build: bump version 0.4.1 → 0.5.0

Necessary for different optimizer runs

.bumpversion.cfg

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

.codacy.yml

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

.codecov.yml

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

.github/workflows/examples.yml

@@ -0,0 +1,25 @@
+# Thi workflow will install Python dependencies, run tests and lint with a single version of Python
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: examples
+
+on:
+  push:
+    paths:
+      - 'examples/**.py'
+jobs:
+  cpu:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python 3.10
+      uses: actions/setup-python@v2
+      with:
+        python-version: "3.10"
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install .[all]
+    - name: Run examples
+      run: |
+        ./tests/test_examples.sh examples/

.github/workflows/pythonapp.yml

@@ -0,0 +1,75 @@
+# This workflow will install Python dependencies, run tests and lint with a single version of Python
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: tests
+
+on:
+  push:
+  pull_request:
+    branches: [ master ]
+
+jobs:
+  style:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python 3.10
+      uses: actions/setup-python@v2
+      with:
+        python-version: "3.10"
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install .[all]
+    - uses: pre-commit/action@v2.0.3
+  compatibility:
+    needs: style
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.7", "3.8", "3.9", "3.10"]
+        os: [ubuntu-latest, windows-latest]
+        exclude:
+        - os: windows-latest
+          python-version: "3.7"
+        - os: windows-latest
+          python-version: "3.8"
+        - os: windows-latest
+          python-version: "3.9"
+
+    runs-on: ${{ matrix.os }}
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install .[all]
+    - name: Test with pytest
+      run: |
+        pytest
+  publish_pypi:
+    if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags')
+    needs: compatibility
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python 3.10
+      uses: actions/setup-python@v2
+      with:
+        python-version: "3.10"
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install .[all]
+        pip install wheel
+    - name: Build package
+      run: python setup.py sdist bdist_wheel
+    - name: Publish a Python distribution to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1
+      with:
+        user: __token__
+        password: ${{ secrets.PYPI_API_TOKEN }}

.pre-commit-config.yaml

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

.travis.yml

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

README.md

@@ -1,6 +1,5 @@
 # ProtoTorch Models
 
-[![Build Status](https://api.travis-ci.com/si-cim/prototorch_models.svg?branch=main)](https://travis-ci.com/github/si-cim/prototorch_models)
 [![GitHub tag (latest by date)](https://img.shields.io/github/v/tag/si-cim/prototorch_models?color=yellow&label=version)](https://github.com/si-cim/prototorch_models/releases)
 [![PyPI](https://img.shields.io/pypi/v/prototorch_models)](https://pypi.org/project/prototorch_models/)
 [![GitHub license](https://img.shields.io/github/license/si-cim/prototorch_models)](https://github.com/si-cim/prototorch_models/blob/master/LICENSE)

