diff --git a/prototorch/datasets/abstract.py b/prototorch/datasets/abstract.py
index 7817bb8..f38110b 100644
--- a/prototorch/datasets/abstract.py
+++ b/prototorch/datasets/abstract.py
@@ -1,4 +1,4 @@
-"""ProtoTorch abstract datasets
+"""ProtoTorch abstract dataset classes.
 
 Based on `torchvision.VisionDataset` and `torchvision.MNIST`
 
@@ -13,7 +13,7 @@ import torch
 
 
 class Dataset(torch.utils.data.Dataset):
-    """Abstract dataset class to be inherited"""
+    """Abstract dataset class to be inherited."""
     _repr_indent = 2
 
     def __init__(self, root):
@@ -29,7 +29,7 @@ class Dataset(torch.utils.data.Dataset):
 
 
 class ProtoDataset(Dataset):
-    """Abstract dataset class to be inherited"""
+    """Abstract dataset class to be inherited."""
     training_file = 'training.pt'
     test_file = 'test.pt'
 
diff --git a/prototorch/functions/activations.py b/prototorch/functions/activations.py
index 1ed141e..f394bc0 100644
--- a/prototorch/functions/activations.py
+++ b/prototorch/functions/activations.py
@@ -16,7 +16,7 @@ def register_activation(function):
 
 @register_activation
 # @torch.jit.script
-def identity(x, beta=torch.tensor([0])):
+def identity(x, beta=torch.tensor(0)):
     """Identity activation function.
 
     Definition:
@@ -27,7 +27,7 @@ def identity(x, beta=torch.tensor([0])):
 
 @register_activation
 # @torch.jit.script
-def sigmoid_beta(x, beta=torch.tensor([10])):
+def sigmoid_beta(x, beta=torch.tensor(10)):
     r"""Sigmoid activation function with scaling.
 
     Definition:
@@ -42,7 +42,7 @@ def sigmoid_beta(x, beta=torch.tensor([10])):
 
 @register_activation
 # @torch.jit.script
-def swish_beta(x, beta=torch.tensor([10])):
+def swish_beta(x, beta=torch.tensor(10)):
     r"""Swish activation function with scaling.
 
     Definition: