserPrototypes
 from .cbc import CBC, ImageCBC
 from .glvq import (
@@ -8,34 +10,18 @@ from .glvq import (
     GLVQ21,
     GMLVQ,
     GRLVQ,
-    GTLVQ,
     LGMLVQ,
     LVQMLN,
     ImageGLVQ,
     ImageGMLVQ,
-    ImageGTLVQ,
     SiameseGLVQ,
     SiameseGMLVQ,
-    SiameseGTLVQ,
 )
 from .knn import KNN
-from .lvq import (
+from .lvq import LVQ1, LVQ21, MedianLVQ
-    LVQ1,
+from .nam import BinaryNAM
-    LVQ21,
+from .probabilistic import CELVQ, PLVQ, RSLVQ, SLVQ
-    MedianLVQ,
+from .unsupervised import GrowingNeuralGas, HeskesSOM, KohonenSOM, NeuralGas
-)
-from .probabilistic import (
-    CELVQ,
-    PLVQ,
-    RSLVQ,
-    SLVQ,
-)
-from .unsupervised import (
-    GrowingNeuralGas,
-    HeskesSOM,
-    KohonenSOM,
-    NeuralGas,
-)
 from .vis import *
 
-__version__ = "0.4.1"
+__version__ = "0.2.0"

prototorch/models/abstract.py

@@ -1,5 +1,7 @@
 """Abstract classes to be inherited by prototorch models."""
 
+from typing import Final, final
+
 import pytorch_lightning as pl
 import torch
 import torchmetrics
@@ -14,7 +16,6 @@ from ..nn.wrappers import LambdaLayer
 
 class ProtoTorchBolt(pl.LightningModule):
     """All ProtoTorch models are ProtoTorch Bolts."""
-
     def __init__(self, hparams, **kwargs):
         super().__init__()
 
@@ -42,6 +43,7 @@ class ProtoTorchBolt(pl.LightningModule):
         else:
             return optimizer
 
+    @final
     def reconfigure_optimizers(self):
         self.trainer.accelerator.setup_optimizers(self.trainer)
 
@@ -53,7 +55,6 @@ class ProtoTorchBolt(pl.LightningModule):
 
 
 class PrototypeModel(ProtoTorchBolt):
-
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -83,7 +84,6 @@ class PrototypeModel(ProtoTorchBolt):
 
 
 class UnsupervisedPrototypeModel(PrototypeModel):
-
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -96,7 +96,7 @@ class UnsupervisedPrototypeModel(PrototypeModel):
             )
 
     def compute_distances(self, x):
-        protos = self.proto_layer().type_as(x)
+        protos = self.proto_layer()
         distances = self.distance_layer(x, protos)
         return distances
 
@@ -106,7 +106,6 @@ class UnsupervisedPrototypeModel(PrototypeModel):
 
 
 class SupervisedPrototypeModel(PrototypeModel):
-
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -137,14 +136,14 @@ class SupervisedPrototypeModel(PrototypeModel):
 
     def forward(self, x):
         distances = self.compute_distances(x)
-        _, plabels = self.proto_layer()
+        plabels = self.proto_layer.labels
         winning = stratified_min_pooling(distances, plabels)
-        y_pred = torch.nn.functional.softmin(winning, dim=1)
+        y_pred = torch.nn.functional.softmin(winning)
         return y_pred
 
     def predict_from_distances(self, distances):
         with torch.no_grad():
-            _, plabels = self.proto_layer()
+            plabels = self.proto_layer.labels
             y_pred = self.competition_layer(distances, plabels)
         return y_pred
 
@@ -166,14 +165,6 @@ 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."""
@@ -182,10 +173,9 @@ class ProtoTorchMixin(object):
 
 class NonGradientMixin(ProtoTorchMixin):
     """Mixin for custom non-gradient optimization."""
-
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
-        self.automatic_optimization = False
+        self.automatic_optimization: Final = False
 
     def training_step(self, train_batch, batch_idx, optimizer_idx=None):
         raise NotImplementedError
@@ -193,7 +183,7 @@ 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

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

prototorch/models/cbc.py

@@ -13,7 +13,6 @@ from .glvq import SiameseGLVQ
 
 class CBC(SiameseGLVQ):
     """Classification-By-Components."""
-
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 

prototorch/models/data.py

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

prototorch/models/extras.py

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

@@ -4,26 +4,16 @@ import torch
 from torch.nn.parameter import Parameter
 
 from ..core.competitions import wtac
-from ..core.distances import (
+from ..core.distances import lomega_distance, omega_distance, squared_euclidean_distance
-    lomega_distance,
-    omega_distance,
-    squared_euclidean_distance,
-)
 from ..core.initializers import EyeTransformInitializer
-from ..core.losses import (
+from ..core.losses import GLVQLoss, lvq1_loss, lvq21_loss
-    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)
 
@@ -65,7 +55,7 @@ class GLVQ(SupervisedPrototypeModel):
     def shared_step(self, batch, batch_idx, optimizer_idx=None):
         x, y = batch
         out = self.compute_distances(x)
-        _, plabels = self.proto_layer()
+        plabels = self.proto_layer.labels
         loss = self.loss(out, y, plabels)
         return out, loss
 
@@ -108,7 +98,6 @@ class SiameseGLVQ(GLVQ):
     transformation pipeline are only learned from the inputs.
 