docs/source/conf.py

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

docs/source/tutorial.ipynb

@@ -2,223 +2,252 @@
  "cells": [
   {
    "cell_type": "markdown",
+   "id": "7ac5eff0",
+   "metadata": {},
    "source": [
     "# A short tutorial for the `prototorch.models` plugin"
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "markdown",
+   "id": "beb83780",
+   "metadata": {},
    "source": [
     "## Introduction"
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "markdown",
+   "id": "43b74278",
+   "metadata": {},
    "source": [
-    "This is a short tutorial for the [models](https://github.com/si-cim/prototorch_models) plugin of the [ProtoTorch](https://github.com/si-cim/prototorch) framework.\n",
+    "This is a short tutorial for the [models](https://github.com/si-cim/prototorch_models) plugin of the [ProtoTorch](https://github.com/si-cim/prototorch) framework. This is by no means a comprehensive look at all the features that the framework has to offer, but it should help you get up and running.\n",
     "\n",
     "[ProtoTorch](https://github.com/si-cim/prototorch) provides [torch.nn](https://pytorch.org/docs/stable/nn.html) modules and utilities to implement prototype-based models. However, it is up to the user to put these modules together into models and handle the training of these models. Expert machine-learning practioners and researchers sometimes prefer this level of control. However, this leads to a lot of boilerplate code that is essentially same across many projects. Needless to say, this is a source of a lot of frustration. [PyTorch-Lightning](https://pytorch-lightning.readthedocs.io/en/latest/) is a framework that helps avoid a lot of this frustration by handling the boilerplate code for you so you don't have to reinvent the wheel every time you need to implement a new model.\n",
     "\n",
     "With the [prototorch.models](https://github.com/si-cim/prototorch_models) plugin, we've gone one step further and pre-packaged commonly used prototype-models like GMLVQ as [Lightning-Modules](https://pytorch-lightning.readthedocs.io/en/latest/api/pytorch_lightning.core.lightning.html?highlight=lightning%20module#pytorch_lightning.core.lightning.LightningModule). With only a few lines to code, it is now possible to build and train prototype-models. It quite simply cannot get any simpler than this."
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "markdown",
+   "id": "4e5d1fad",
+   "metadata": {},
    "source": [
     "## Basics"
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "markdown",
+   "id": "1244b66b",
+   "metadata": {},
    "source": [
     "First things first. When working with the models plugin, you'll probably need `torch`, `prototorch` and `pytorch_lightning`. So, we recommend that you import all three like so:"
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "dcb88e8a",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "import prototorch as pt\n",
     "import pytorch_lightning as pl\n",
     "import torch"
-   ],
+   ]
-   "outputs": [],
-   "metadata": {}
   },
   {
    "cell_type": "markdown",
+   "id": "1adbe2f8",
+   "metadata": {},
    "source": [
     "### Building Models"
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "markdown",
+   "id": "96663ab1",
+   "metadata": {},
    "source": [
     "Let's start by building a `GLVQ` model. It is one of the simplest models to build. The only requirements are a prototype distribution and an initializer."
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "819ba756",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "model = pt.models.GLVQ(\n",
     "    hparams=dict(distribution=[1, 1, 1]),\n",
     "    prototypes_initializer=pt.initializers.ZerosCompInitializer(2),\n",
     ")"
-   ],
+   ]
-   "outputs": [],
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "1b37e97c",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "print(model)"
-   ],
+   ]
-   "outputs": [],
-   "metadata": {}
   },
   {
    "cell_type": "markdown",
+   "id": "d2c86903",
+   "metadata": {},
    "source": [
     "The key `distribution` in the `hparams` argument describes the prototype distribution. If it is a Python [list](https://docs.python.org/3/tutorial/datastructures.html), it is assumed that there are as many entries in this list as there are classes, and the number at each location of this list describes the number of prototypes to be used for that particular class. So, `[1, 1, 1]` implies that we have three classes with one prototype per class.   If it is a Python [tuple](https://docs.python.org/3/tutorial/datastructures.html), a shorthand of `(num_classes, prototypes_per_class)` is assumed. If it is a Python [dictionary](https://docs.python.org/3/tutorial/datastructures.html), the key-value pairs describe the class label and the number of prototypes for that class respectively. So, `{0: 2, 1: 2, 2: 2}` implies that we have three classes with labels `{1, 2, 3}`, each equipped with two prototypes. If however, the dictionary contains the keys `\"num_classes\"` and `\"per_class\"`, they are parsed to use their values as one might expect.\n",
     "\n",
     "The `prototypes_initializer` argument describes how the prototypes are meant to be initialized. This argument has to be an instantiated object of some kind of [AbstractComponentsInitializer](https://github.com/si-cim/prototorch/blob/dev/prototorch/components/initializers.py#L18). If this is a [ShapeAwareCompInitializer](https://github.com/si-cim/prototorch/blob/dev/prototorch/components/initializers.py#L41), this only requires a `shape` arugment that describes the shape of the prototypes. So, `pt.initializers.ZerosCompInitializer(3)` creates 3d-vector prototypes all initialized to zeros."
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "markdown",
+   "id": "45806052",
+   "metadata": {},
    "source": [
     "### Data"
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "markdown",
+   "id": "9d62c4c6",
+   "metadata": {},
    "source": [
     "The preferred way to working with data in `torch` is to use the [Dataset and Dataloader API](https://pytorch.org/tutorials/beginner/basics/data_tutorial.html). There a few pre-packaged datasets available under `prototorch.datasets`. See [here](https://prototorch.readthedocs.io/en/latest/api.html#module-prototorch.datasets) for a full list of available datasets."
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "504df02c",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "train_ds = pt.datasets.Iris(dims=[0, 2])"
-   ],
+   ]
-   "outputs": [],
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "3b8e7756",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "type(train_ds)"
-   ],
+   ]
-   "outputs": [],
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "bce43afa",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "train_ds.data.shape, train_ds.targets.shape"
-   ],
+   ]
-   "outputs": [],
-   "metadata": {}
   },
   {
    "cell_type": "markdown",
+   "id": "26a83328",
+   "metadata": {},
    "source": [
     "Once we have such a dataset, we could wrap it in a `Dataloader` to load the data in batches, and possibly apply some transformations on the fly."
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "67b80fbe",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "train_loader = torch.utils.data.DataLoader(train_ds, batch_size=2)"
-   ],
+   ]
-   "outputs": [],
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "c1185f31",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "type(train_loader)"
-   ],
+   ]
-   "outputs": [],
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "9b5a8963",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "x_batch, y_batch = next(iter(train_loader))\n",
     "print(f\"{x_batch=}, {y_batch=}\")"
-   ],
+   ]
-   "outputs": [],
-   "metadata": {}
   },
   {
    "cell_type": "markdown",
+   "id": "dd492ee2",
+   "metadata": {},
    "source": [
     "This perhaps seems like a lot of work for a small dataset that fits completely in memory. However, this comes in very handy when dealing with huge datasets that can only be processed in batches."
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "markdown",
+   "id": "5176b055",
+   "metadata": {},
    "source": [
     "### Training"
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "markdown",
+   "id": "46a7a506",
+   "metadata": {},
    "source": [
     "If you're familiar with other deep learning frameworks, you might perhaps expect a `.fit(...)` or `.train(...)` method. However, in PyTorch-Lightning, this is done slightly differently. We first create a trainer and then pass the model and the Dataloader to `trainer.fit(...)` instead. So, it is more functional in style than object-oriented."
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "279e75b7",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "trainer = pl.Trainer(max_epochs=2, weights_summary=None)"
-   ],
+   ]
-   "outputs": [],
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "e496b492",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "trainer.fit(model, train_loader)"
-   ],
+   ]
-   "outputs": [],
-   "metadata": {}
   },
   {
    "cell_type": "markdown",
+   "id": "497fbff6",
+   "metadata": {},
    "source": [
     "### From data to a trained model - a very minimal example"
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "ab069c5d",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "train_ds = pt.datasets.Iris(dims=[0, 2])\n",
     "train_loader = torch.utils.data.DataLoader(train_ds, batch_size=32)\n",
@@ -230,49 +259,239 @@
     "\n",
     "trainer = pl.Trainer(max_epochs=50, weights_summary=None)\n",
     "trainer.fit(model, train_loader)"
-   ],
+   ]
-   "outputs": [],
-   "metadata": {}
   },
   {
    "cell_type": "markdown",
+   "id": "30c71a93",
+   "metadata": {},
    "source": [
-    "## Advanced"
+    "### Saving/Loading trained models"
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "markdown",
+   "id": "f74ed2c1",
+   "metadata": {},
    "source": [
-    "### Initializing prototypes with a subset of a dataset (along with transformations)"
+    "Pytorch Lightning can automatically checkpoint the model during various stages of training, but it also possible to manually save a checkpoint after training."
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "3156658d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ckpt_path = \"./checkpoints/glvq_iris.ckpt\"\n",
+    "trainer.save_checkpoint(ckpt_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c1c34055",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loaded_model = pt.models.GLVQ.load_from_checkpoint(ckpt_path, strict=False)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bbbb08e9",
+   "metadata": {},
+   "source": [
+    "### Visualizing decision boundaries in 2D"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "53ca52dc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pt.models.VisGLVQ2D(data=train_ds).visualize(loaded_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8373531f",
+   "metadata": {},
+   "source": [
+    "### Saving/Loading trained weights"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "937bc458",
+   "metadata": {},
+   "source": [
+    "In most cases, the checkpointing workflow is sufficient. In some cases however, one might want to only save the trained weights from the model. The disadvantage of this method is that the model has be re-created using compatible initialization parameters before the weights could be loaded."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1f2035af",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ckpt_path = \"./checkpoints/glvq_iris_weights.pth\"\n",
+    "torch.save(model.state_dict(), ckpt_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1206021a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = pt.models.GLVQ(\n",
+    "    dict(distribution=(3, 2)),\n",
+    "    prototypes_initializer=pt.initializers.ZerosCompInitializer(2),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9f2a4beb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pt.models.VisGLVQ2D(data=train_ds, title=\"Before loading the weights\").visualize(model)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "528d2fc2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "torch.load(ckpt_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ec817e6b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model.load_state_dict(torch.load(ckpt_path), strict=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a208eab7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pt.models.VisGLVQ2D(data=train_ds, title=\"After loading the weights\").visualize(model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f8de748f",
+   "metadata": {},
+   "source": [
+    "## Advanced"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "53a64063",
+   "metadata": {},
+   "source": [
+    "### Warm-start a model with prototypes learned from another model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3177c277",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "trained_model = pt.models.GLVQ.load_from_checkpoint(\"./checkpoints/glvq_iris.ckpt\", strict=False)\n",
+    "model = pt.models.SiameseGMLVQ(\n",
+    "    dict(input_dim=2,\n",
+    "         latent_dim=2,\n",
+    "         distribution=(3, 2),\n",
+    "         proto_lr=0.0001,\n",
+    "         bb_lr=0.0001),\n",
+    "    optimizer=torch.optim.Adam,\n",
+    "    prototypes_initializer=pt.initializers.LCI(trained_model.prototypes),\n",
+    "    labels_initializer=pt.initializers.LLI(trained_model.prototype_labels),\n",
+    "    omega_initializer=pt.initializers.LLTI(torch.tensor([[0., 1.], [1., 0.]])),  # permute axes\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8baee9a2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(model)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cc203088",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pt.models.VisSiameseGLVQ2D(data=train_ds, title=\"GMLVQ - Warm-start state\").visualize(model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1f6a33a5",
+   "metadata": {},
+   "source": [
+    "### Initializing prototypes with a subset of a dataset (along with transformations)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "946ce341",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "import prototorch as pt\n",
     "import pytorch_lightning as pl\n",
     "import torch\n",
     "from torchvision import transforms\n",
-    "from torchvision.datasets import MNIST"
+    "from torchvision.datasets import MNIST\n",
-   ],
+    "from torchvision.utils import make_grid"
-   "outputs": [],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "510d9bd4",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "from matplotlib import pyplot as plt"
-   ],
+   ]
-   "outputs": [],
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "ea7c1228",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "train_ds = MNIST(\n",
     "    \"~/datasets\",\n",
@@ -284,59 +503,87 @@
     "        transforms.ToTensor(),\n",
     "    ]),\n",
     ")"
-   ],
+   ]
-   "outputs": [],
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "1b9eaf5c",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "s = int(0.05 * len(train_ds))\n",
     "init_ds, rest_ds = torch.utils.data.random_split(train_ds, [s, len(train_ds) - s])"
-   ],
+   ]
-   "outputs": [],
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "8c32c9f2",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "init_ds"
-   ],
+   ]
-   "outputs": [],
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "68a9a8b9",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "model = pt.models.ImageGLVQ(\n",
-    "    dict(distribution=(10, 5)),\n",
+    "    dict(distribution=(10, 1)),\n",
     "    prototypes_initializer=pt.initializers.SMCI(init_ds),\n",
     ")"
-   ],
+   ]
-   "outputs": [],
-   "metadata": {}
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "source": [
+   "id": "6f23df86",
-    "plt.imshow(model.get_prototype_grid(num_columns=10))"
+   "metadata": {},
-   ],
    "outputs": [],
-   "metadata": {}
+   "source": [
+    "plt.imshow(model.get_prototype_grid(num_columns=5))"
+   ]
   },
   {
    "cell_type": "markdown",
+   "id": "1c23c7b2",
+   "metadata": {},
+   "source": [
+    "We could, of course, just use the initializers in isolation. For example, we could quickly obtain a stratified selection from the data like so:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "30780927",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "protos, plabels = pt.components.LabeledComponents(\n",
+    "    distribution=(10, 5),\n",
+    "    components_initializer=pt.initializers.SMCI(init_ds),\n",
+    "    labels_initializer=pt.initializers.LabelsInitializer(),\n",
+    ")()\n",
+    "plt.imshow(make_grid(protos, 10).permute(1, 2, 0)[:, :, 0], cmap=\"jet\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4fa69f92",
+   "metadata": {},
    "source": [
     "## FAQs"
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "markdown",
+   "id": "fa20f9ac",
+   "metadata": {},
    "source": [
     "### How do I Retrieve the prototypes and their respective labels from the model?\n",
     "\n",
@@ -351,11 +598,12 @@
     "```python\n",
     ">>> model.prototype_labels\n",
     "```"
-   ],
+   ]
-   "metadata": {}
   },
   {
    "cell_type": "markdown",
+   "id": "ba8215bf",
+   "metadata": {},
    "source": [
     "### How do I make inferences/predictions/recall with my trained model?\n",
     "\n",
@@ -370,13 +618,12 @@
     "```python\n",
     ">>> y_pred = model(torch.Tensor(x_train))  # returns probabilities\n",
     "```"
-   ],
+   ]
-   "metadata": {}
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -390,7 +637,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.4"
+   "version": "3.9.12"
   }
  },
  "nbformat": 4,

