From 7701add1fb68357f31f06c693e54dc3d6c767ad5 Mon Sep 17 00:00:00 2001 From: Merve Noyan Date: Tue, 6 Feb 2024 22:22:28 +0300 Subject: [PATCH] Update docs/source/en/tasks/mask_generation.md Co-authored-by: Maria Khalusova --- docs/source/en/tasks/mask_generation.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/en/tasks/mask_generation.md b/docs/source/en/tasks/mask_generation.md index 8bae4eb990fb01..06bfa0865dfaf5 100644 --- a/docs/source/en/tasks/mask_generation.md +++ b/docs/source/en/tasks/mask_generation.md @@ -142,7 +142,7 @@ processor = SamProcessor.from_pretrained("facebook/sam-vit-base") ``` You can do point prompting like below. Simply pass the input point to the processor. Take the processor output -and pass it to the model for inference. To postprocess the model output, we pass the outputs and +and pass it to the model for inference. To post-process the model output, pass the outputs and `original_sizes` and `reshaped_input_sizes` we take from the processor's initial output. We need to pass these since processor resizes the image, and the output needs to be extrapolated.