     """
-
     def __init__(self,
                  hparams,
                  backbone=torch.nn.Identity(),
@@ -123,8 +112,7 @@ class SiameseGLVQ(GLVQ):
         proto_opt = self.optimizer(self.proto_layer.parameters(),
                                    lr=self.hparams.proto_lr)
         # Only add a backbone optimizer if backbone has trainable parameters
-        bb_params = list(self.backbone.parameters())
+        if (bb_params := list(self.backbone.parameters())):
-        if (bb_params):
             bb_opt = self.optimizer(bb_params, lr=self.hparams.bb_lr)
             optimizers = [proto_opt, bb_opt]
         else:
@@ -175,7 +163,6 @@ class LVQMLN(SiameseGLVQ):
     rather in the embedding space.
 
     """
-
     def compute_distances(self, x):
         latent_protos, _ = self.proto_layer()
         latent_x = self.backbone(x)
@@ -191,7 +178,6 @@ class GRLVQ(SiameseGLVQ):
     TODO Make a RelevanceLayer. `bb_lr` is ignored otherwise.
 
     """
-
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -217,7 +203,6 @@ class SiameseGMLVQ(SiameseGLVQ):
     Implemented as a Siamese network with a linear transformation backbone.
 
     """
-
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -248,7 +233,6 @@ 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)
@@ -266,12 +250,6 @@ class GMLVQ(GLVQ):
     def omega_matrix(self):
         return self._omega.detach().cpu()
 
-    @property
-    def lambda_matrix(self):
-        omega = self._omega.detach()  # (input_dim, latent_dim)
-        lam = omega @ omega.T
-        return lam.detach().cpu()
-
     def compute_distances(self, x):
         protos, _ = self.proto_layer()
         distances = self.distance_layer(x, protos, self._omega)
@@ -283,7 +261,6 @@ 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)
@@ -298,48 +275,8 @@ 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)
@@ -348,7 +285,6 @@ 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)
@@ -371,18 +307,3 @@ 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

@@ -4,17 +4,13 @@ import warnings
 
 from ..core.competitions import KNNC
 from ..core.components import LabeledComponents
-from ..core.initializers import (
+from ..core.initializers import LiteralCompInitializer, LiteralLabelsInitializer
-    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)
 

prototorch/models/lvq.py

@@ -9,9 +9,10 @@ from .glvq import GLVQ
 
 class LVQ1(NonGradientMixin, GLVQ):
     """Learning Vector Quantization 1."""
-
     def training_step(self, train_batch, batch_idx, optimizer_idx=None):
-        protos, plables = self.proto_layer()
+        protos = self.proto_layer.components
+        plabels = self.proto_layer.labels
+
         x, y = train_batch
         dis = self.compute_distances(x)
         # TODO Vectorized implementation
@@ -29,8 +30,8 @@ class LVQ1(NonGradientMixin, GLVQ):
             self.proto_layer.load_state_dict({"_components": updated_protos},
                                              strict=False)
 
-        print(f"dis={dis}")
+        print(f"{dis=}")
-        print(f"y={y}")
+        print(f"{y=}")
         # Logging
         self.log_acc(dis, y, tag="train_acc")
 
@@ -39,9 +40,9 @@ 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, plabels = self.proto_layer()
+        protos = self.proto_layer.components
+        plabels = self.proto_layer.labels
 
         x, y = train_batch
         dis = self.compute_distances(x)
@@ -72,7 +73,6 @@ class MedianLVQ(NonGradientMixin, GLVQ):
     # TODO Avoid computing distances over and over
 
