diff --git a/README.md b/README.md index c929e7ba..86dcf75f 100644 --- a/README.md +++ b/README.md @@ -38,7 +38,7 @@ ______________________________________________________________________ > object detection should not be more difficult than classification, and should not require complex libraries for training and inference. -`yolort` is very simple to implement and experiment with. You like the implementation of torchvision's faster-rcnn, retinanet or detr? You like yolov5? You love `yolort`! +`yolort` is very simple to implement and experiment with. Do you like the implementation of torchvision's faster-rcnn, retinanet or detr? Do you like yolov5? You'll love `yolort`! YOLO inference demo diff --git a/notebooks/inference-pytorch-export-libtorch.ipynb b/notebooks/inference-pytorch-export-libtorch.ipynb index 620194e3..d49e9781 100644 --- a/notebooks/inference-pytorch-export-libtorch.ipynb +++ b/notebooks/inference-pytorch-export-libtorch.ipynb @@ -235,7 +235,7 @@ "source": [ "## Detection output visualisation\n", "\n", - "First let get the labels of COCO datasets." + "First let's get the labels of COCO datasets." ] }, { diff --git a/yolort/models/transform.py b/yolort/models/transform.py index b951c417..20f4a7ac 100644 --- a/yolort/models/transform.py +++ b/yolort/models/transform.py @@ -180,7 +180,7 @@ def forward( if targets is not None: # make a copy of targets to avoid modifying it in-place # once torchscript supports dict comprehension - # this can be simplified as as follows + # this can be simplified as follows # targets = [{k: v for k,v in t.items()} for t in targets] targets_copy: List[Dict[str, Tensor]] = [] for t in targets: @@ -305,7 +305,7 @@ def max_by_axis(self, the_list: List[List[int]]) -> List[int]: def batch_images(self, images: List[Tensor]) -> Tensor: """ - Nest a list of tensors. It plays the same role of the lettebox function. + Nest a list of tensors. It plays the same role of the letterbox function. """ if torchvision._is_tracing():