feat: CLCC register torchmetrics added

Could be moved in a seperate plugin.

.bumpversion.cfg

@@ -1,10 +1,13 @@
 [bumpversion]
-current_version = 0.1.8
+current_version = 0.3.0
 commit = True
 tag = True
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)
 serialize = {major}.{minor}.{patch}
+message = build: bump version {current_version} → {new_version}
 
 [bumpversion:file:setup.py]
 
 [bumpversion:file:./prototorch/models/__init__.py]
+
+[bumpversion:file:./docs/source/conf.py]

.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.

.gitignore

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

.pre-commit-config.yaml

@@ -1,54 +1,54 @@
 # See https://pre-commit.com for more information
 # See https://pre-commit.com/hooks.html for more hooks
-repos:
--   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.0.1
-    hooks:
-    -   id: trailing-whitespace
-    -   id: end-of-file-fixer
-    -   id: check-yaml
-    -   id: check-added-large-files
-    -   id: check-ast
-    -   id: check-case-conflict
 
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.0.1
+  hooks:
+  - id: trailing-whitespace
+  - id: end-of-file-fixer
+  - id: check-yaml
+  - id: check-added-large-files
+  - id: check-ast
+  - id: check-case-conflict
 
 - repo: https://github.com/myint/autoflake
   rev: v1.4
   hooks:
-  -   id: autoflake
+  - id: autoflake
 
 - repo: http://github.com/PyCQA/isort
-  rev: 5.8.0
+  rev: 5.9.3
   hooks:
-  -   id: isort
+  - id: isort
 
--   repo: https://github.com/pre-commit/mirrors-mypy
+- repo: https://github.com/pre-commit/mirrors-mypy
-    rev: 'v0.902'
+  rev: v0.910-1
-    hooks:
+  hooks:
-    -   id: mypy
+  - id: mypy
-        files: prototorch
+    files: prototorch
-        additional_dependencies: [types-pkg_resources]
+    additional_dependencies: [types-pkg_resources]
 
--   repo: https://github.com/pre-commit/mirrors-yapf
+- repo: https://github.com/pre-commit/mirrors-yapf
-    rev: 'v0.31.0'  # Use the sha / tag you want to point at
+  rev: v0.31.0
-    hooks:
+  hooks:
-    -   id: yapf
+  - id: yapf
 
--   repo: https://github.com/pre-commit/pygrep-hooks
+- repo: https://github.com/pre-commit/pygrep-hooks
-    rev: v1.9.0  # Use the ref you want to point at
+  rev: v1.9.0
-    hooks:
+  hooks:
-    -   id: python-use-type-annotations
+  - id: python-use-type-annotations
-    -   id: python-no-log-warn
+  - id: python-no-log-warn
-    -   id: python-check-blanket-noqa
+  - id: python-check-blanket-noqa
 
+- repo: https://github.com/asottile/pyupgrade
+  rev: v2.29.0
+  hooks:
+  - id: pyupgrade
+    args: [--py36-plus]
 
--   repo: https://github.com/asottile/pyupgrade
+- repo: https://github.com/si-cim/gitlint
-    rev: v2.19.4
+  rev: v0.15.2-unofficial
-    hooks:
+  hooks:
-    -   id: pyupgrade
+  - id: gitlint
-
+    args: [--contrib=CT1, --ignore=B6, --msg-filename]
--   repo: https://github.com/jorisroovers/gitlint
-    rev: "v0.15.1"
-    hooks:
-    -   id: gitlint
-        args: [--contrib=CT1, --ignore=B6, --msg-filename]

.travis.yml

@@ -1,7 +1,11 @@
 dist: bionic
 sudo: false
 language: python
-python: 3.9
+python:
+  - 3.9
+  - 3.8
+  - 3.7
+  - 3.6
 cache:
   directories:
   - "$HOME/.cache/pip"
@@ -15,11 +19,26 @@ script:
 - ./tests/test_examples.sh examples/
 after_success:
 - bash <(curl -s https://codecov.io/bash)
-deploy:
+
-  provider: pypi
+# Publish on PyPI
-  username: __token__
+jobs:
-  password:
+  include:
-    secure: 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
+    - stage: build
-  on:
+      python: 3.9
-    tags: true
+      script: echo "Starting Pypi build"
-    skip_existing: true
+      deploy:
+        provider: pypi
+        username: __token__
+        distributions: "sdist bdist_wheel"
+        password:
+          secure: PDoASdYdVlt1aIROYilAsCW6XpBs/TDel0CSptDzX0CI7i4+ksEW6Jk0JyL58bQt7V4F8PeGty4A8SODzAUIk2d8sty5RI4VJjvXZFCXlUsW+JGUN3EvWNqJLnwN8TDxgu2ENao37GUh0dC6pL8b6bVDGeOLaY1E/YR1jimmTJuxxjKjBIU8ByqTNBnC3rzybMTPU3nRoOM/WMQUyReHrPoUJj685sLqrLruhAqhiYsPbotP8xY6i8+KBbhp5vgiARV2+LkbeGcYZwozCzrEqPKY7YIfVPh895cw0v4NRyFwK1P2jyyIt22Z9Ni0Uy1J5/Qp9Sv6mBPeGjm3pnpDCQyS+2bNIDaj08KUYTIo1mC/Jcu4jQgppZEF+oey9q1tgGo+/JhsTeERKV9BoPF5HDiRArU1s5aWJjFnCsHfu+W1XqX8bwN3aTYsEIaApT3/irc6XyFJIfMN82+z+lUcZ4Y1yAHT3nH1Vif+pZYZB0UOSGrHwuI/UayjKzbCzHMuHWylWB/9ehd4o4YVp6iubVHc7Sj0KQkwBgwgl6TvwNcUuFsplFabCxmX0mVcavXsWiOBc+ivPmU6574zGj0JcEk5ghVgnKH+QS96aVrKOzegwbl4O13jY8dJp+/zgXl0gJOvRKr4BhuBJKcBaMQHdSKUChVsJJtqDyt59GvWcbg=
+        on:
+          tags: true
+          skip_existing: true
+
+# The password is encrypted with:
+# `cd prototorch && travis encrypt your-pypi-api-token --add deploy.password`
+# See https://docs.travis-ci.com/user/deployment/pypi and
+# https://github.com/travis-ci/travis.rb#installation
+# for more details
+# Note: The encrypt command does not work well in ZSH.

README.md

@@ -20,23 +20,6 @@ pip install prototorch_models
 of** [ProtoTorch](https://github.com/si-cim/prototorch). The plugin should then
 be available for use in your Python environment as `prototorch.models`.
 
-## Contribution
-
-This repository contains definition for [git hooks](https://githooks.com).
-[Pre-commit](https://pre-commit.com) is automatically installed as development
-dependency with prototorch or you can install it manually with `pip install
-pre-commit`.
-
-Please install the hooks by running:
-```bash
-pre-commit install
-pre-commit install --hook-type commit-msg
-```
-before creating the first commit.
-
-The commit will fail if the commit message does not follow the specification
-provided [here](https://www.conventionalcommits.org/en/v1.0.0/#specification).
-
 ## Available models
 
 ### LVQ Family
@@ -53,6 +36,7 @@ provided [here](https://www.conventionalcommits.org/en/v1.0.0/#specification).
 - Soft Learning Vector Quantization (SLVQ)
 - Robust Soft Learning Vector Quantization (RSLVQ)
 - Probabilistic Learning Vector Quantization (PLVQ)
+- Median-LVQ
 
 ### Other
 
@@ -68,7 +52,6 @@ provided [here](https://www.conventionalcommits.org/en/v1.0.0/#specification).
 