     """
-
     def __init__(self, hparams, verbose=True, **kwargs):
         self.verbose = verbose
         super().__init__(hparams, **kwargs)
@@ -99,7 +99,8 @@ class MedianLVQ(NonGradientMixin, GLVQ):
         return lower_bound
 
     def training_step(self, train_batch, batch_idx, optimizer_idx=None):
-        protos, plabels = self.proto_layer()
+        protos = self.proto_layer.components
+        plabels = self.proto_layer.labels
 
         x, y = train_batch
         dis = self.compute_distances(x)

prototorch/models/nam.py

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

prototorch/models/probabilistic.py

@@ -1,5 +1,4 @@
 """Probabilistic GLVQ methods"""
-
 import torch
 
 from ..core.losses import nllr_loss, rslvq_loss
@@ -11,7 +10,6 @@ from .glvq import GLVQ, SiameseGMLVQ
 
 class CELVQ(GLVQ):
     """Cross-Entropy Learning Vector Quantization."""
-
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -21,7 +19,7 @@ class CELVQ(GLVQ):
     def shared_step(self, batch, batch_idx, optimizer_idx=None):
         x, y = batch
         out = self.compute_distances(x)  # [None, num_protos]
-        _, plabels = self.proto_layer()
+        plabels = self.proto_layer.labels
         winning = stratified_min_pooling(out, plabels)  # [None, num_classes]
         probs = -1.0 * winning
         batch_loss = self.loss(probs, y.long())
@@ -30,11 +28,10 @@ class CELVQ(GLVQ):
 
 
 class ProbabilisticLVQ(GLVQ):
-
     def __init__(self, hparams, rejection_confidence=0.0, **kwargs):
         super().__init__(hparams, **kwargs)
 
-        self.conditional_distribution = None
+        self.conditional_distribution = GaussianPrior(self.hparams.variance)
         self.rejection_confidence = rejection_confidence
 
     def forward(self, x):
@@ -56,28 +53,25 @@ class ProbabilisticLVQ(GLVQ):
     def training_step(self, batch, batch_idx, optimizer_idx=None):
         x, y = batch
         out = self.forward(x)
-        _, plabels = self.proto_layer()
+        plabels = self.proto_layer.labels
         batch_loss = self.loss(out, y, plabels)
-        loss = batch_loss.sum()
+        train_loss = batch_loss.sum()
-        return loss
+        self.log("train_loss", train_loss)
+        return train_loss
 
 
 class SLVQ(ProbabilisticLVQ):
     """Soft Learning Vector Quantization."""
-
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
         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)
         self.loss = LossLayer(rslvq_loss)
-        self.conditional_distribution = GaussianPrior(self.hparams.variance)
 
 
 class PLVQ(ProbabilisticLVQ, SiameseGMLVQ):
@@ -85,7 +79,6 @@ class PLVQ(ProbabilisticLVQ, SiameseGMLVQ):
 
     TODO: Use Backbone LVQ instead
     """
-
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
         self.conditional_distribution = RankScaledGaussianPrior(

prototorch/models/unsupervised.py

@@ -18,7 +18,6 @@ class KohonenSOM(NonGradientMixin, UnsupervisedPrototypeModel):
     TODO Allow non-2D grids
 
     """
-
     def __init__(self, hparams, **kwargs):
         h, w = hparams.get("shape")
         # Ignore `num_prototypes`
@@ -54,7 +53,7 @@ class KohonenSOM(NonGradientMixin, UnsupervisedPrototypeModel):
         grid = self._grid.view(-1, 2)
         gd = squared_euclidean_distance(wp, grid)
         nh = torch.exp(-gd / self._sigma**2)
-        protos = self.proto_layer()
+        protos = self.proto_layer.components
         diff = x.unsqueeze(dim=1) - protos
         delta = self._lr * self.hparams.alpha * nh.unsqueeze(-1) * diff
         updated_protos = protos + delta.sum(dim=0)
@@ -70,7 +69,6 @@ class KohonenSOM(NonGradientMixin, UnsupervisedPrototypeModel):
 
 
 class HeskesSOM(UnsupervisedPrototypeModel):
-
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -80,7 +78,6 @@ class HeskesSOM(UnsupervisedPrototypeModel):
 
 
 class NeuralGas(UnsupervisedPrototypeModel):
-
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -113,7 +110,6 @@ class NeuralGas(UnsupervisedPrototypeModel):
 
 
 class GrowingNeuralGas(NeuralGas):
-
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 

prototorch/models/vis.py

@@ -11,7 +11,6 @@ from ..utils.utils import mesh2d
 
 
 class Vis2DAbstract(pl.Callback):
-
     def __init__(self,
                  data,
                  title="Prototype Visualization",
@@ -118,8 +117,25 @@ class Vis2DAbstract(pl.Callback):
         plt.close()
 
 
-class VisGLVQ2D(Vis2DAbstract):
+class Vis2D(Vis2DAbstract):
+    def on_epoch_end(self, trainer, pl_module):
+        if not self.precheck(trainer):
+            return True
 
