feat: ImageGTLVQ and SiameseGTLVQ with examples

examples/gtlvq_mnist.py

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

@@ -24,79 +24,12 @@ if __name__ == "__main__":
                                                shuffle=True)
 
     # Hyperparameters
-    hparams = dict(distribution=[1, 3], input_dim=2, latent_dim=2)
+    # 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),
-        omega_initializer=-pt.initializers.PCALinearTransformInitializer(
-            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)
-"""Localized-GMLVQ 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
-    hparams = dict(distribution=[1, 3], input_dim=2, latent_dim=2)
-
-    # Initialize the model
-    model = pt.models.GTLVQ(
-        hparams,
-        prototypes_initializer=pt.initializers.SMCI(train_ds),
-        omega_initializer=-pt.initializers.PCALinearTransformInitializer(
-            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/siamese_gtlvq_iris.py

@@ -0,0 +1,72 @@
+"""Siamese GLVQ 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)