mrdbourke/FoodExtract-1k-Vision download history

mrdbourke/FoodExtract-1k-Vision is an image text to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 128 times (43 in the last 7 days), and 2,317 times in total. It ranks #125,167 among datasets by monthly downloads.

FoodExtract-1k-Vision Dataset to practice fine-tuning VLM models. Goal: Extract food/drink items from an image in a structured format. Input: Image (e.g. PIL or similar) Output: JSON with the structure below Examples: Input: Image of a car (not food). { 'is_food': 0, 'image_titl

Models trained on FoodExtract-1k-Vision

4 models list it as training data.

Open mrdbourke/FoodExtract-1k-Vision on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.