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

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

examples/cli/gmlvq.yaml

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

examples/glvq_iris.py

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

examples/gmlvq_iris.py

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

examples/gmlvq_spiral.py

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

examples/gtlvq_mnist.py

@@ -0,0 +1,104 @@
+"""GTLVQ example using the MNIST dataset."""
+
+import argparse
+
+import prototorch as pt
+import pytorch_lightning as pl
+import torch
+from torchvision import transforms
+from torchvision.datasets import MNIST
+
+if __name__ == "__main__":
+    # Command-line arguments
+    parser = argparse.ArgumentParser()
+    parser = pl.Trainer.add_argparse_args(parser)
+    args = parser.parse_args()
+
+    # Dataset
+    train_ds = MNIST(
+        "~/datasets",
+        train=True,
+        download=True,
+        transform=transforms.Compose([
+            transforms.ToTensor(),
+        ]),
+    )
+    test_ds = MNIST(
+        "~/datasets",
+        train=False,
+        download=True,
+        transform=transforms.Compose([
+            transforms.ToTensor(),
+        ]),
+    )
+
+    # Dataloaders
+    train_loader = torch.utils.data.DataLoader(train_ds,
+                                               num_workers=0,
+                                               batch_size=256)
+    test_loader = torch.utils.data.DataLoader(test_ds,
+                                              num_workers=0,
+                                              batch_size=256)
+
+    # Hyperparameters
+    num_classes = 10
+    prototypes_per_class = 1
+    hparams = dict(
+        input_dim=28 * 28,
+        latent_dim=28,
+        distribution=(num_classes, prototypes_per_class),
+        proto_lr=0.01,
+        bb_lr=0.01,
+    )
+
+    # Initialize the model
+    model = pt.models.ImageGTLVQ(
+        hparams,
+        optimizer=torch.optim.Adam,
+        prototypes_initializer=pt.initializers.SMCI(train_ds),
+        #Use one batch of data for subspace initiator.
+        omega_initializer=pt.initializers.PCALinearTransformInitializer(
+            next(iter(train_loader))[0].reshape(256, 28 * 28)))
+
+    # Callbacks
+    vis = pt.models.VisImgComp(
+        data=train_ds,
+        num_columns=10,
+        show=False,
+        tensorboard=True,
+        random_data=100,
+        add_embedding=True,
+        embedding_data=200,
+        flatten_data=False,
+    )
+    pruning = pt.models.PruneLoserPrototypes(
+        threshold=0.01,
+        idle_epochs=1,
+        prune_quota_per_epoch=10,
+        frequency=1,
+        verbose=True,
+    )
+    es = pl.callbacks.EarlyStopping(
+        monitor="train_loss",
+        min_delta=0.001,
+        patience=15,
+        mode="min",
+        check_on_train_epoch_end=True,
+    )
+
+    # Setup trainer
+    # using GPUs here is strongly recommended!
+    trainer = pl.Trainer.from_argparse_args(
+        args,
+        callbacks=[
+            vis,
+            pruning,
+            # es,
+        ],
+        terminate_on_nan=True,
+        weights_summary=None,
+        accelerator="ddp",
+    )
+
+    # Training loop
+    trainer.fit(model, train_loader)

examples/gtlvq_moons.py

@@ -0,0 +1,63 @@
+"""Localized-GTLVQ example using the Moons dataset."""
+
+import argparse
+
+import prototorch as pt
+import pytorch_lightning as pl
+import torch
+
+if __name__ == "__main__":
+    # Command-line arguments
+    parser = argparse.ArgumentParser()
+    parser = pl.Trainer.add_argparse_args(parser)
+    args = parser.parse_args()
+
+    # Reproducibility
+    pl.utilities.seed.seed_everything(seed=2)
+
+    # Dataset
+    train_ds = pt.datasets.Moons(num_samples=300, noise=0.2, seed=42)
+
+    # Dataloaders
+    train_loader = torch.utils.data.DataLoader(train_ds,
+                                               batch_size=256,
+                                               shuffle=True)
+
+    # Hyperparameters
+    # Latent_dim should be lower than input dim.
+    hparams = dict(distribution=[1, 3], input_dim=2, latent_dim=1)
+
+    # Initialize the model
+    model = pt.models.GTLVQ(
+        hparams, prototypes_initializer=pt.initializers.SMCI(train_ds))
+
+    # Compute intermediate input and output sizes
+    model.example_input_array = torch.zeros(4, 2)
+
+    # Summary
+    print(model)
+
+    # Callbacks
+    vis = pt.models.VisGLVQ2D(data=train_ds)
+    es = pl.callbacks.EarlyStopping(
+        monitor="train_acc",
+        min_delta=0.001,
+        patience=20,
+        mode="max",
+        verbose=False,
+        check_on_train_epoch_end=True,
+    )
+
+    # Setup trainer
+    trainer = pl.Trainer.from_argparse_args(
+        args,
+        callbacks=[
+            vis,
+            es,
+        ],
+        weights_summary="full",
+        accelerator="ddp",
+    )
+
+    # Training loop
+    trainer.fit(model, train_loader)

examples/knn_iris.py

@@ -6,6 +6,7 @@ import prototorch as pt
 import pytorch_lightning as pl
 import torch
 from sklearn.datasets import load_iris
+from sklearn.model_selection import train_test_split
 
 if __name__ == "__main__":
     # Command-line arguments
@@ -14,12 +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)
@@ -35,7 +44,7 @@ if __name__ == "__main__":
 
     # Callbacks
     vis = pt.models.VisGLVQ2D(
-        data=(x_train, y_train),
+        data=(X_train, y_train),
         resolution=200,
         block=True,
     )
@@ -53,5 +62,8 @@ if __name__ == "__main__":
     trainer.fit(model, train_loader)
 
     # Recall
-    y_pred = model.predict(torch.tensor(x_train))
+    y_pred = model.predict(torch.tensor(X_train))
     print(y_pred)
+
+    # Test
+    trainer.test(model, dataloaders=test_loader)

examples/ksom_colors.py

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

examples/lvqmln_iris.py

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

examples/siamese_glvq_iris.py

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

examples/siamese_gtlvq_iris.py

@@ -0,0 +1,73 @@
+"""Siamese GTLVQ example using all four dimensions of the Iris dataset."""
+
+import argparse
+
+import prototorch as pt
+import pytorch_lightning as pl
+import torch
+
+
+class Backbone(torch.nn.Module):
+
+    def __init__(self, input_size=4, hidden_size=10, latent_size=2):
+        super().__init__()
+        self.input_size = input_size
+        self.hidden_size = hidden_size
+        self.latent_size = latent_size
+        self.dense1 = torch.nn.Linear(self.input_size, self.hidden_size)
+        self.dense2 = torch.nn.Linear(self.hidden_size, self.latent_size)
+        self.activation = torch.nn.Sigmoid()
+
+    def forward(self, x):
+        x = self.activation(self.dense1(x))
+        out = self.activation(self.dense2(x))
+        return out
+
+
+if __name__ == "__main__":
+    # Command-line arguments
+    parser = argparse.ArgumentParser()
+    parser = pl.Trainer.add_argparse_args(parser)
+    args = parser.parse_args()
+
+    # Dataset
+    train_ds = pt.datasets.Iris()
+
+    # Reproducibility
+    pl.utilities.seed.seed_everything(seed=2)
+
+    # Dataloaders
+    train_loader = torch.utils.data.DataLoader(train_ds, batch_size=150)
+
+    # Hyperparameters
+    hparams = dict(distribution=[1, 2, 3],
+                   proto_lr=0.01,
+                   bb_lr=0.01,
+                   input_dim=2,
+                   latent_dim=1)
+
+    # Initialize the backbone
+    backbone = Backbone(latent_size=hparams["input_dim"])
+
+    # Initialize the model
+    model = pt.models.SiameseGTLVQ(
+        hparams,
+        prototypes_initializer=pt.initializers.SMCI(train_ds),
+        backbone=backbone,
+        both_path_gradients=False,
+    )
+
+    # Model summary
+    print(model)
+
+    # Callbacks
+    vis = pt.models.VisSiameseGLVQ2D(data=train_ds, border=0.1)
+
+    # Setup trainer
+    trainer = pl.Trainer.from_argparse_args(
+        args,
+        callbacks=[vis],
+    )
+
+    # Training loop
+    trainer.fit(model, train_loader)