 ## Planned models
 
-- Median-LVQ
 - Generalized Tangent Learning Vector Quantization (GTLVQ)
 - Self-Incremental Learning Vector Quantization (SILVQ)
 
@@ -103,6 +86,23 @@ To assist in the development process, you may also find it useful to install
 please avoid installing Tensorflow in this environment. It is known to cause
 problems with PyTorch-Lightning.**
 
+## Contribution
+
+This repository contains definition for [git hooks](https://githooks.com).
+[Pre-commit](https://pre-commit.com) is automatically installed as development
+dependency with prototorch or you can install it manually with `pip install
+pre-commit`.
+
+Please install the hooks by running:
+```bash
+pre-commit install
+pre-commit install --hook-type commit-msg
+```
+before creating the first commit.
+
+The commit will fail if the commit message does not follow the specification
+provided [here](https://www.conventionalcommits.org/en/v1.0.0/#specification).
+
 ## FAQ
 
 ### How do I update the plugin?

docs/source/conf.py

@@ -23,7 +23,7 @@ author = "Jensun Ravichandran"
 
 # The full version, including alpha/beta/rc tags
 #
-release = "0.4.4"
+release = "0.3.0"
 
 # -- General configuration ---------------------------------------------------
 

examples/cbc_iris.py

@@ -2,11 +2,10 @@
 
 import argparse
 
+import prototorch as pt
 import pytorch_lightning as pl
 import torch
 
-import prototorch as pt
-
 if __name__ == "__main__":
     # Command-line arguments
     parser = argparse.ArgumentParser()
@@ -24,21 +23,27 @@ if __name__ == "__main__":
 
     # Hyperparameters
     hparams = dict(
-        distribution=[2, 2, 2],
+        distribution=[1, 0, 3],
-        proto_lr=0.1,
+        margin=0.1,
+        proto_lr=0.01,
+        bb_lr=0.01,
     )
 
     # Initialize the model
     model = pt.models.CBC(
         hparams,
-        prototype_initializer=pt.components.SSI(train_ds, noise=0.01),
+        components_initializer=pt.initializers.SSCI(train_ds, noise=0.01),
+        reasonings_iniitializer=pt.initializers.
+        PurePositiveReasoningsInitializer(),
     )
 
     # Callbacks
-    vis = pt.models.VisCBC2D(data=train_ds,
+    vis = pt.models.Visualize2DVoronoiCallback(
-                             title="CBC Iris Example",
+        data=train_ds,
-                             resolution=100,
+        title="CBC Iris Example",
-                             axis_off=True)
+        resolution=100,
+        axis_off=True,
+    )
 
     # Setup trainer
     trainer = pl.Trainer.from_argparse_args(

examples/cli/README.md

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

examples/cli/gmlvq.py

@@ -1,20 +0,0 @@
-"""GMLVQ example using the MNIST dataset."""
-
-import torch
-from pytorch_lightning.utilities.cli import LightningCLI
-
-import prototorch as pt
-from prototorch.models import ImageGMLVQ
-from prototorch.models.abstract import PrototypeModel
-from prototorch.models.data import MNISTDataModule
-
-
-class ExperimentClass(ImageGMLVQ):
-    def __init__(self, hparams, **kwargs):
-        super().__init__(hparams,
-                         optimizer=torch.optim.Adam,
-                         prototype_initializer=pt.components.zeros(28 * 28),
-                         **kwargs)
-
-
-cli = LightningCLI(ImageGMLVQ, MNISTDataModule)

examples/cli/gmlvq.yaml

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

examples/dynamic_pruning.py

@@ -2,11 +2,10 @@
 
 import argparse
 
+import prototorch as pt
 import pytorch_lightning as pl
 import torch
 
-import prototorch as pt
-
 if __name__ == "__main__":
     # Command-line arguments
     parser = argparse.ArgumentParser()
@@ -37,7 +36,7 @@ if __name__ == "__main__":
     # Initialize the model
     model = pt.models.CELVQ(
         hparams,
-        prototype_initializer=pt.components.Ones(2, scale=3),
+        prototypes_initializer=pt.initializers.FVCI(2, 3.0),
     )
 
     # Compute intermediate input and output sizes

examples/glvq_iris.py

@@ -2,12 +2,12 @@
 
 import argparse
 
+import prototorch as pt
+import prototorch.models.clcc
 import pytorch_lightning as pl
 import torch
 from torch.optim.lr_scheduler import ExponentialLR
 
-import prototorch as pt
-
 if __name__ == "__main__":
     # Command-line arguments
     parser = argparse.ArgumentParser()
@@ -24,16 +24,16 @@ if __name__ == "__main__":
     hparams = dict(
         distribution={
             "num_classes": 3,
-            "prototypes_per_class": 4
+            "per_class": 4
         },
         lr=0.01,
     )
 
     # Initialize the model
-    model = pt.models.GLVQ(
+    model = prototorch.models.GLVQ(
         hparams,
         optimizer=torch.optim.Adam,
-        prototype_initializer=pt.components.SMI(train_ds),
+        prototypes_initializer=pt.initializers.SMCI(train_ds),
         lr_scheduler=ExponentialLR,
         lr_scheduler_kwargs=dict(gamma=0.99, verbose=False),
     )
@@ -42,7 +42,13 @@ if __name__ == "__main__":
     model.example_input_array = torch.zeros(4, 2)
 
     # Callbacks
-    vis = pt.models.VisGLVQ2D(data=train_ds)
+    vis = pt.models.Visualize2DVoronoiCallback(
+        data=train_ds,
+        resolution=200,
+        title="Example: GLVQ on Iris",
+        x_label="sepal length",
+        y_label="petal length",
+    )
 
     # Setup trainer
     trainer = pl.Trainer.from_argparse_args(

examples/glvq_spiral.py

@@ -2,11 +2,10 @@
 
 import argparse
 
+import prototorch as pt
 import pytorch_lightning as pl
 import torch
 
-import prototorch as pt
-
 if __name__ == "__main__":
     # Command-line arguments
     parser = argparse.ArgumentParser()
@@ -26,7 +25,6 @@ if __name__ == "__main__":
         distribution=(num_classes, prototypes_per_class),
         transfer_function="swish_beta",
         transfer_beta=10.0,
-        # lr=0.1,
         proto_lr=0.1,
         bb_lr=0.1,
         input_dim=2,
@@ -37,7 +35,7 @@ if __name__ == "__main__":
     model = pt.models.GMLVQ(
         hparams,
         optimizer=torch.optim.Adam,
-        prototype_initializer=pt.components.SSI(train_ds, noise=1e-2),
+        prototypes_initializer=pt.initializers.SSCI(train_ds, noise=1e-2),
     )
 
     # Callbacks
@@ -47,12 +45,12 @@ if __name__ == "__main__":
         block=False,
     )
     pruning = pt.models.PruneLoserPrototypes(
-        threshold=0.02,
+        threshold=0.01,
         idle_epochs=10,
         prune_quota_per_epoch=5,
-        frequency=2,
+        frequency=5,
         replace=True,
-        initializer=pt.components.SSI(train_ds, noise=1e-2),
+        prototypes_initializer=pt.initializers.SSCI(train_ds, noise=1e-1),
         verbose=True,
     )
     es = pl.callbacks.EarlyStopping(
@@ -68,7 +66,7 @@ if __name__ == "__main__":
         args,
         callbacks=[
             vis,
-            # es,
+            es,
             pruning,
         ],
         terminate_on_nan=True,

examples/gmlvq_iris.py

@@ -1,4 +1,4 @@
-"""GLVQ example using the Iris dataset."""
+"""GMLVQ example using the Iris dataset."""
 
 import argparse
 
@@ -22,30 +22,29 @@ if __name__ == "__main__":
     # Hyperparameters
     hparams = dict(
         input_dim=4,
-        latent_dim=3,
+        latent_dim=4,
         distribution={
             "num_classes": 3,
-            "prototypes_per_class": 2
+            "per_class": 2
         },
-        proto_lr=0.0005,
+        proto_lr=0.01,
-        bb_lr=0.0005,
+        bb_lr=0.01,
     )
 
     # Initialize the model
     model = pt.models.GMLVQ(
         hparams,
         optimizer=torch.optim.Adam,
-        prototype_initializer=pt.components.SSI(train_ds),
+        prototypes_initializer=pt.initializers.SMCI(train_ds),
         lr_scheduler=ExponentialLR,
         lr_scheduler_kwargs=dict(gamma=0.99, verbose=False),
-        omega_initializer=pt.components.PCA(train_ds.data)
     )
 
     # Compute intermediate input and output sizes
-    #model.example_input_array = torch.zeros(4, 2)
+    model.example_input_array = torch.zeros(4, 4)
 
     # Callbacks
-    vis = pt.models.VisGMLVQ2D(data=train_ds, border=0.1)
+    vis = pt.models.VisGMLVQ2D(data=train_ds)
 
     # Setup trainer
     trainer = pl.Trainer.from_argparse_args(

examples/gmlvq_mnist.py

@@ -2,13 +2,12 @@
 
 import argparse
 
+import prototorch as pt
 import pytorch_lightning as pl
 import torch
 from torchvision import transforms
 from torchvision.datasets import MNIST
 
