Instructions to use google/matcha-chartqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/matcha-chartqa with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="google/matcha-chartqa")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("google/matcha-chartqa") model = AutoModelForImageTextToText.from_pretrained("google/matcha-chartqa") - Notebooks
- Google Colab
- Kaggle
Possible to add several images as input and compare them?
#1
by pauljkathmann - opened
I am wondering if it is possible to use this model to input several images into the processor and ask the model to compare between the two charts? Or potentially to even combine the data from the two charts and overlay them onto a new chart?
E.g.: I want to compare the GDP growth of India and China over the last 20 years and have two graphs for the GDP for each country. Then I want to generate a new chart (or the code for it at least) where both of them are on the same chart and to answer the question which one grew faster.