prototorch/models/__init__.py

@@ -1,7 +1,5 @@
 """`models` plugin for the `prototorch` package."""
 
-from importlib.metadata import PackageNotFoundError, version
-
 from .callbacks import PrototypeConvergence, PruneLoserPrototypes
 from .cbc import CBC, ImageCBC
 from .glvq import (
@@ -10,17 +8,32 @@ from .glvq import (
     GLVQ21,
     GMLVQ,
     GRLVQ,
+    GTLVQ,
     LGMLVQ,
     LVQMLN,
     ImageGLVQ,
     ImageGMLVQ,
+    ImageGTLVQ,
     SiameseGLVQ,
     SiameseGMLVQ,
+    SiameseGTLVQ,
 )
 from .knn import KNN
-from .lvq import LVQ1, LVQ21, MedianLVQ
+from .lvq import (
-from .probabilistic import CELVQ, PLVQ, RSLVQ, SLVQ
+    LVQ1,
-from .unsupervised import GrowingNeuralGas, HeskesSOM, KohonenSOM, NeuralGas
+    LVQ21,
+    MedianLVQ,
+)
+from .probabilistic import (
+    CELVQ,
+    RSLVQ,
+    SLVQ,
+)
+from .unsupervised import (
+    GrowingNeuralGas,
+    KohonenSOM,
+    NeuralGas,
+)
 from .vis import *
 
-__version__ = "0.2.0"
+__version__ = "0.5.0"

prototorch/models/abstract.py

@@ -1,7 +1,5 @@
 """Abstract classes to be inherited by prototorch models."""
 
-from typing import Final, final
-
 import pytorch_lightning as pl
 import torch
 import torchmetrics
@@ -9,13 +7,14 @@ import torchmetrics
 from ..core.competitions import WTAC
 from ..core.components import Components, LabeledComponents
 from ..core.distances import euclidean_distance
-from ..core.initializers import LabelsInitializer
+from ..core.initializers import LabelsInitializer, ZerosCompInitializer
 from ..core.pooling import stratified_min_pooling
 from ..nn.wrappers import LambdaLayer
 
 
 class ProtoTorchBolt(pl.LightningModule):
     """All ProtoTorch models are ProtoTorch Bolts."""
+
     def __init__(self, hparams, **kwargs):
         super().__init__()
 
@@ -43,9 +42,8 @@ class ProtoTorchBolt(pl.LightningModule):
         else:
             return optimizer
 
-    @final
     def reconfigure_optimizers(self):
-        self.trainer.accelerator.setup_optimizers(self.trainer)
+        self.trainer.strategy.setup_optimizers(self.trainer)
 
     def __repr__(self):
         surep = super().__repr__()
@@ -55,6 +53,7 @@ class ProtoTorchBolt(pl.LightningModule):
 
 
 class PrototypeModel(ProtoTorchBolt):
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -76,14 +75,17 @@ class PrototypeModel(ProtoTorchBolt):
 
     def add_prototypes(self, *args, **kwargs):
         self.proto_layer.add_components(*args, **kwargs)
+        self.hparams.distribution = self.proto_layer.distribution
         self.reconfigure_optimizers()
 
     def remove_prototypes(self, indices):
         self.proto_layer.remove_components(indices)
+        self.hparams.distribution = self.proto_layer.distribution
         self.reconfigure_optimizers()
 
 
 class UnsupervisedPrototypeModel(PrototypeModel):
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -96,7 +98,7 @@ class UnsupervisedPrototypeModel(PrototypeModel):
             )
 
     def compute_distances(self, x):
-        protos = self.proto_layer()
+        protos = self.proto_layer().type_as(x)
         distances = self.distance_layer(x, protos)
         return distances
 
@@ -106,19 +108,33 @@ class UnsupervisedPrototypeModel(PrototypeModel):
 
 
 class SupervisedPrototypeModel(PrototypeModel):
-    def __init__(self, hparams, **kwargs):
+
+    def __init__(self, hparams, skip_proto_layer=False, **kwargs):
         super().__init__(hparams, **kwargs)
 
         # Layers
+        distribution = hparams.get("distribution", None)
         prototypes_initializer = kwargs.get("prototypes_initializer", None)
         labels_initializer = kwargs.get("labels_initializer",
                                         LabelsInitializer())
-        if prototypes_initializer is not None:
+        if not skip_proto_layer:
-            self.proto_layer = LabeledComponents(
+            # when subclasses do not need a customized prototype layer
-                distribution=self.hparams.distribution,
+            if prototypes_initializer is not None:
-                components_initializer=prototypes_initializer,
+                # when building a new model
-                labels_initializer=labels_initializer,
+                self.proto_layer = LabeledComponents(
-            )
+                    distribution=distribution,
+                    components_initializer=prototypes_initializer,
+                    labels_initializer=labels_initializer,
+                )
+                proto_shape = self.proto_layer.components.shape[1:]
+                self.hparams.initialized_proto_shape = proto_shape
+            else:
+                # when restoring a checkpointed model
+                self.proto_layer = LabeledComponents(
+                    distribution=distribution,
+                    components_initializer=ZerosCompInitializer(
+                        self.hparams.initialized_proto_shape),
+                )
         self.competition_layer = WTAC()
 
     @property
@@ -136,14 +152,14 @@ class SupervisedPrototypeModel(PrototypeModel):
 
     def forward(self, x):
         distances = self.compute_distances(x)
-        plabels = self.proto_layer.labels
+        _, plabels = self.proto_layer()
         winning = stratified_min_pooling(distances, plabels)
-        y_pred = torch.nn.functional.softmin(winning)
+        y_pred = torch.nn.functional.softmin(winning, dim=1)
         return y_pred
 
     def predict_from_distances(self, distances):
         with torch.no_grad():
-            plabels = self.proto_layer.labels
+            _, plabels = self.proto_layer()
             y_pred = self.competition_layer(distances, plabels)
         return y_pred
 
@@ -165,17 +181,25 @@ class SupervisedPrototypeModel(PrototypeModel):
                  prog_bar=True,
                  logger=True)
 
+    def test_step(self, batch, batch_idx):
+        x, targets = batch
+
+        preds = self.predict(x)
+        accuracy = torchmetrics.functional.accuracy(preds.int(), targets.int())
+
+        self.log("test_acc", accuracy)
+
 
 class ProtoTorchMixin(object):
     """All mixins are ProtoTorchMixins."""
-    pass
 
 
 class NonGradientMixin(ProtoTorchMixin):
     """Mixin for custom non-gradient optimization."""
+
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
-        self.automatic_optimization: Final = False
+        self.automatic_optimization = False
 
     def training_step(self, train_batch, batch_idx, optimizer_idx=None):
         raise NotImplementedError
@@ -183,7 +207,7 @@ class NonGradientMixin(ProtoTorchMixin):
 
 class ImagePrototypesMixin(ProtoTorchMixin):
     """Mixin for models with image prototypes."""
-    @final
+
     def on_train_batch_end(self, outputs, batch, batch_idx, dataloader_idx):
         """Constrain the components to the range [0, 1] by clamping after updates."""
         self.proto_layer.components.data.clamp_(0.0, 1.0)

prototorch/models/callbacks.py

@@ -11,6 +11,7 @@ from .extras import ConnectionTopology
 
 
 class PruneLoserPrototypes(pl.Callback):
+
     def __init__(self,
                  threshold=0.01,
                  idle_epochs=10,
@@ -55,7 +56,7 @@ class PruneLoserPrototypes(pl.Callback):
                 distribution = dict(zip(labels.tolist(), counts.tolist()))
                 if self.verbose:
                     print(f"Re-adding pruned prototypes...")
-                    print(f"{distribution=}")
+                    print(f"distribution={distribution}")
                 pl_module.add_prototypes(
                     distribution=distribution,
                     components_initializer=self.prototypes_initializer)
@@ -67,6 +68,7 @@ class PruneLoserPrototypes(pl.Callback):
 
 
 class PrototypeConvergence(pl.Callback):
+
     def __init__(self, min_delta=0.01, idle_epochs=10, verbose=False):
         self.min_delta = min_delta
         self.idle_epochs = idle_epochs  # epochs to wait
@@ -89,6 +91,7 @@ class GNGCallback(pl.Callback):
     Based on "A Growing Neural Gas Network Learns Topologies" by Bernd Fritzke.
 