-import prototorch as pt
-
 if __name__ == "__main__":
     # Command-line arguments
     parser = argparse.ArgumentParser()
@@ -56,7 +55,7 @@ if __name__ == "__main__":
     model = pt.models.ImageGMLVQ(
         hparams,
         optimizer=torch.optim.Adam,
-        prototype_initializer=pt.components.SMI(train_ds),
+        prototypes_initializer=pt.initializers.SMCI(train_ds),
     )
 
     # Callbacks
@@ -95,7 +94,7 @@ if __name__ == "__main__":
         ],
         terminate_on_nan=True,
         weights_summary=None,
-        accelerator="ddp",
+        # accelerator="ddp",
     )
 
     # Training loop

examples/gng_iris.py

@@ -2,11 +2,10 @@
 
 import argparse
 
+import prototorch as pt
 import pytorch_lightning as pl
 import torch
 
-import prototorch as pt
-
 if __name__ == "__main__":
     # Command-line arguments
     parser = argparse.ArgumentParser()
@@ -30,7 +29,7 @@ if __name__ == "__main__":
     # Initialize the model
     model = pt.models.GrowingNeuralGas(
         hparams,
-        prototype_initializer=pt.components.Zeros(2),
+        prototypes_initializer=pt.initializers.ZCI(2),
     )
 
     # Compute intermediate input and output sizes

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

@@ -2,25 +2,11 @@
 
 import argparse
 
+import prototorch as pt
 import pytorch_lightning as pl
 import torch
 from matplotlib import pyplot as plt
-
+from prototorch.utils.colors import hex_to_rgb
-import prototorch as pt
-
-
-def hex_to_rgb(hex_values):
-    for v in hex_values:
-        v = v.lstrip('#')
-        lv = len(v)
-        c = [int(v[i:i + lv // 3], 16) for i in range(0, lv, lv // 3)]
-        yield c
-
-
-def rgb_to_hex(rgb_values):
-    for v in rgb_values:
-        c = "%02x%02x%02x" % tuple(v)
-        yield c
 
 
 class Vis2DColorSOM(pl.Callback):
@@ -93,7 +79,7 @@ if __name__ == "__main__":
     # Initialize the model
     model = pt.models.KohonenSOM(
         hparams,
-        prototype_initializer=pt.components.Random(3),
+        prototypes_initializer=pt.initializers.RNCI(3),
     )
 
     # Compute intermediate input and output sizes

examples/lgmlvq_moons.py

@@ -2,23 +2,22 @@
 
 import argparse
 
+import prototorch as pt
 import pytorch_lightning as pl
 import torch
 
-import prototorch as pt
-
 if __name__ == "__main__":
     # Command-line arguments
     parser = argparse.ArgumentParser()
     parser = pl.Trainer.add_argparse_args(parser)
     args = parser.parse_args()
 
-    # Dataset
-    train_ds = pt.datasets.Moons(num_samples=300, noise=0.2, seed=42)
-
     # 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,
@@ -32,8 +31,10 @@ if __name__ == "__main__":
     )
 
     # Initialize the model
-    model = pt.models.LGMLVQ(hparams,
+    model = pt.models.LGMLVQ(
-                             prototype_initializer=pt.components.SMI(train_ds))
+        hparams,
+        prototypes_initializer=pt.initializers.SMCI(train_ds),
+    )
 
     # Compute intermediate input and output sizes
     model.example_input_array = torch.zeros(4, 2)

examples/liramlvq_tecator.py

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

examples/lvqmln_iris.py

@@ -2,11 +2,10 @@
 
 import argparse
 
+import prototorch as pt
 import pytorch_lightning as pl
 import torch
 
-import prototorch as pt
-
 
 class Backbone(torch.nn.Module):
     def __init__(self, input_size=4, hidden_size=10, latent_size=2):
@@ -41,7 +40,7 @@ if __name__ == "__main__":
 
     # Hyperparameters
     hparams = dict(
-        distribution=[1, 2, 2],
+        distribution=[3, 4, 5],
         proto_lr=0.001,
         bb_lr=0.001,
     )
@@ -52,7 +51,10 @@ if __name__ == "__main__":
     # Initialize the model
     model = pt.models.LVQMLN(
         hparams,
-        prototype_initializer=pt.components.SSI(train_ds, transform=backbone),
+        prototypes_initializer=pt.initializers.SSCI(
+            train_ds,
+            transform=backbone,
+        ),
         backbone=backbone,
     )
 
@@ -67,11 +69,21 @@ if __name__ == "__main__":
         resolution=500,
         axis_off=True,
     )
+    pruning = pt.models.PruneLoserPrototypes(
+        threshold=0.01,
+        idle_epochs=20,
+        prune_quota_per_epoch=2,
+        frequency=10,
+        verbose=True,
+    )
 
     # Setup trainer
     trainer = pl.Trainer.from_argparse_args(
         args,
-        callbacks=[vis],
+        callbacks=[
+            vis,
+            pruning,
+        ],
     )
 
     # Training loop

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/ng_iris.py

@@ -2,14 +2,13 @@
 
 import argparse
 
+import prototorch as pt
 import pytorch_lightning as pl
 import torch
 from sklearn.datasets import load_iris
 from sklearn.preprocessing import StandardScaler
 from torch.optim.lr_scheduler import ExponentialLR
 
-import prototorch as pt
-
 if __name__ == "__main__":
     # Command-line arguments
     parser = argparse.ArgumentParser()
@@ -38,7 +37,7 @@ if __name__ == "__main__":
     # Initialize the model
     model = pt.models.NeuralGas(
         hparams,
-        prototype_initializer=pt.components.Zeros(2),
+        prototypes_initializer=pt.core.ZCI(2),
         lr_scheduler=ExponentialLR,
         lr_scheduler_kwargs=dict(gamma=0.99, verbose=False),
     )

examples/rslvq_iris.py

@@ -2,11 +2,9 @@
 
 import argparse
 
+import prototorch as pt
 import pytorch_lightning as pl
 import torch
-from torchvision.transforms import Lambda
-
-import prototorch as pt
 
 if __name__ == "__main__":
     # Command-line arguments
@@ -28,19 +26,17 @@ if __name__ == "__main__":
         distribution=[2, 2, 3],
         proto_lr=0.05,
         lambd=0.1,
+        variance=1.0,
         input_dim=2,
         latent_dim=2,
         bb_lr=0.01,
     )
 
     # Initialize the model
-    model = pt.models.probabilistic.PLVQ(
+    model = pt.models.RSLVQ(
         hparams,
         optimizer=torch.optim.Adam,
-        # prototype_initializer=pt.components.SMI(train_ds),
+        prototypes_initializer=pt.initializers.SSCI(train_ds, noise=0.2),
-        prototype_initializer=pt.components.SSI(train_ds, noise=0.2),
-        # prototype_initializer=pt.components.Zeros(2),
-        # prototype_initializer=pt.components.Ones(2, scale=2.0),
     )
 
     # Compute intermediate input and output sizes
@@ -50,7 +46,7 @@ if __name__ == "__main__":
     print(model)
 
     # Callbacks
-    vis = pt.models.VisSiameseGLVQ2D(data=train_ds)
+    vis = pt.models.VisGLVQ2D(data=train_ds)
 
     # Setup trainer
     trainer = pl.Trainer.from_argparse_args(

examples/siamese_glvq_iris.py

@@ -2,11 +2,10 @@
 
 import argparse
 
+import prototorch as pt
 import pytorch_lightning as pl
 import torch
 
-import prototorch as pt
-
 
 class Backbone(torch.nn.Module):
     def __init__(self, input_size=4, hidden_size=10, latent_size=2):
@@ -52,7 +51,7 @@ if __name__ == "__main__":
     # Initialize the model
     model = pt.models.SiameseGLVQ(
         hparams,
-        prototype_initializer=pt.components.SMI(train_ds),
+        prototypes_initializer=pt.initializers.SMCI(train_ds),
         backbone=backbone,
         both_path_gradients=False,
     )

