fix: training loss is a zero dimensional tensor

Should fix the problem with EarlyStopping callback.

examples/cli/gmlvq.py

@@ -1,12 +1,11 @@
 """GMLVQ example using the MNIST dataset."""
 
-import torch
-from pytorch_lightning.utilities.cli import LightningCLI
-
 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):

examples/knn_iris.py

@@ -2,12 +2,11 @@
 
 import argparse
 
+import prototorch as pt
 import pytorch_lightning as pl
 import torch
 from sklearn.datasets import load_iris
 
-import prototorch as pt
-
 if __name__ == "__main__":
     # Command-line arguments
     parser = argparse.ArgumentParser()

prototorch/models/cbc.py

@@ -48,7 +48,7 @@ class CBC(SiameseGLVQ):
         y_pred = self(x)
         num_classes = self.num_classes
         y_true = torch.nn.functional.one_hot(y.long(), num_classes=num_classes)
-        loss = self.loss(y_pred, y_true).mean(dim=0)
+        loss = self.loss(y_pred, y_true).mean()
         return y_pred, loss
 
     def training_step(self, batch, batch_idx, optimizer_idx=None):

prototorch/models/data.py

@@ -5,13 +5,12 @@ 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
 
-import prototorch as pt
-
 
 # MNIST
 class MNISTDataModule(pl.LightningDataModule):

prototorch/models/glvq.py

@@ -58,7 +58,7 @@ class GLVQ(SupervisedPrototypeModel):
         plabels = self.proto_layer.labels
         mu = self.loss(out, y, prototype_labels=plabels)
         batch_loss = self.transfer_layer(mu, beta=self.hparams.transfer_beta)
-        loss = batch_loss.sum(dim=0)
+        loss = batch_loss.sum()
         return out, loss
 
     def training_step(self, batch, batch_idx, optimizer_idx=None):

prototorch/models/probabilistic.py

@@ -24,7 +24,7 @@ class CELVQ(GLVQ):
         winning = stratified_min_pooling(out, plabels)  # [None, num_classes]
         probs = -1.0 * winning
         batch_loss = self.loss(probs, y.long())
-        loss = batch_loss.sum(dim=0)
+        loss = batch_loss.sum()
         return out, loss
 
 
@@ -56,7 +56,7 @@ class ProbabilisticLVQ(GLVQ):
         out = self.forward(x)
         plabels = self.proto_layer.labels
         batch_loss = self.loss(out, y, plabels)
-        loss = batch_loss.sum(dim=0)
+        loss = batch_loss.sum()
         return loss
 
 
@@ -92,5 +92,5 @@ class PLVQ(ProbabilisticLVQ, SiameseGMLVQ):
     #     x, y = batch
     #     y_pred = self(x)
     #     batch_loss = self.loss(y_pred, y)
-    #     loss = batch_loss.sum(dim=0)
+    #     loss = batch_loss.sum()
     #     return loss

prototorch/models/unsupervised.py

@@ -132,7 +132,7 @@ class GrowingNeuralGas(NeuralGas):
         mask[torch.arange(len(mask)), winner] = 1.0
         dp = d * mask
 
-        self.errors += torch.sum(dp * dp, dim=0)
+        self.errors += torch.sum(dp * dp)
         self.errors *= self.hparams.step_reduction
 
         self.topology_layer(d)