     """
+
     def __init__(self, reduction=0.1, freq=10):
         self.reduction = reduction
         self.freq = freq
@@ -134,4 +137,4 @@ class GNGCallback(pl.Callback):
             pl_module.errors[
                 worst_neighbor] = errors[worst_neighbor] * self.reduction
 
-            trainer.accelerator_backend.setup_optimizers(trainer)
+            trainer.strategy.setup_optimizers(trainer)

prototorch/models/cbc.py

@@ -13,8 +13,9 @@ from .glvq import SiameseGLVQ
 
 class CBC(SiameseGLVQ):
     """Classification-By-Components."""
+
     def __init__(self, hparams, **kwargs):
-        super().__init__(hparams, **kwargs)
+        super().__init__(hparams, skip_proto_layer=True, **kwargs)
 
         similarity_fn = kwargs.get("similarity_fn", euclidean_similarity)
         components_initializer = kwargs.get("components_initializer", None)

prototorch/models/data.py

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

prototorch/models/extras.py

@@ -15,7 +15,46 @@ def rank_scaled_gaussian(distances, lambd):
     return torch.exp(-torch.exp(-ranks / lambd) * distances)
 
 
+def orthogonalization(tensors):
+    """Orthogonalization via polar decomposition """
+    u, _, v = torch.svd(tensors, compute_uv=True)
+    u_shape = tuple(list(u.shape))
+    v_shape = tuple(list(v.shape))
+
+    # reshape to (num x N x M)
+    u = torch.reshape(u, (-1, u_shape[-2], u_shape[-1]))
+    v = torch.reshape(v, (-1, v_shape[-2], v_shape[-1]))
+
+    out = u @ v.permute([0, 2, 1])
+
+    out = torch.reshape(out, u_shape[:-1] + (v_shape[-2], ))
+
+    return out
+
+
+def ltangent_distance(x, y, omegas):
+    r"""Localized Tangent distance.
+    Compute Orthogonal Complement: math:`\bm P_k = \bm I - \Omega_k \Omega_k^T`
+    Compute Tangent Distance: math:`{\| \bm P \bm x - \bm P_k \bm y_k \|}_2`
+
+    :param `torch.tensor` omegas: Three dimensional matrix
+    :rtype: `torch.tensor`
+    """
+    x, y = [arr.view(arr.size(0), -1) for arr in (x, y)]
+    p = torch.eye(omegas.shape[-2], device=omegas.device) - torch.bmm(
+        omegas, omegas.permute([0, 2, 1]))
+    projected_x = x @ p
+    projected_y = torch.diagonal(y @ p).T
+    expanded_y = torch.unsqueeze(projected_y, dim=1)
+    batchwise_difference = expanded_y - projected_x
+    differences_squared = batchwise_difference**2
+    distances = torch.sqrt(torch.sum(differences_squared, dim=2))
+    distances = distances.permute(1, 0)
+    return distances
+
+
 class GaussianPrior(torch.nn.Module):
+
     def __init__(self, variance):
         super().__init__()
         self.variance = variance
@@ -25,6 +64,7 @@ class GaussianPrior(torch.nn.Module):
 
 
 class RankScaledGaussianPrior(torch.nn.Module):
+
     def __init__(self, lambd):
         super().__init__()
         self.lambd = lambd
@@ -34,6 +74,7 @@ class RankScaledGaussianPrior(torch.nn.Module):
 
 
 class ConnectionTopology(torch.nn.Module):
+
     def __init__(self, agelimit, num_prototypes):
         super().__init__()
         self.agelimit = agelimit

prototorch/models/glvq.py

@@ -4,16 +4,26 @@ import torch
 from torch.nn.parameter import Parameter
 
 from ..core.competitions import wtac
-from ..core.distances import lomega_distance, omega_distance, squared_euclidean_distance
+from ..core.distances import (
-from ..core.initializers import EyeTransformInitializer
+    lomega_distance,
-from ..core.losses import GLVQLoss, lvq1_loss, lvq21_loss
+    omega_distance,
+    squared_euclidean_distance,
+)
+from ..core.initializers import EyeLinearTransformInitializer
+from ..core.losses import (
+    GLVQLoss,
+    lvq1_loss,
+    lvq21_loss,
+)
 from ..core.transforms import LinearTransform
 from ..nn.wrappers import LambdaLayer, LossLayer
 from .abstract import ImagePrototypesMixin, SupervisedPrototypeModel
+from .extras import ltangent_distance, orthogonalization
 
 
 class GLVQ(SupervisedPrototypeModel):
     """Generalized Learning Vector Quantization."""
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -29,6 +39,10 @@ class GLVQ(SupervisedPrototypeModel):
             beta=self.hparams.transfer_beta,
         )
 
+    # def on_save_checkpoint(self, checkpoint):
+    #     if "prototype_win_ratios" in checkpoint["state_dict"]:
+    #         del checkpoint["state_dict"]["prototype_win_ratios"]
+
     def initialize_prototype_win_ratios(self):
         self.register_buffer(
             "prototype_win_ratios",
@@ -55,7 +69,7 @@ class GLVQ(SupervisedPrototypeModel):
     def shared_step(self, batch, batch_idx, optimizer_idx=None):
         x, y = batch
         out = self.compute_distances(x)
-        plabels = self.proto_layer.labels
+        _, plabels = self.proto_layer()
         loss = self.loss(out, y, plabels)
         return out, loss
 
@@ -98,6 +112,7 @@ class SiameseGLVQ(GLVQ):
     transformation pipeline are only learned from the inputs.
 
     """
+
     def __init__(self,
                  hparams,
                  backbone=torch.nn.Identity(),
@@ -112,7 +127,8 @@ class SiameseGLVQ(GLVQ):
         proto_opt = self.optimizer(self.proto_layer.parameters(),
                                    lr=self.hparams.proto_lr)
         # Only add a backbone optimizer if backbone has trainable parameters
-        if (bb_params := list(self.backbone.parameters())):
+        bb_params = list(self.backbone.parameters())
+        if (bb_params):
             bb_opt = self.optimizer(bb_params, lr=self.hparams.bb_lr)
             optimizers = [proto_opt, bb_opt]
         else:
@@ -131,9 +147,13 @@ class SiameseGLVQ(GLVQ):
         protos, _ = self.proto_layer()
         x, protos = [arr.view(arr.size(0), -1) for arr in (x, protos)]
         latent_x = self.backbone(x)
-        self.backbone.requires_grad_(self.both_path_gradients)
+
+        bb_grad = any([el.requires_grad for el in self.backbone.parameters()])
+
+        self.backbone.requires_grad_(bb_grad and self.both_path_gradients)
         latent_protos = self.backbone(protos)
-        self.backbone.requires_grad_(True)
+        self.backbone.requires_grad_(bb_grad)
+
         distances = self.distance_layer(latent_x, latent_protos)
         return distances
 
@@ -163,6 +183,7 @@ class LVQMLN(SiameseGLVQ):
     rather in the embedding space.
 
     """
+
     def compute_distances(self, x):
         latent_protos, _ = self.proto_layer()
         latent_x = self.backbone(x)
@@ -178,6 +199,7 @@ class GRLVQ(SiameseGLVQ):
     TODO Make a RelevanceLayer. `bb_lr` is ignored otherwise.
 