examples/warm_starting.py

@@ -0,0 +1,103 @@
+"""Warm-starting GLVQ with prototypes from Growing Neural Gas."""
+
+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()
+
+    # Prepare the data
+    train_ds = pt.datasets.Iris(dims=[0, 2])
+    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=64)
+
+    # Initialize the gng
+    gng = pt.models.GrowingNeuralGas(
+        hparams=dict(num_prototypes=5, insert_freq=2, lr=0.1),
+        prototypes_initializer=pt.initializers.ZCI(2),
+        lr_scheduler=ExponentialLR,
+        lr_scheduler_kwargs=dict(gamma=0.99, verbose=False),
+    )
+
+    # Callbacks
+    es = pl.callbacks.EarlyStopping(
+        monitor="loss",
+        min_delta=0.001,
+        patience=20,
+        mode="min",
+        verbose=False,
+        check_on_train_epoch_end=True,
+    )
+
+    # Setup trainer for GNG
+    trainer = pl.Trainer(
+        max_epochs=100,
+        callbacks=[es],
+        weights_summary=None,
+    )
+
+    # Training loop
+    trainer.fit(gng, train_loader)
+
+    # Hyperparameters
+    hparams = dict(
+        distribution=[],
+        lr=0.01,
+    )
+
+    # Warm-start prototypes
+    knn = pt.models.KNN(dict(k=1), data=train_ds)
+    prototypes = gng.prototypes
+    plabels = knn.predict(prototypes)
+
+    # Initialize the model
+    model = pt.models.GLVQ(
+        hparams,
+        optimizer=torch.optim.Adam,
+        prototypes_initializer=pt.initializers.LCI(prototypes),
+        labels_initializer=pt.initializers.LLI(plabels),
+        lr_scheduler=ExponentialLR,
+        lr_scheduler_kwargs=dict(gamma=0.99, verbose=False),
+    )
+
+    # Compute intermediate input and output sizes
+    model.example_input_array = torch.zeros(4, 2)
+
+    # Callbacks
+    vis = 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,
+            pruning,
+            es,
+        ],
+        weights_summary="full",
+        accelerator="ddp",
+    )
+
+    # Training loop
+    trainer.fit(model, train_loader)

prototorch/models/__init__.py

@@ -1,15 +1,24 @@
 """`models` plugin for the `prototorch` package."""
 
-from importlib.metadata import PackageNotFoundError, version
-
 from .callbacks import PrototypeConvergence, PruneLoserPrototypes
 from .cbc import CBC, ImageCBC
-from .glvq import (GLVQ, GLVQ1, GLVQ21, GMLVQ, GRLVQ, LGMLVQ, LVQMLN,
+from .glvq import (
-                   ImageGLVQ, ImageGMLVQ, SiameseGLVQ, SiameseGMLVQ)
+    GLVQ,
+    GLVQ1,
+    GLVQ21,
+    GMLVQ,
+    GRLVQ,
+    LGMLVQ,
+    LVQMLN,
+    ImageGLVQ,
+    ImageGMLVQ,
+    SiameseGLVQ,
+    SiameseGMLVQ,
+)
 from .knn import KNN
 from .lvq import LVQ1, LVQ21, MedianLVQ
 from .probabilistic import CELVQ, PLVQ, RSLVQ, SLVQ
 from .unsupervised import GrowingNeuralGas, HeskesSOM, KohonenSOM, NeuralGas
 from .vis import *
 
-__version__ = "0.1.8"
+__version__ = "0.3.0"

prototorch/models/abstract.py

@@ -1,29 +1,18 @@
 """Abstract classes to be inherited by prototorch models."""
 
-from typing import Final, final
-
 import pytorch_lightning as pl
 import torch
 import torchmetrics
-from prototorch.components import Components, LabeledComponents
+from prototorch.core.competitions import WTAC
-from prototorch.functions.distances import euclidean_distance
+from prototorch.core.components import Components, LabeledComponents
-from prototorch.modules import WTAC, LambdaLayer
+from prototorch.core.distances import euclidean_distance
-
+from prototorch.core.initializers import LabelsInitializer
-
+from prototorch.core.pooling import stratified_min_pooling
-class ProtoTorchMixin(object):
+from prototorch.nn.wrappers import LambdaLayer
-    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__()
 
@@ -38,6 +27,33 @@ 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.accelerator.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)
 
@@ -54,23 +70,6 @@ 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.reconfigure_optimizers()
@@ -85,17 +84,15 @@ class UnsupervisedPrototypeModel(PrototypeModel):
         super().__init__(hparams, **kwargs)
 
         # Layers
-        prototype_initializer = kwargs.get("prototype_initializer", None)
+        prototypes_initializer = kwargs.get("prototypes_initializer", None)
-        initialized_prototypes = kwargs.get("initialized_prototypes", None)
+        if prototypes_initializer is not None:
-        if prototype_initializer is not None or initialized_prototypes is not None:
             self.proto_layer = Components(
                 self.hparams.num_prototypes,
-                initializer=prototype_initializer,
+                initializer=prototypes_initializer,
-                initialized_components=initialized_prototypes,
             )
 
     def compute_distances(self, x):
-        protos = self.proto_layer()
+        protos = self.proto_layer().type_as(x)
         distances = self.distance_layer(x, protos)
         return distances
 
@@ -109,23 +106,24 @@ class SupervisedPrototypeModel(PrototypeModel):
         super().__init__(hparams, **kwargs)
 
         # Layers
-        prototype_initializer = kwargs.get("prototype_initializer", None)
+        prototypes_initializer = kwargs.get("prototypes_initializer", None)
-        initialized_prototypes = kwargs.get("initialized_prototypes", None)
+        labels_initializer = kwargs.get("labels_initializer",
-        if prototype_initializer is not None or initialized_prototypes is not None:
+                                        LabelsInitializer())
+        if prototypes_initializer is not None:
             self.proto_layer = LabeledComponents(
                 distribution=self.hparams.distribution,
-                initializer=prototype_initializer,
+                components_initializer=prototypes_initializer,
-                initialized_components=initialized_prototypes,
+                labels_initializer=labels_initializer,
             )
         self.competition_layer = WTAC()
 
     @property
     def prototype_labels(self):
-        return self.proto_layer.component_labels.detach().cpu()
+        return self.proto_layer.labels.detach().cpu()
 
     @property
     def num_classes(self):
-        return len(self.proto_layer.distribution)
+        return self.proto_layer.num_classes
 
     def compute_distances(self, x):
         protos, _ = self.proto_layer()
@@ -134,15 +132,14 @@ class SupervisedPrototypeModel(PrototypeModel):
 
     def forward(self, x):
         distances = self.compute_distances(x)
-        y_pred = self.predict_from_distances(distances)
+        _, plabels = self.proto_layer()
-        # TODO
+        winning = stratified_min_pooling(distances, plabels)
-        y_pred = torch.eye(self.num_classes, device=self.device)[
+        y_pred = torch.nn.functional.softmin(winning)
-            y_pred.long()]  # depends on labels {0,...,num_classes}
         return y_pred
 
     def predict_from_distances(self, distances):
         with torch.no_grad():
-            plabels = self.proto_layer.component_labels
+            _, plabels = self.proto_layer()
             y_pred = self.competition_layer(distances, plabels)
         return y_pred
 
@@ -164,27 +161,10 @@ class SupervisedPrototypeModel(PrototypeModel):
                  prog_bar=True,
                  logger=True)
 
+    def test_step(self, batch, batch_idx):
+        x, targets = batch
 
-class NonGradientMixin(ProtoTorchMixin):
+        preds = self.predict(x)
-    """Mixin for custom non-gradient optimization."""
+        accuracy = torchmetrics.functional.accuracy(preds.int(), targets.int())
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.automatic_optimization: Final = False
 
-    def training_step(self, train_batch, batch_idx, optimizer_idx=None):
+        self.log("test_acc", accuracy)
-        raise NotImplementedError
-
-
-class ImagePrototypesMixin(ProtoTorchMixin):
-    """Mixin for models with image prototypes."""
-    @final
-    def on_train_batch_end(self, outputs, batch, batch_idx, dataloader_idx):
-        """Constrain the components to the range [0, 1] by clamping after updates."""
-        self.proto_layer.components.data.clamp_(0.0, 1.0)
-
-    def get_prototype_grid(self, num_columns=2, return_channels_last=True):
-        from torchvision.utils import make_grid
-        grid = make_grid(self.components, nrow=num_columns)
-        if return_channels_last:
-            grid = grid.permute((1, 2, 0))
-        return grid.cpu()

prototorch/models/callbacks.py

@@ -4,7 +4,8 @@ import logging
 
 import pytorch_lightning as pl
 import torch
-from prototorch.components import Components
+from prototorch.core.components import Components
+from prototorch.core.initializers import LiteralCompInitializer
 
 from .extras import ConnectionTopology
 
@@ -16,7 +17,7 @@ class PruneLoserPrototypes(pl.Callback):
                  prune_quota_per_epoch=-1,
                  frequency=1,
                  replace=False,
-                 initializer=None,
+                 prototypes_initializer=None,
                  verbose=False):
         self.threshold = threshold  # minimum win ratio
         self.idle_epochs = idle_epochs  # epochs to wait before pruning
@@ -24,7 +25,7 @@ class PruneLoserPrototypes(pl.Callback):
         self.frequency = frequency
         self.replace = replace
         self.verbose = verbose
-        self.initializer = initializer
+        self.prototypes_initializer = prototypes_initializer
 
     def on_epoch_end(self, trainer, pl_module):
         if (trainer.current_epoch + 1) < self.idle_epochs:
@@ -54,9 +55,10 @@ 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,
+                pl_module.add_prototypes(
-                                         initializer=self.initializer)
+                    distribution=distribution,
+                    components_initializer=self.prototypes_initializer)
             new_num_protos = pl_module.num_prototypes
             if self.verbose:
                 print(f"`num_prototypes` changed from {cur_num_protos} "
@@ -116,7 +118,8 @@ class GNGCallback(pl.Callback):
 