+        x_train, y_train = self.x_train, self.y_train
+        ax = self.setup_ax(xlabel="Data dimension 1",
+                           ylabel="Data dimension 2")
+        self.plot_data(ax, x_train, y_train)
+        mesh_input, xx, yy = mesh2d(x_train, self.border, self.resolution)
+        mesh_input = torch.from_numpy(mesh_input).type_as(x_train)
+        y_pred = pl_module.predict(mesh_input)
+        y_pred = y_pred.cpu().reshape(xx.shape)
+        ax.contourf(xx, yy, y_pred, cmap=self.cmap, alpha=0.35)
+
+        self.log_and_display(trainer, pl_module)
+
+
+class VisGLVQ2D(Vis2DAbstract):
     def on_epoch_end(self, trainer, pl_module):
         if not self.precheck(trainer):
             return True
@@ -143,7 +159,6 @@ class VisGLVQ2D(Vis2DAbstract):
 
 
 class VisSiameseGLVQ2D(Vis2DAbstract):
-
     def __init__(self, *args, map_protos=True, **kwargs):
         super().__init__(*args, **kwargs)
         self.map_protos = map_protos
@@ -181,42 +196,7 @@ class VisSiameseGLVQ2D(Vis2DAbstract):
         self.log_and_display(trainer, pl_module)
 
 
-class VisGMLVQ2D(Vis2DAbstract):
-
-    def __init__(self, *args, ev_proj=True, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.ev_proj = ev_proj
-
-    def on_epoch_end(self, trainer, pl_module):
-        if not self.precheck(trainer):
-            return True
-
-        protos = pl_module.prototypes
-        plabels = pl_module.prototype_labels
-        x_train, y_train = self.x_train, self.y_train
-        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)
-
-        self.log_and_display(trainer, pl_module)
-
-
 class VisCBC2D(Vis2DAbstract):
-
     def on_epoch_end(self, trainer, pl_module):
         if not self.precheck(trainer):
             return True
@@ -240,7 +220,6 @@ class VisCBC2D(Vis2DAbstract):
 
 
 class VisNG2D(Vis2DAbstract):
-
     def on_epoch_end(self, trainer, pl_module):
         if not self.precheck(trainer):
             return True
@@ -268,7 +247,6 @@ class VisNG2D(Vis2DAbstract):
 
 
 class VisImgComp(Vis2DAbstract):
-
     def __init__(self,
                  *args,
                  random_data=0,
@@ -291,6 +269,8 @@ class VisImgComp(Vis2DAbstract):
                                    size=self.embedding_data,
                                    replace=False)
             data = self.x_train[ind]
+            # print(f"{data.shape=}")
+            # print(f"{self.y_train[ind].shape=}")
             tb.add_embedding(data.view(len(ind), -1),
                              label_img=data,
                              global_step=None,

setup.cfg

@@ -1,23 +1,8 @@
+[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

@@ -22,7 +22,7 @@ with open("README.md", "r") as fh:
     long_description = fh.read()
 
 INSTALL_REQUIRES = [
-    "prototorch>=0.7.0",
+    "prototorch>=0.6.0",
     "pytorch_lightning>=1.3.5",
     "torchmetrics",
 ]
@@ -37,7 +37,6 @@ DOCS = [
     "recommonmark",
     "sphinx",
     "nbsphinx",
-    "ipykernel",
     "sphinx_rtd_theme",
     "sphinxcontrib-katex",
     "sphinxcontrib-bibtex",
@@ -54,7 +53,7 @@ ALL = CLI + DEV + DOCS + EXAMPLES + TESTS
 
 setup(
     name=safe_name("prototorch_" + PLUGIN_NAME),
-    version="0.4.1",
+    version="0.2.0",
     description="Pre-packaged prototype-based "
     "machine learning models using ProtoTorch and PyTorch-Lightning.",
     long_description=long_description,
@@ -64,7 +63,7 @@ setup(
     url=PROJECT_URL,
     download_url=DOWNLOAD_URL,
     license="MIT",
-    python_requires=">=3.6",
+    python_requires=">=3.9",
     install_requires=INSTALL_REQUIRES,
     extras_require={
         "dev": DEV,
@@ -81,9 +80,6 @@ setup(
         "License :: OSI Approved :: MIT License",
         "Natural Language :: English",
         "Programming Language :: Python :: 3.9",
-        "Programming Language :: Python :: 3.8",
-        "Programming Language :: Python :: 3.7",
-        "Programming Language :: Python :: 3.6",
         "Operating System :: OS Independent",
         "Topic :: Scientific/Engineering :: Artificial Intelligence",
         "Topic :: Software Development :: Libraries",

tests/test_.py

@@ -4,7 +4,6 @@ import unittest
 
 
 class TestDummy(unittest.TestCase):
-
     def setUp(self):
         pass
 

tests/test_examples.sh

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