     """
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -203,15 +225,16 @@ class SiameseGMLVQ(SiameseGLVQ):
     Implemented as a Siamese network with a linear transformation backbone.
 
     """
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
         # Override the backbone
         omega_initializer = kwargs.get("omega_initializer",
-                                       EyeTransformInitializer())
+                                       EyeLinearTransformInitializer())
         self.backbone = LinearTransform(
             self.hparams.input_dim,
-            self.hparams.output_dim,
+            self.hparams.latent_dim,
             initializer=omega_initializer,
         )
 
@@ -233,13 +256,14 @@ class GMLVQ(GLVQ):
     function. This makes it easier to implement a localized variant.
 
     """
+
     def __init__(self, hparams, **kwargs):
         distance_fn = kwargs.pop("distance_fn", omega_distance)
         super().__init__(hparams, distance_fn=distance_fn, **kwargs)
 
         # Additional parameters
         omega_initializer = kwargs.get("omega_initializer",
-                                       EyeTransformInitializer())
+                                       EyeLinearTransformInitializer())
         omega = omega_initializer.generate(self.hparams.input_dim,
                                            self.hparams.latent_dim)
         self.register_parameter("_omega", Parameter(omega))
@@ -250,6 +274,12 @@ class GMLVQ(GLVQ):
     def omega_matrix(self):
         return self._omega.detach().cpu()
 
+    @property
+    def lambda_matrix(self):
+        omega = self._omega.detach()  # (input_dim, latent_dim)
+        lam = omega @ omega.T
+        return lam.detach().cpu()
+
     def compute_distances(self, x):
         protos, _ = self.proto_layer()
         distances = self.distance_layer(x, protos, self._omega)
@@ -261,6 +291,7 @@ class GMLVQ(GLVQ):
 
 class LGMLVQ(GMLVQ):
     """Localized and Generalized Matrix Learning Vector Quantization."""
+
     def __init__(self, hparams, **kwargs):
         distance_fn = kwargs.pop("distance_fn", lomega_distance)
         super().__init__(hparams, distance_fn=distance_fn, **kwargs)
@@ -275,8 +306,48 @@ class LGMLVQ(GMLVQ):
         self.register_parameter("_omega", Parameter(omega))
 
 
+class GTLVQ(LGMLVQ):
+    """Localized and Generalized Tangent Learning Vector Quantization."""
+
+    def __init__(self, hparams, **kwargs):
+        distance_fn = kwargs.pop("distance_fn", ltangent_distance)
+        super().__init__(hparams, distance_fn=distance_fn, **kwargs)
+
+        omega_initializer = kwargs.get("omega_initializer")
+
+        if omega_initializer is not None:
+            subspace = omega_initializer.generate(self.hparams.input_dim,
+                                                  self.hparams.latent_dim)
+            omega = torch.repeat_interleave(subspace.unsqueeze(0),
+                                            self.num_prototypes,
+                                            dim=0)
+        else:
+            omega = torch.rand(
+                self.num_prototypes,
+                self.hparams.input_dim,
+                self.hparams.latent_dim,
+                device=self.device,
+            )
+
+        # Re-register `_omega` to override the one from the super class.
+        self.register_parameter("_omega", Parameter(omega))
+
+    def on_train_batch_end(self, outputs, batch, batch_idx, dataloader_idx):
+        with torch.no_grad():
+            self._omega.copy_(orthogonalization(self._omega))
+
+
+class SiameseGTLVQ(SiameseGLVQ, GTLVQ):
+    """Generalized Tangent Learning Vector Quantization.
+
+    Implemented as a Siamese network with a linear transformation backbone.
+
+    """
+
+
 class GLVQ1(GLVQ):
     """Generalized Learning Vector Quantization 1."""
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
         self.loss = LossLayer(lvq1_loss)
@@ -285,6 +356,7 @@ class GLVQ1(GLVQ):
 
 class GLVQ21(GLVQ):
     """Generalized Learning Vector Quantization 2.1."""
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
         self.loss = LossLayer(lvq21_loss)
@@ -307,3 +379,18 @@ class ImageGMLVQ(ImagePrototypesMixin, GMLVQ):
     after updates.
 
     """
+
+
+class ImageGTLVQ(ImagePrototypesMixin, GTLVQ):
+    """GTLVQ for training on image data.
+
+    GTLVQ model that constrains the prototypes to the range [0, 1] by clamping
+    after updates.
+
+    """
+
+    def on_train_batch_end(self, outputs, batch, batch_idx, dataloader_idx):
+        """Constrain the components to the range [0, 1] by clamping after updates."""
+        self.proto_layer.components.data.clamp_(0.0, 1.0)
+        with torch.no_grad():
+            self._omega.copy_(orthogonalization(self._omega))

prototorch/models/knn.py

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

prototorch/models/lvq.py

@@ -9,10 +9,9 @@ from .glvq import GLVQ
 
 class LVQ1(NonGradientMixin, GLVQ):
     """Learning Vector Quantization 1."""
-    def training_step(self, train_batch, batch_idx, optimizer_idx=None):
-        protos = self.proto_layer.components
-        plabels = self.proto_layer.labels
 
+    def training_step(self, train_batch, batch_idx, optimizer_idx=None):
+        protos, plables = self.proto_layer()
         x, y = train_batch
         dis = self.compute_distances(x)
         # TODO Vectorized implementation
@@ -30,8 +29,8 @@ class LVQ1(NonGradientMixin, GLVQ):
             self.proto_layer.load_state_dict({"_components": updated_protos},
                                              strict=False)
 
-        print(f"{dis=}")
+        print(f"dis={dis}")
-        print(f"{y=}")
+        print(f"y={y}")
         # Logging
         self.log_acc(dis, y, tag="train_acc")
 
@@ -40,9 +39,9 @@ class LVQ1(NonGradientMixin, GLVQ):
 
 class LVQ21(NonGradientMixin, GLVQ):
     """Learning Vector Quantization 2.1."""
+
     def training_step(self, train_batch, batch_idx, optimizer_idx=None):
-        protos = self.proto_layer.components
+        protos, plabels = self.proto_layer()
-        plabels = self.proto_layer.labels
 
         x, y = train_batch
         dis = self.compute_distances(x)
@@ -73,6 +72,7 @@ class MedianLVQ(NonGradientMixin, GLVQ):
     # TODO Avoid computing distances over and over
 
     """
+
     def __init__(self, hparams, verbose=True, **kwargs):
         self.verbose = verbose
         super().__init__(hparams, **kwargs)
@@ -99,8 +99,7 @@ class MedianLVQ(NonGradientMixin, GLVQ):
         return lower_bound
 
     def training_step(self, train_batch, batch_idx, optimizer_idx=None):
-        protos = self.proto_layer.components
+        protos, plabels = self.proto_layer()
-        plabels = self.proto_layer.labels
 
         x, y = train_batch
         dis = self.compute_distances(x)

prototorch/models/probabilistic.py

@@ -11,6 +11,7 @@ from .glvq import GLVQ, SiameseGMLVQ
 
 class CELVQ(GLVQ):
     """Cross-Entropy Learning Vector Quantization."""
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -20,7 +21,7 @@ class CELVQ(GLVQ):
     def shared_step(self, batch, batch_idx, optimizer_idx=None):
         x, y = batch
         out = self.compute_distances(x)  # [None, num_protos]
-        plabels = self.proto_layer.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())
@@ -29,6 +30,7 @@ class CELVQ(GLVQ):
 
 
 class ProbabilisticLVQ(GLVQ):
+
     def __init__(self, hparams, rejection_confidence=0.0, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -54,7 +56,7 @@ class ProbabilisticLVQ(GLVQ):
     def training_step(self, batch, batch_idx, optimizer_idx=None):
         x, y = batch
         out = self.forward(x)
-        plabels = self.proto_layer.labels
+        _, plabels = self.proto_layer()
         batch_loss = self.loss(out, y, plabels)
         loss = batch_loss.sum()
         return loss
@@ -62,18 +64,30 @@ class ProbabilisticLVQ(GLVQ):
 
 class SLVQ(ProbabilisticLVQ):
     """Soft Learning Vector Quantization."""
+
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
+
+        # Default hparams
+        self.hparams.setdefault("variance", 1.0)
+        variance = self.hparams.get("variance")
+
+        self.conditional_distribution = GaussianPrior(variance)
         self.loss = LossLayer(nllr_loss)
-        self.conditional_distribution = GaussianPrior(self.hparams.variance)
 
 
 class RSLVQ(ProbabilisticLVQ):
     """Robust Soft Learning Vector Quantization."""
+
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
+
+        # Default hparams
+        self.hparams.setdefault("variance", 1.0)
+        variance = self.hparams.get("variance")
+
+        self.conditional_distribution = GaussianPrior(variance)
         self.loss = LossLayer(rslvq_loss)
-        self.conditional_distribution = GaussianPrior(self.hparams.variance)
 
 
 class PLVQ(ProbabilisticLVQ, SiameseGMLVQ):
@@ -81,10 +95,15 @@ class PLVQ(ProbabilisticLVQ, SiameseGMLVQ):
 