             # Add component
             pl_module.proto_layer.add_components(
-                initialized_components=new_component.unsqueeze(0))
+                None,
+                initializer=LiteralCompInitializer(new_component.unsqueeze(0)))
 
             # Adjust Topology
             topology.add_prototype()
@@ -131,4 +134,4 @@ class GNGCallback(pl.Callback):
             pl_module.errors[
                 worst_neighbor] = errors[worst_neighbor] * self.reduction
 
-            trainer.accelerator_backend.setup_optimizers(trainer)
+            trainer.accelerator.setup_optimizers(trainer)

prototorch/models/cbc.py

@@ -1,49 +1,54 @@
 import torch
 import torchmetrics
+from prototorch.core.competitions import CBCC
+from prototorch.core.components import ReasoningComponents
+from prototorch.core.initializers import RandomReasoningsInitializer
+from prototorch.core.losses import MarginLoss
+from prototorch.core.similarities import euclidean_similarity
+from prototorch.nn.wrappers import LambdaLayer
 
-from .abstract import ImagePrototypesMixin
-from .extras import (CosineSimilarity, MarginLoss, ReasoningLayer,
-                     euclidean_similarity, rescaled_cosine_similarity,
-                     shift_activation)
 from .glvq import SiameseGLVQ
+from .mixin import ImagePrototypesMixin
 
 
 class CBC(SiameseGLVQ):
     """Classification-By-Components."""
-    def __init__(self, hparams, margin=0.1, **kwargs):
+    def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
-        self.margin = margin
-        self.similarity_fn = kwargs.get("similarity_fn", euclidean_similarity)
-        num_components = self.components.shape[0]
-        self.reasoning_layer = ReasoningLayer(num_components=num_components,
-                                              num_classes=self.num_classes)
-        self.component_layer = self.proto_layer
 
-    @property
+        similarity_fn = kwargs.get("similarity_fn", euclidean_similarity)
-    def components(self):
+        components_initializer = kwargs.get("components_initializer", None)
-        return self.prototypes
+        reasonings_initializer = kwargs.get("reasonings_initializer",
+                                            RandomReasoningsInitializer())
+        self.components_layer = ReasoningComponents(
+            self.hparams.distribution,
+            components_initializer=components_initializer,
+            reasonings_initializer=reasonings_initializer,
+        )
+        self.similarity_layer = LambdaLayer(similarity_fn)
+        self.competition_layer = CBCC()
 
-    @property
+        # Namespace hook
-    def reasonings(self):
+        self.proto_layer = self.components_layer
-        return self.reasoning_layer.reasonings.cpu()
+
+        self.loss = MarginLoss(self.hparams.margin)
 
     def forward(self, x):
-        components, _ = self.component_layer()
+        components, reasonings = self.components_layer()
         latent_x = self.backbone(x)
         self.backbone.requires_grad_(self.both_path_gradients)
         latent_components = self.backbone(components)
         self.backbone.requires_grad_(True)
-        detections = self.similarity_fn(latent_x, latent_components)
+        detections = self.similarity_layer(latent_x, latent_components)
-        probs = self.reasoning_layer(detections)
+        probs = self.competition_layer(detections, reasonings)
         return probs
 
     def shared_step(self, batch, batch_idx, optimizer_idx=None):
         x, y = batch
-        # x = x.view(x.size(0), -1)
         y_pred = self(x)
-        num_classes = self.reasoning_layer.num_classes
+        num_classes = self.num_classes
         y_true = torch.nn.functional.one_hot(y.long(), num_classes=num_classes)
-        loss = MarginLoss(self.margin)(y_pred, y_true).mean(dim=0)
+        loss = self.loss(y_pred, y_true).mean()
         return y_pred, loss
 
     def training_step(self, batch, batch_idx, optimizer_idx=None):
@@ -70,7 +75,3 @@ class ImageCBC(ImagePrototypesMixin, CBC):
     """CBC model that constrains the components to the range [0, 1] by
     clamping after updates.
     """
-    def __init__(self, hparams, **kwargs):
-        super().__init__(hparams, **kwargs)
-        # Namespace hook
-        self.proto_layer = self.component_layer

prototorch/models/clcc/clcc_glvq.py

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

prototorch/models/clcc/clcc_scheme.py

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

prototorch/models/clcc/test_clcc.py

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

prototorch/models/data.py

@@ -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

@@ -5,23 +5,31 @@ Modules not yet available in prototorch go here temporarily.
 """
 
 import torch
-from prototorch.functions.distances import euclidean_distance
+from prototorch.core.similarities import gaussian
-from prototorch.functions.similarities import cosine_similarity
 
 
-def rescaled_cosine_similarity(x, y):
+def rank_scaled_gaussian(distances, lambd):
-    """Cosine Similarity rescaled to [0, 1]."""
+    order = torch.argsort(distances, dim=1)
-    similarities = cosine_similarity(x, y)
+    ranks = torch.argsort(order, dim=1)
-    return (similarities + 1.0) / 2.0
+    return torch.exp(-torch.exp(-ranks / lambd) * distances)
 
 
-def shift_activation(x):
+class GaussianPrior(torch.nn.Module):
-    return (x + 1.0) / 2.0
+    def __init__(self, variance):
+        super().__init__()
+        self.variance = variance
+
+    def forward(self, distances):
+        return gaussian(distances, self.variance)
 
 
-def euclidean_similarity(x, y, variance=1.0):
+class RankScaledGaussianPrior(torch.nn.Module):
-    d = euclidean_distance(x, y)
+    def __init__(self, lambd):
-    return torch.exp(-(d * d) / (2 * variance))
+        super().__init__()
+        self.lambd = lambd
+
+    def forward(self, distances):
+        return rank_scaled_gaussian(distances, self.lambd)
 
 
 class ConnectionTopology(torch.nn.Module):
@@ -79,64 +87,3 @@ class ConnectionTopology(torch.nn.Module):
 
     def extra_repr(self):
         return f"(agelimit): ({self.agelimit})"
-
-
-class CosineSimilarity(torch.nn.Module):
-    def __init__(self, activation=shift_activation):
-        super().__init__()
-        self.activation = activation
-
-    def forward(self, x, y):
-        epsilon = torch.finfo(x.dtype).eps
-        normed_x = (x / x.pow(2).sum(dim=tuple(range(
-            1, x.ndim)), keepdim=True).clamp(min=epsilon).sqrt()).flatten(
-                start_dim=1)
-        normed_y = (y / y.pow(2).sum(dim=tuple(range(
-            1, y.ndim)), keepdim=True).clamp(min=epsilon).sqrt()).flatten(
-                start_dim=1)
-        # normed_x = (x / torch.linalg.norm(x, dim=1))
-        diss = torch.inner(normed_x, normed_y)
-        return self.activation(diss)
-
-
-class MarginLoss(torch.nn.modules.loss._Loss):
-    def __init__(self,
-                 margin=0.3,
-                 size_average=None,
-                 reduce=None,
-                 reduction="mean"):
-        super().__init__(size_average, reduce, reduction)
-        self.margin = margin
-
-    def forward(self, input_, target):
-        dp = torch.sum(target * input_, dim=-1)
-        dm = torch.max(input_ - target, dim=-1).values
-        return torch.nn.functional.relu(dm - dp + self.margin)
-
-
-class ReasoningLayer(torch.nn.Module):
-    def __init__(self, num_components, num_classes, num_replicas=1):
-        super().__init__()
-        self.num_replicas = num_replicas
-        self.num_classes = num_classes
-        probabilities_init = torch.zeros(2, 1, num_components,
-                                         self.num_classes)
-        probabilities_init.uniform_(0.4, 0.6)
-        # TODO Use `self.register_parameter("param", Paramater(param))` instead
-        self.reasoning_probabilities = torch.nn.Parameter(probabilities_init)
-
-    @property
-    def reasonings(self):
-        pk = self.reasoning_probabilities[0]
-        nk = (1 - pk) * self.reasoning_probabilities[1]
-        ik = 1 - pk - nk
-        img = torch.cat([pk, nk, ik], dim=0).permute(1, 0, 2)
-        return img.unsqueeze(1)
-
-    def forward(self, detections):
-        pk = self.reasoning_probabilities[0].clamp(0, 1)
-        nk = (1 - pk) * self.reasoning_probabilities[1].clamp(0, 1)
-        numerator = (detections @ (pk - nk)) + nk.sum(1)
-        probs = numerator / (pk + nk).sum(1)
-        probs = probs.squeeze(0)
-        return probs

