Classify and extract text 10x better and faster 🦾


➡️  Learn more

VisDial Dataset

Created by Das et al. at 2017, the VisDial Dataset contains images from COCO training set, and dialogues. Meant to be used for model to be trained in answering questions about images during conversation. Contains 1.2M dialog question-answers., in English language. Containing 1.2M in JSON file format.

Dataset Sources

Here you can download the VisDial dataset in JSON format.

Download VisDial dataset JSON files

Fine-tune with VisDial dataset

Metatext is a powerful no-code tool for train, tune and integrate custom NLP models

➡️  Learn more

Paper

Read full original VisDial paper.

Download PDF paper


Classify and extract text 10x better and faster 🦾

Metatext helps you to classify and extract information from text and documents with customized language models with your data and expertise.