Merge pull request #223 from tatsuookubo/master

Very minor typos in the type hint and text description

Author: vpj

labml_nn/diffusion/ddpm/unet.py

@@ -312,7 +312,7 @@ class UNet(Module):
 
     def __init__(self, image_channels: int = 3, n_channels: int = 64,
                  ch_mults: Union[Tuple[int, ...], List[int]] = (1, 2, 2, 4),
-                 is_attn: Union[Tuple[bool, ...], List[int]] = (False, False, True, True),
+                 is_attn: Union[Tuple[bool, ...], List[bool]] = (False, False, True, True),
                  n_blocks: int = 2):
         """
         * `image_channels` is the number of channels in the image. $3$ for RGB.

labml_nn/normalization/group_norm/readme.md

@@ -15,6 +15,6 @@ This is based on the observation that classical features such as
 The paper proposes dividing feature channels into groups and then separately normalizing
 all channels within each group.
 
-Here's a [CIFAR 10 classification model](https://nn.labml.ai/normalization/group_norm/experiment.html) that uses instance normalization.
+Here's a [CIFAR 10 classification model](https://nn.labml.ai/normalization/group_norm/experiment.html) that uses group normalization.
 
 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/normalization/group_norm/experiment.ipynb)