prototorch/models/glvq.py

@@ -1,17 +1,16 @@
 """Models based on the GLVQ framework."""
 
 import torch
-from prototorch.functions.activations import get_activation
+from prototorch.core.competitions import wtac
-from prototorch.functions.competitions import wtac
+from prototorch.core.distances import lomega_distance, omega_distance, squared_euclidean_distance
-from prototorch.functions.distances import (lomega_distance, omega_distance,
+from prototorch.core.initializers import EyeTransformInitializer
-                                            squared_euclidean_distance)
+from prototorch.core.losses import GLVQLoss, lvq1_loss, lvq21_loss
-from prototorch.functions.helper import get_flat
+from prototorch.core.transforms import LinearTransform
-from prototorch.functions.losses import glvq_loss, lvq1_loss, lvq21_loss
+from prototorch.nn.wrappers import LambdaLayer, LossLayer
-from prototorch.components import LinearMapping
-from prototorch.modules import LambdaLayer, LossLayer
 from torch.nn.parameter import Parameter
 
-from .abstract import ImagePrototypesMixin, SupervisedPrototypeModel
+from .abstract import SupervisedPrototypeModel
+from .mixin import ImagePrototypesMixin
 
 
 class GLVQ(SupervisedPrototypeModel):
@@ -20,18 +19,16 @@ class GLVQ(SupervisedPrototypeModel):
         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,
-        # Prototype metrics
+            transfer_fn=self.hparams.transfer_fn,
-        self.initialize_prototype_win_ratios()
+            beta=self.hparams.transfer_beta,
+        )
 
     def initialize_prototype_win_ratios(self):
         self.register_buffer(
@@ -59,10 +56,8 @@ 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.component_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):
@@ -118,7 +113,8 @@ 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:
@@ -135,7 +131,7 @@ class SiameseGLVQ(GLVQ):
 
     def compute_distances(self, x):
         protos, _ = self.proto_layer()
-        x, protos = get_flat(x, protos)
+        x, protos = (arr.view(arr.size(0), -1) for arr in (x, protos))
         latent_x = self.backbone(x)
         self.backbone.requires_grad_(self.both_path_gradients)
         latent_protos = self.backbone(protos)
@@ -213,18 +209,22 @@ class SiameseGMLVQ(SiameseGLVQ):
         super().__init__(hparams, **kwargs)
 
         # Override the backbone
-        self.backbone = torch.nn.Linear(self.hparams.input_dim,
+        omega_initializer = kwargs.get("omega_initializer",
-                                        self.hparams.latent_dim,
+                                       EyeTransformInitializer())
-                                        bias=False)
+        self.backbone = LinearTransform(
+            self.hparams.input_dim,
+            self.hparams.output_dim,
+            initializer=omega_initializer,
+        )
 
     @property
     def omega_matrix(self):
-        return self.backbone.weight.detach().cpu()
+        return self.backbone.weights
 
     @property
     def lambda_matrix(self):
-        omega = self.backbone.weight  # (latent_dim, input_dim)
+        omega = self.backbone.weight  # (input_dim, latent_dim)
-        lam = omega.T @ omega
+        lam = omega @ omega.T
         return lam.detach().cpu()
 
 
@@ -240,22 +240,24 @@ class GMLVQ(GLVQ):
         super().__init__(hparams, distance_fn=distance_fn, **kwargs)
 
         # Additional parameters
-        omega_initializer = kwargs.get("omega_initializer", None)
+        omega_initializer = kwargs.get("omega_initializer",
-        initialized_omega = kwargs.get("initialized_omega", None)
+                                       EyeTransformInitializer())
-        if omega_initializer is not None or initialized_omega is not None:
+        omega = omega_initializer.generate(self.hparams.input_dim,
-            self.omega_layer = LinearMapping(
+                                           self.hparams.latent_dim)
-                mapping_shape=(self.hparams.input_dim, self.hparams.latent_dim),
+        self.register_parameter("_omega", Parameter(omega))
-                initializer=omega_initializer,
+        self.backbone = LambdaLayer(lambda x: x @ self._omega,
-                initialized_linearmapping=initialized_omega,
+                                    name="omega matrix")
-            )
-
-        self.register_parameter("_omega", Parameter(self.omega_layer.mapping))
-        self.backbone = LambdaLayer(lambda x: x @ self._omega, name = "omega matrix")
 
     @property
     def omega_matrix(self):
         return self._omega.detach().cpu()
 
+    @property
+    def lambda_matrix(self):
+        omega = self._omega.detach()  # (input_dim, latent_dim)
+        lam = omega @ omega.T
+        return lam.detach().cpu()
+
     def compute_distances(self, x):
         protos, _ = self.proto_layer()
         distances = self.distance_layer(x, protos, self._omega)
@@ -264,24 +266,6 @@ class GMLVQ(GLVQ):
     def extra_repr(self):
         return f"(omega): (shape: {tuple(self._omega.shape)})"
 
-    def predict_latent(self, x, map_protos=True):
-        """Predict `x` assuming it is already embedded in the latent space.
-
-        Only the prototypes are embedded in the latent space using the
-        backbone.
- 
-        """
-        self.eval()
-        with torch.no_grad():
-            protos, plabels = self.proto_layer()
-            if map_protos:
-                protos = self.backbone(protos)
-            d = squared_euclidean_distance(x, protos)
-            y_pred = wtac(d, plabels)
-        return y_pred
-
-
-
 
 class LGMLVQ(GMLVQ):
     """Localized and Generalized Matrix Learning Vector Quantization."""

prototorch/models/knn.py

@@ -2,8 +2,10 @@
 
 import warnings
 
-from prototorch.components import LabeledComponents
+from prototorch.core.competitions import KNNC
-from prototorch.modules import KNNC
+from prototorch.core.components import LabeledComponents
+from prototorch.core.initializers import LiteralCompInitializer, LiteralLabelsInitializer
+from prototorch.utils.utils import parse_data_arg
 
 from .abstract import SupervisedPrototypeModel
 
@@ -19,9 +21,13 @@ class KNN(SupervisedPrototypeModel):
         data = kwargs.get("data", None)
         if data is None:
             raise ValueError("KNN requires data, but was not provided!")
+        data, targets = parse_data_arg(data)
 
         # Layers
-        self.proto_layer = LabeledComponents(initialized_components=data)
+        self.proto_layer = LabeledComponents(
+            distribution=[],
+            components_initializer=LiteralCompInitializer(data),
+            labels_initializer=LiteralLabelsInitializer(targets))
         self.competition_layer = KNNC(k=self.hparams.k)
 
     def training_step(self, train_batch, batch_idx, optimizer_idx=None):

prototorch/models/lvq.py

@@ -1,17 +1,17 @@
 """LVQ models that are optimized using non-gradient methods."""
 
