gallery: Fix typos

Author: ivysochyn

gallery/others/plot_optical_flow.py

@@ -134,7 +134,7 @@ def preprocess(img1_batch, img2_batch):
 # (N, 2, H, W) batch of predicted flows that corresponds to a given "iteration"
 # in the model. For more details on the iterative nature of the model, please
 # refer to the `original paper <https://arxiv.org/abs/2003.12039>`_. Here, we
-# are only interested in the final predicted flows (they are the most acccurate
+# are only interested in the final predicted flows (they are the most accurate
 # ones), so we will just retrieve the last item in the list.
 #
 # As described above, a flow is a tensor with dimensions (2, H, W) (or (N, 2, H,
@@ -151,7 +151,7 @@ def preprocess(img1_batch, img2_batch):
 # %%
 # Visualizing predicted flows
 # ---------------------------
-# Torchvision provides the :func:`~torchvision.utils.flow_to_image` utlity to
+# Torchvision provides the :func:`~torchvision.utils.flow_to_image` utility to
 # convert a flow into an RGB image. It also supports batches of flows.
 # each "direction" in the flow will be mapped to a given RGB color. In the
 # images below, pixels with similar colors are assumed by the model to be moving

gallery/v2_transforms/plot_custom_transforms.py

@@ -84,7 +84,7 @@ def forward(self, img, bboxes, label):  # we assume inputs are always structured
 # In the section above, we have assumed that you already know the structure of
 # your inputs and that you're OK with hard-coding this expected structure in
 # your code. If you want your custom transforms to be as flexible as possible,
-# this can be a bit limitting.
+# this can be a bit limiting.
 #
 # A key feature of the builtin Torchvision V2 transforms is that they can accept
 # arbitrary input structure and return the same structure as output (with