     TODO: Use Backbone LVQ instead
     """
+
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
-        self.conditional_distribution = RankScaledGaussianPrior(
+
-            self.hparams.lambd)
+        # Default hparams
+        self.hparams.setdefault("lambda", 1.0)
+        lam = self.hparams.get("lambda", 1.0)
+
+        self.conditional_distribution = RankScaledGaussianPrior(lam)
         self.loss = torch.nn.KLDivLoss()
 
     # FIXME

prototorch/models/unsupervised.py

@@ -18,6 +18,7 @@ class KohonenSOM(NonGradientMixin, UnsupervisedPrototypeModel):
     TODO Allow non-2D grids
 
     """
+
     def __init__(self, hparams, **kwargs):
         h, w = hparams.get("shape")
         # Ignore `num_prototypes`
@@ -34,7 +35,7 @@ class KohonenSOM(NonGradientMixin, UnsupervisedPrototypeModel):
 
         # Additional parameters
         x, y = torch.arange(h), torch.arange(w)
-        grid = torch.stack(torch.meshgrid(x, y), dim=-1)
+        grid = torch.stack(torch.meshgrid(x, y, indexing="ij"), dim=-1)
         self.register_buffer("_grid", grid)
         self._sigma = self.hparams.sigma
         self._lr = self.hparams.lr
@@ -53,12 +54,14 @@ class KohonenSOM(NonGradientMixin, UnsupervisedPrototypeModel):
         grid = self._grid.view(-1, 2)
         gd = squared_euclidean_distance(wp, grid)
         nh = torch.exp(-gd / self._sigma**2)
-        protos = self.proto_layer.components
+        protos = self.proto_layer()
         diff = x.unsqueeze(dim=1) - protos
         delta = self._lr * self.hparams.alpha * nh.unsqueeze(-1) * diff
         updated_protos = protos + delta.sum(dim=0)
-        self.proto_layer.load_state_dict({"_components": updated_protos},
+        self.proto_layer.load_state_dict(
-                                         strict=False)
+            {"_components": updated_protos},
+            strict=False,
+        )
 
     def training_epoch_end(self, training_step_outputs):
         self._sigma = self.hparams.sigma * np.exp(
@@ -69,6 +72,7 @@ class KohonenSOM(NonGradientMixin, UnsupervisedPrototypeModel):
 
 
 class HeskesSOM(UnsupervisedPrototypeModel):
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -78,6 +82,7 @@ class HeskesSOM(UnsupervisedPrototypeModel):
 
 
 class NeuralGas(UnsupervisedPrototypeModel):
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -85,12 +90,12 @@ class NeuralGas(UnsupervisedPrototypeModel):
         self.save_hyperparameters(hparams)
 
         # Default hparams
-        self.hparams.setdefault("agelimit", 10)
+        self.hparams.setdefault("age_limit", 10)
         self.hparams.setdefault("lm", 1)
 
         self.energy_layer = NeuralGasEnergy(lm=self.hparams.lm)
         self.topology_layer = ConnectionTopology(
-            agelimit=self.hparams.agelimit,
+            agelimit=self.hparams.age_limit,
             num_prototypes=self.hparams.num_prototypes,
         )
 
@@ -110,6 +115,7 @@ class NeuralGas(UnsupervisedPrototypeModel):
 
 
 class GrowingNeuralGas(NeuralGas):
+
     def __init__(self, hparams, **kwargs):
         super().__init__(hparams, **kwargs)
 
@@ -141,6 +147,8 @@ class GrowingNeuralGas(NeuralGas):
 
     def configure_callbacks(self):
         return [
-            GNGCallback(reduction=self.hparams.insert_reduction,
+            GNGCallback(
-                        freq=self.hparams.insert_freq)
+                reduction=self.hparams.insert_reduction,
+                freq=self.hparams.insert_freq,
+            )
         ]

prototorch/models/vis.py

@@ -7,14 +7,19 @@ import torchvision
 from matplotlib import pyplot as plt
 from torch.utils.data import DataLoader, Dataset
 
+from ..utils.colors import get_colors, get_legend_handles
 from ..utils.utils import mesh2d
 
 
 class Vis2DAbstract(pl.Callback):
+
     def __init__(self,
-                 data,
+                 data=None,
                  title="Prototype Visualization",
                  cmap="viridis",
+                 xlabel="Data dimension 1",
+                 ylabel="Data dimension 2",
+                 legend_labels=None,
                  border=0.1,
                  resolution=100,
                  flatten_data=True,
@@ -27,24 +32,31 @@ class Vis2DAbstract(pl.Callback):
                  block=False):
         super().__init__()
 
-        if isinstance(data, Dataset):
+        if data:
-            x, y = next(iter(DataLoader(data, batch_size=len(data))))
+            if isinstance(data, Dataset):
-        elif isinstance(data, torch.utils.data.DataLoader):
+                x, y = next(iter(DataLoader(data, batch_size=len(data))))
-            x = torch.tensor([])
+            elif isinstance(data, torch.utils.data.DataLoader):
-            y = torch.tensor([])
+                x = torch.tensor([])
-            for x_b, y_b in data:
+                y = torch.tensor([])
-                x = torch.cat([x, x_b])
+                for x_b, y_b in data:
-                y = torch.cat([y, y_b])
+                    x = torch.cat([x, x_b])
+                    y = torch.cat([y, y_b])
+            else:
+                x, y = data
+
+            if flatten_data:
+                x = x.reshape(len(x), -1)
+
+            self.x_train = x
+            self.y_train = y
         else:
-            x, y = data
+            self.x_train = None
-
+            self.y_train = None
-        if flatten_data:
-            x = x.reshape(len(x), -1)
-
-        self.x_train = x
-        self.y_train = y
 
         self.title = title
+        self.xlabel = xlabel
+        self.ylabel = ylabel
+        self.legend_labels = legend_labels
         self.fig = plt.figure(self.title)
         self.cmap = cmap
         self.border = border
@@ -63,14 +75,12 @@ class Vis2DAbstract(pl.Callback):
                 return False
         return True
 
-    def setup_ax(self, xlabel=None, ylabel=None):
+    def setup_ax(self):
         ax = self.fig.gca()
         ax.cla()
         ax.set_title(self.title)
-        if xlabel:
+        ax.set_xlabel(self.xlabel)
-            ax.set_xlabel("Data dimension 1")
+        ax.set_ylabel(self.ylabel)
-        if ylabel:
-            ax.set_ylabel("Data dimension 2")
         if self.axis_off:
             ax.axis("off")
         return ax
@@ -113,42 +123,44 @@ class Vis2DAbstract(pl.Callback):
             else:
                 plt.show(block=self.block)
 
+    def on_epoch_end(self, trainer, pl_module):
+        if not self.precheck(trainer):
+            return True
+        self.visualize(pl_module)
+        self.log_and_display(trainer, pl_module)
+
     def on_train_end(self, trainer, pl_module):
         plt.close()
 
 
 class VisGLVQ2D(Vis2DAbstract):
-    def on_epoch_end(self, trainer, pl_module):
-        if not self.precheck(trainer):
-            return True
 