-from prototorch.functions.losses import _get_dp_dm
+from prototorch.core.losses import _get_dp_dm
+from prototorch.nn.activations import get_activation
+from prototorch.nn.wrappers import LambdaLayer
 
-from .abstract import NonGradientMixin
 from .glvq import GLVQ
+from .mixin import NonGradientMixin
 
 
 class LVQ1(NonGradientMixin, GLVQ):
     """Learning Vector Quantization 1."""
     def training_step(self, train_batch, batch_idx, optimizer_idx=None):
-        protos = self.proto_layer.components
+        protos, plables = self.proto_layer()
-        plabels = self.proto_layer.component_labels
-
         x, y = train_batch
         dis = self.compute_distances(x)
         # TODO Vectorized implementation
@@ -29,6 +29,8 @@ class LVQ1(NonGradientMixin, GLVQ):
             self.proto_layer.load_state_dict({"_components": updated_protos},
                                              strict=False)
 
+        print(f"dis={dis}")
+        print(f"y={y}")
         # Logging
         self.log_acc(dis, y, tag="train_acc")
 
@@ -38,8 +40,7 @@ class LVQ1(NonGradientMixin, GLVQ):
 class LVQ21(NonGradientMixin, GLVQ):
     """Learning Vector Quantization 2.1."""
     def training_step(self, train_batch, batch_idx, optimizer_idx=None):
-        protos = self.proto_layer.components
+        protos, plabels = self.proto_layer()
-        plabels = self.proto_layer.component_labels
 
         x, y = train_batch
         dis = self.compute_distances(x)
@@ -65,4 +66,60 @@ 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/mixin.py

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

prototorch/models/probabilistic.py

@@ -1,13 +1,11 @@
 """Probabilistic GLVQ methods"""
 
 import torch
-from prototorch.functions.losses import nllr_loss, rslvq_loss
+from prototorch.core.losses import nllr_loss, rslvq_loss
-from prototorch.functions.pooling import (stratified_min_pooling,
+from prototorch.core.pooling import stratified_min_pooling, stratified_sum_pooling
-                                          stratified_sum_pooling)
+from prototorch.nn.wrappers import LambdaLayer, LossLayer
-from prototorch.functions.transforms import (GaussianPrior,
-                                             RankScaledGaussianPrior)
-from prototorch.modules import LambdaLayer, LossLayer
 
+from .extras import GaussianPrior, RankScaledGaussianPrior
 from .glvq import GLVQ, SiameseGMLVQ
 
 
@@ -22,11 +20,11 @@ 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.component_labels
+        _, plabels = self.proto_layer()
         winning = stratified_min_pooling(out, plabels)  # [None, num_classes]
         probs = -1.0 * winning
         batch_loss = self.loss(probs, y.long())
-        loss = batch_loss.sum(dim=0)
+        loss = batch_loss.sum()
         return out, loss
 
 
@@ -56,9 +54,9 @@ class ProbabilisticLVQ(GLVQ):
     def training_step(self, batch, batch_idx, optimizer_idx=None):
         x, y = batch
         out = self.forward(x)
-        plabels = self.proto_layer.component_labels
+        _, plabels = self.proto_layer()
         batch_loss = self.loss(out, y, plabels)
-        loss = batch_loss.sum(dim=0)
+        loss = batch_loss.sum()
         return loss
 
 
@@ -89,11 +87,10 @@ class PLVQ(ProbabilisticLVQ, SiameseGMLVQ):
             self.hparams.lambd)
         self.loss = torch.nn.KLDivLoss()
 
-    def training_step(self, batch, batch_idx, optimizer_idx=None):
+    # FIXME
-        x, y = batch
+    # def training_step(self, batch, batch_idx, optimizer_idx=None):
-        out = self.forward(x)
+    #     x, y = batch
-        y_dist = torch.nn.functional.one_hot(
+    #     y_pred = self(x)
-            y.long(), num_classes=self.num_classes).float()
+    #     batch_loss = self.loss(y_pred, y)
-        batch_loss = self.loss(out, y_dist)
+    #     loss = batch_loss.sum()
-        loss = batch_loss.sum(dim=0)
+    #     return loss
-        return loss

prototorch/models/unsupervised.py

@@ -2,14 +2,15 @@
 
 import numpy as np
 import torch
-from prototorch.functions.competitions import wtac
+from prototorch.core.competitions import wtac
-from prototorch.functions.distances import squared_euclidean_distance
+from prototorch.core.distances import squared_euclidean_distance
-from prototorch.modules import LambdaLayer
+from prototorch.core.losses import NeuralGasEnergy
-from prototorch.modules.losses import NeuralGasEnergy
+from prototorch.nn.wrappers import LambdaLayer
 
-from .abstract import NonGradientMixin, UnsupervisedPrototypeModel
+from .abstract import UnsupervisedPrototypeModel
 from .callbacks import GNGCallback
 from .extras import ConnectionTopology
+from .mixin import NonGradientMixin
 
 
 class KohonenSOM(NonGradientMixin, UnsupervisedPrototypeModel):
@@ -53,7 +54,7 @@ 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.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)
@@ -132,7 +133,7 @@ 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)

prototorch/models/vis.py

@@ -5,13 +5,18 @@ import pytorch_lightning as pl
 import torch
 import torchvision
 from matplotlib import pyplot as plt
+from prototorch.utils.utils import generate_mesh, mesh2d
 from torch.utils.data import DataLoader, Dataset
 
+COLOR_UNLABELED = 'w'
+
 
 class Vis2DAbstract(pl.Callback):
     def __init__(self,
                  data,
-                 title="Prototype Visualization",
+                 title=None,
+                 x_label=None,
+                 y_label=None,
                  cmap="viridis",
                  border=0.1,
                  resolution=100,
@@ -43,6 +48,8 @@ class Vis2DAbstract(pl.Callback):
         self.y_train = y
 
         self.title = title
+        self.x_label = x_label
+        self.y_label = y_label
         self.fig = plt.figure(self.title)
         self.cmap = cmap
         self.border = border
@@ -55,41 +62,24 @@ class Vis2DAbstract(pl.Callback):
         self.pause_time = pause_time
         self.block = block
 
-    def precheck(self, trainer):
+    def show_on_current_epoch(self, trainer):
-        if self.show_last_only:
+        if self.show_last_only and trainer.current_epoch != trainer.max_epochs - 1:
-            if trainer.current_epoch != trainer.max_epochs - 1:
+            return False
-                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:
+        if self.x_label:
-            ax.set_xlabel("Data dimension 1")
+            ax.set_xlabel(self.x_label)
-        if ylabel:
+        if self.x_label:
-            ax.set_ylabel("Data dimension 2")
+            ax.set_ylabel(self.y_label)
         if self.axis_off:
             ax.axis("off")
         return ax
 
-    def get_mesh_input(self, x):
+    def plot_data(self, ax, x, y):
-        x_shift = self.border * np.ptp(x[:, 0])
-        y_shift = self.border * np.ptp(x[:, 1])
-        x_min, x_max = x[:, 0].min() - x_shift, x[:, 0].max() + x_shift
-        y_min, y_max = x[:, 1].min() - y_shift, x[:, 1].max() + y_shift
-        xx, yy = np.meshgrid(np.linspace(x_min, x_max, self.resolution),
-                             np.linspace(y_min, y_max, self.resolution))
-        mesh_input = np.c_[xx.ravel(), yy.ravel()]
-        return mesh_input, xx, yy
-
-    def perform_pca_2D(self, data):
-        (_, eigVal, eigVec) = torch.pca_lowrank(data, q=2)
-        return data @ eigVec
-
-    def plot_data(self, ax, x, y, pca=False):
-        if pca:
-            x = self.perform_pca_2D(x)
         ax.scatter(
             x[:, 0],
             x[:, 1],
@@ -100,9 +90,7 @@ class Vis2DAbstract(pl.Callback):
             s=30,
         )
 
-    def plot_protos(self, ax, protos, plabels, pca=False):
+    def plot_protos(self, ax, protos, plabels):
-        if pca:
-            protos = self.perform_pca_2D(protos)
         ax.scatter(
             protos[:, 0],
             protos[:, 1],
@@ -133,25 +121,64 @@ class Vis2DAbstract(pl.Callback):
         plt.close()
 
 
-class VisGLVQ2D(Vis2DAbstract):
+class Visualize2DVoronoiCallback(Vis2DAbstract):
+    def __init__(self, data, **kwargs):
+        super().__init__(data, **kwargs)
+
+        self.data_min = torch.min(self.x_train, axis=0).values
+        self.data_max = torch.max(self.x_train, axis=0).values
+
+    def current_span(self, proto_values):
+        proto_min = torch.min(proto_values, axis=0).values
+        proto_max = torch.max(proto_values, axis=0).values
+
+        overall_min = torch.minimum(proto_min, self.data_min)
+        overall_max = torch.maximum(proto_max, self.data_max)
+
+        return overall_min, overall_max
+
+    def get_voronoi_diagram(self, min, max, model):
+        mesh_input, (xx, yy) = generate_mesh(
+            min,
+            max,
+            border=self.border,
+            resolution=self.resolution,
+            device=model.device,
+        )
+
+        y_pred = model.predict(mesh_input)
+        return xx, yy, y_pred.reshape(xx.shape)
+
     def on_epoch_end(self, trainer, pl_module):
-        if not self.precheck(trainer):
+        if not self.show_on_current_epoch(trainer):
             return True
 
