From 73c79f9ae35664c26422572782ea69dd8c24f4f4 Mon Sep 17 00:00:00 2001 From: Naomi Pentrel <5212232+npentrel@users.noreply.github.com> Date: Thu, 4 Sep 2025 20:17:39 +0200 Subject: [PATCH 1/2] DOCS-3387: Update tips for model training --- static/include/data/dataset-requirements.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/static/include/data/dataset-requirements.md b/static/include/data/dataset-requirements.md index dc610eb993..8e20d4a3d2 100644 --- a/static/include/data/dataset-requirements.md +++ b/static/include/data/dataset-requirements.md @@ -6,5 +6,5 @@ When you label your dataset, include: - images with and _without_ the categories you're looking to identify - a roughly equal number of images for each category -- images from your production environment, including lighting and camera quality +- images from your production environment, using the same backgrounds, lighting, camera quality, and focus - examples from every angle and distance that you expect the model to handle From 36768667e66922acfe798d8b39dbacead61d8d2d Mon Sep 17 00:00:00 2001 From: Naomi Pentrel <5212232+npentrel@users.noreply.github.com> Date: Fri, 5 Sep 2025 18:36:46 +0200 Subject: [PATCH 2/2] Update dataset-requirements.md --- static/include/data/dataset-requirements.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/static/include/data/dataset-requirements.md b/static/include/data/dataset-requirements.md index 8e20d4a3d2..28b8241ff2 100644 --- a/static/include/data/dataset-requirements.md +++ b/static/include/data/dataset-requirements.md @@ -1,4 +1,4 @@ -- At least 15 images +- At least 15 images, more images result in better models - At least 80% of the images have labels - For each training label, at least 10 examples