+    def visualize(self, pl_module):
         protos = pl_module.prototypes
         plabels = pl_module.prototype_labels
         x_train, y_train = self.x_train, self.y_train
-        ax = self.setup_ax(xlabel="Data dimension 1",
+        ax = self.setup_ax()
-                           ylabel="Data dimension 2")
-        self.plot_data(ax, x_train, y_train)
         self.plot_protos(ax, protos, plabels)
-        x = np.vstack((x_train, protos))
+        if x_train is not None:
-        mesh_input, xx, yy = mesh2d(x, self.border, self.resolution)
+            self.plot_data(ax, x_train, y_train)
+            mesh_input, xx, yy = mesh2d(np.vstack([x_train, protos]),
+                                        self.border, self.resolution)
+        else:
+            mesh_input, xx, yy = mesh2d(protos, self.border, self.resolution)
         _components = pl_module.proto_layer._components
         mesh_input = torch.from_numpy(mesh_input).type_as(_components)
         y_pred = pl_module.predict(mesh_input)
         y_pred = y_pred.cpu().reshape(xx.shape)
         ax.contourf(xx, yy, y_pred, cmap=self.cmap, alpha=0.35)
 
-        self.log_and_display(trainer, pl_module)
-
 
 class VisSiameseGLVQ2D(Vis2DAbstract):
+
     def __init__(self, *args, map_protos=True, **kwargs):
         super().__init__(*args, **kwargs)
         self.map_protos = map_protos
 
-    def on_epoch_end(self, trainer, pl_module):
+    def visualize(self, pl_module):
-        if not self.precheck(trainer):
-            return True
-
         protos = pl_module.prototypes
         plabels = pl_module.prototype_labels
         x_train, y_train = self.x_train, self.y_train
@@ -175,18 +187,42 @@ class VisSiameseGLVQ2D(Vis2DAbstract):
         y_pred = y_pred.cpu().reshape(xx.shape)
         ax.contourf(xx, yy, y_pred, cmap=self.cmap, alpha=0.35)
 
-        self.log_and_display(trainer, pl_module)
+
+class VisGMLVQ2D(Vis2DAbstract):
+
+    def __init__(self, *args, ev_proj=True, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.ev_proj = ev_proj
+
+    def visualize(self, pl_module):
+        protos = pl_module.prototypes
+        plabels = pl_module.prototype_labels
+        x_train, y_train = self.x_train, self.y_train
+        device = pl_module.device
+        omega = pl_module._omega.detach()
+        lam = omega @ omega.T
+        u, _, _ = torch.pca_lowrank(lam, q=2)
+        with torch.no_grad():
+            x_train = torch.Tensor(x_train).to(device)
+            x_train = x_train @ u
+            x_train = x_train.cpu().detach()
+        if self.show_protos:
+            with torch.no_grad():
+                protos = torch.Tensor(protos).to(device)
+                protos = protos @ u
+                protos = protos.cpu().detach()
+        ax = self.setup_ax()
+        self.plot_data(ax, x_train, y_train)
+        if self.show_protos:
+            self.plot_protos(ax, protos, plabels)
 
 
 class VisCBC2D(Vis2DAbstract):
-    def on_epoch_end(self, trainer, pl_module):
-        if not self.precheck(trainer):
-            return True
 
+    def visualize(self, pl_module):
         x_train, y_train = self.x_train, self.y_train
         protos = pl_module.components
-        ax = self.setup_ax(xlabel="Data dimension 1",
+        ax = self.setup_ax()
-                           ylabel="Data dimension 2")
         self.plot_data(ax, x_train, y_train)
         self.plot_protos(ax, protos, "w")
         x = np.vstack((x_train, protos))
@@ -198,20 +234,15 @@ class VisCBC2D(Vis2DAbstract):
 
         ax.contourf(xx, yy, y_pred, cmap=self.cmap, alpha=0.35)
 
-        self.log_and_display(trainer, pl_module)
-
 
 class VisNG2D(Vis2DAbstract):
-    def on_epoch_end(self, trainer, pl_module):
-        if not self.precheck(trainer):
-            return True
 
+    def visualize(self, pl_module):
         x_train, y_train = self.x_train, self.y_train
         protos = pl_module.prototypes
         cmat = pl_module.topology_layer.cmat.cpu().numpy()
 
-        ax = self.setup_ax(xlabel="Data dimension 1",
+        ax = self.setup_ax()
-                           ylabel="Data dimension 2")
         self.plot_data(ax, x_train, y_train)
         self.plot_protos(ax, protos, "w")
 
@@ -225,10 +256,27 @@ class VisNG2D(Vis2DAbstract):
                         "k-",
                     )
 
-        self.log_and_display(trainer, pl_module)
+
+class VisSpectralProtos(Vis2DAbstract):
+
+    def visualize(self, pl_module):
+        protos = pl_module.prototypes
+        plabels = pl_module.prototype_labels
+        ax = self.setup_ax()
+        colors = get_colors(vmax=max(plabels), vmin=min(plabels))
+        for p, pl in zip(protos, plabels):
+            ax.plot(p, c=colors[int(pl)])
+        if self.legend_labels:
+            handles = get_legend_handles(
+                colors,
+                self.legend_labels,
+                marker="lines",
+            )
+            ax.legend(handles=handles)
 
 
 class VisImgComp(Vis2DAbstract):
+
     def __init__(self,
                  *args,
                  random_data=0,
@@ -251,8 +299,6 @@ class VisImgComp(Vis2DAbstract):
                                    size=self.embedding_data,
                                    replace=False)
             data = self.x_train[ind]
-            # print(f"{data.shape=}")
-            # print(f"{self.y_train[ind].shape=}")
             tb.add_embedding(data.view(len(ind), -1),
                              label_img=data,
                              global_step=None,
@@ -283,14 +329,9 @@ class VisImgComp(Vis2DAbstract):
             dataformats=self.dataformats,
         )
 
-    def on_epoch_end(self, trainer, pl_module):
+    def visualize(self, pl_module):
-        if not self.precheck(trainer):
-            return True
-
         if self.show:
             components = pl_module.components
             grid = torchvision.utils.make_grid(components,
                                                nrow=self.num_columns)
             plt.imshow(grid.permute((1, 2, 0)).cpu(), cmap=self.cmap)
-
-        self.log_and_display(trainer, pl_module)

setup.cfg

@@ -1,8 +1,23 @@
-[isort]
-profile = hug
-src_paths = isort, test
-
 [yapf]
 based_on_style = pep8
 spaces_before_comment = 2
 split_before_logical_operator = true
+
+[pylint]
+disable =
+	too-many-arguments,
+	too-few-public-methods,
+	fixme,
+
+
+[pycodestyle]
+max-line-length = 79
+
+[isort]
+profile = hug
+src_paths = isort, test
+multi_line_output = 3
+include_trailing_comma = True
+force_grid_wrap = 3
+use_parentheses = True
+line_length = 79

setup.py

@@ -22,8 +22,8 @@ with open("README.md", "r") as fh:
     long_description = fh.read()
 
 INSTALL_REQUIRES = [
-    "prototorch>=0.6.0",
+    "prototorch>=0.7.3",
-    "pytorch_lightning>=1.3.5",
+    "pytorch_lightning>=1.6.0",
     "torchmetrics",
 ]
 CLI = [
@@ -37,6 +37,7 @@ DOCS = [
     "recommonmark",
     "sphinx",
     "nbsphinx",
+    "ipykernel",
     "sphinx_rtd_theme",
     "sphinxcontrib-katex",
     "sphinxcontrib-bibtex",
@@ -53,7 +54,7 @@ ALL = CLI + DEV + DOCS + EXAMPLES + TESTS
 
 setup(
     name=safe_name("prototorch_" + PLUGIN_NAME),
-    version="0.2.0",
+    version="0.5.0",
     description="Pre-packaged prototype-based "
     "machine learning models using ProtoTorch and PyTorch-Lightning.",
     long_description=long_description,
@@ -63,7 +64,7 @@ setup(
     url=PROJECT_URL,
     download_url=DOWNLOAD_URL,
     license="MIT",
-    python_requires=">=3.9",
+    python_requires=">=3.7",
     install_requires=INSTALL_REQUIRES,
     extras_require={
         "dev": DEV,
@@ -79,7 +80,10 @@ setup(
         "Intended Audience :: Science/Research",
         "License :: OSI Approved :: MIT License",
         "Natural Language :: English",
+        "Programming Language :: Python :: 3.10",
         "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.8",
+        "Programming Language :: Python :: 3.7",
         "Operating System :: OS Independent",
         "Topic :: Scientific/Engineering :: Artificial Intelligence",
         "Topic :: Software Development :: Libraries",

tests/test_.py

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

tests/test_examples.sh

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

tests/test_models.py

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