-        protos = pl_module.prototypes
+        # Extract Prototypes
-        plabels = pl_module.prototype_labels
+        proto_values = pl_module.prototypes
-        x_train, y_train = self.x_train, self.y_train
+        if hasattr(pl_module, "prototype_labels"):
-        ax = self.setup_ax(xlabel="Data dimension 1",
+            proto_labels = pl_module.prototype_labels
-                           ylabel="Data dimension 2")
+        else:
-        self.plot_data(ax, x_train, y_train)
+            proto_labels = COLOR_UNLABELED
-        self.plot_protos(ax, protos, plabels)
+
-        x = np.vstack((x_train, protos))
+        # Calculate Voronoi Diagram
-        mesh_input, xx, yy = self.get_mesh_input(x)
+        overall_min, overall_max = self.current_span(proto_values)
-        _components = pl_module.proto_layer._components
+        xx, yy, y_pred = self.get_voronoi_diagram(
-        mesh_input = torch.from_numpy(mesh_input).type_as(_components)
+            overall_min,
-        y_pred = pl_module.predict(mesh_input)
+            overall_max,
-        y_pred = y_pred.cpu().reshape(xx.shape)
+            pl_module,
-        ax.contourf(xx, yy, y_pred, cmap=self.cmap, alpha=0.35)
+        )
+
+        ax = self.setup_ax()
+        ax.contourf(
+            xx.cpu(),
+            yy.cpu(),
+            y_pred.cpu(),
+            cmap=self.cmap,
+            alpha=0.35,
+        )
+
+        self.plot_data(ax, self.x_train, self.y_train)
+        self.plot_protos(ax, proto_values, proto_labels)
 
         self.log_and_display(trainer, pl_module)
 
@@ -162,7 +189,7 @@ class VisSiameseGLVQ2D(Vis2DAbstract):
         self.map_protos = map_protos
 
     def on_epoch_end(self, trainer, pl_module):
-        if not self.precheck(trainer):
+        if not self.show_on_current_epoch(trainer):
             return True
 
         protos = pl_module.prototypes
@@ -181,9 +208,9 @@ class VisSiameseGLVQ2D(Vis2DAbstract):
         if self.show_protos:
             self.plot_protos(ax, protos, plabels)
             x = np.vstack((x_train, protos))
-            mesh_input, xx, yy = self.get_mesh_input(x)
+            mesh_input, xx, yy = mesh2d(x, self.border, self.resolution)
         else:
-            mesh_input, xx, yy = self.get_mesh_input(x_train)
+            mesh_input, xx, yy = mesh2d(x_train, self.border, self.resolution)
         _components = pl_module.proto_layer._components
         mesh_input = torch.Tensor(mesh_input).type_as(_components)
         y_pred = pl_module.predict_latent(mesh_input,
@@ -195,83 +222,48 @@ class VisSiameseGLVQ2D(Vis2DAbstract):
 
 
 class VisGMLVQ2D(Vis2DAbstract):
-    def __init__(self, *args, map_protos=True, **kwargs):
+    def __init__(self, *args, ev_proj=True, **kwargs):
         super().__init__(*args, **kwargs)
-        self.map_protos = map_protos
+        self.ev_proj = ev_proj
 
     def on_epoch_end(self, trainer, pl_module):
-        if not self.precheck(trainer):
+        if not self.show_on_current_epoch(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 = pl_module.backbone(torch.Tensor(x_train).to(device))
+            x_train = torch.Tensor(x_train).to(device)
+            x_train = x_train @ u
             x_train = x_train.cpu().detach()
-        if self.map_protos:
+        if self.show_protos:
             with torch.no_grad():
-                protos = pl_module.backbone(torch.Tensor(protos).to(device))
+                protos = torch.Tensor(protos).to(device)
+                protos = protos @ u
                 protos = protos.cpu().detach()
         ax = self.setup_ax()
-        if x_train.shape[1] > 2:
-            self.plot_data(ax, x_train, y_train, pca=True)
-        else:
-            self.plot_data(ax, x_train, y_train, pca=False)
-        if self.show_protos:
-            if protos.shape[1] > 2:
-                self.plot_protos(ax, protos, plabels, pca=True)
-            else:
-                self.plot_protos(ax, protos, plabels, pca=False)
-        ### something to work on: meshgrid with pca
-        #    x = np.vstack((x_train, protos))
-        #    mesh_input, xx, yy = self.get_mesh_input(x)
-        #else:
-        #    mesh_input, xx, yy = self.get_mesh_input(x_train)
-        #_components = pl_module.proto_layer._components
-        #mesh_input = torch.Tensor(mesh_input).type_as(_components)
-        #y_pred = pl_module.predict_latent(mesh_input,
-        #                                  map_protos=self.map_protos)
-        #y_pred = y_pred.cpu().reshape(xx.shape)
-        #ax.contourf(xx, yy, y_pred, cmap=self.cmap, alpha=0.35)
-        self.log_and_display(trainer, pl_module)
-
-
-class VisCBC2D(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
-        protos = pl_module.components
-        ax = self.setup_ax(xlabel="Data dimension 1",
-                           ylabel="Data dimension 2")
         self.plot_data(ax, x_train, y_train)
-        self.plot_protos(ax, protos, "w")
+        if self.show_protos:
-        x = np.vstack((x_train, protos))
+            self.plot_protos(ax, protos, plabels)
-        mesh_input, xx, yy = self.get_mesh_input(x)
-        _components = pl_module.component_layer._components
-        y_pred = pl_module.predict(
-            torch.Tensor(mesh_input).type_as(_components))
-        y_pred = y_pred.cpu().reshape(xx.shape)
-
-        ax.contourf(xx, yy, y_pred, cmap=self.cmap, alpha=0.35)
 
         self.log_and_display(trainer, pl_module)
 
 
 class VisNG2D(Vis2DAbstract):
     def on_epoch_end(self, trainer, pl_module):
-        if not self.precheck(trainer):
+        if not self.show_on_current_epoch(trainer):
             return True
 
         x_train, y_train = self.x_train, self.y_train
         protos = pl_module.prototypes
         cmat = pl_module.topology_layer.cmat.cpu().numpy()
 
-        ax = self.setup_ax(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")
 
@@ -311,8 +303,6 @@ 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,
@@ -344,7 +334,7 @@ class VisImgComp(Vis2DAbstract):
         )
 
     def on_epoch_end(self, trainer, pl_module):
-        if not self.precheck(trainer):
+        if not self.show_on_current_epoch(trainer):
             return True
 
         if self.show:

setup.cfg

@@ -0,0 +1,8 @@
+[isort]
+profile = hug
+src_paths = isort, test
+
+[yapf]
+based_on_style = pep8
+spaces_before_comment = 2
+split_before_logical_operator = true

setup.py

@@ -18,11 +18,11 @@ PLUGIN_NAME = "models"
 PROJECT_URL = "https://github.com/si-cim/prototorch_models"
 DOWNLOAD_URL = "https://github.com/si-cim/prototorch_models.git"
 
-with open("README.md", "r") as fh:
+with open("README.md") as fh:
     long_description = fh.read()
 
 INSTALL_REQUIRES = [
-    "prototorch>=0.5.0,<0.6.0",
+    "prototorch>=0.7.0",
     "pytorch_lightning>=1.3.5",
     "torchmetrics",
 ]
@@ -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="0.1.8",
+    version="0.3.0",
     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=">=3.6",
     install_requires=INSTALL_REQUIRES,
     extras_require={
         "dev": DEV,
@@ -80,6 +81,9 @@ setup(
         "License :: OSI Approved :: MIT License",
         "Natural Language :: English",
         "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.8",
+        "Programming Language :: Python :: 3.7",
+        "Programming Language :: Python :: 3.6",
         "Operating System :: OS Independent",
         "Topic :: Scientific/Engineering :: Artificial Intelligence",
         "Topic :: Software Development :: Libraries",

tests/test_examples.sh

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