google-research-datasets / wit
WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.
☆1,047Updated 6 months ago
Alternatives and similar repositories for wit:
Users that are interested in wit are comparing it to the libraries listed below
- OpenAI CLIP text encoders for multiple languages!☆789Updated last year
- Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch☆1,237Updated 2 years ago
- A concise but complete implementation of CLIP with various experimental improvements from recent papers☆707Updated last year
- Code release for SLIP Self-supervision meets Language-Image Pre-training☆765Updated 2 years ago
- 🧀 Code and models for the ICML 2023 paper "Grounding Language Models to Images for Multimodal Inputs and Outputs".☆481Updated last year
- DataComp: In search of the next generation of multimodal datasets☆692Updated last year
- A PyTorch Lightning solution to training OpenAI's CLIP from scratch.☆686Updated 2 years ago
- Conceptual Captions is a dataset containing (image-URL, caption) pairs designed for the training and evaluation of machine learned image …☆535Updated 3 years ago
- Conceptual 12M is a dataset containing (image-URL, caption) pairs collected for vision-and-language pre-training.☆386Updated 2 years ago
- MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.☆925Updated 3 weeks ago
- Robust fine-tuning of zero-shot models☆690Updated 2 years ago
- COYO-700M: Large-scale Image-Text Pair Dataset☆1,209Updated 2 years ago
- NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations☆781Updated 10 months ago
- CLIP-like model evaluation☆686Updated 2 weeks ago
- ☆996Updated 2 years ago
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆861Updated last year
- Automatically create Faiss knn indices with the most optimal similarity search parameters.☆848Updated 10 months ago
- ☆501Updated last year
- Flexible components pairing 🤗 Transformers with Pytorch Lightning☆609Updated 2 years ago
- Implementation of CoCa, Contrastive Captioners are Image-Text Foundation Models, in Pytorch☆1,121Updated last year
- Library for Knowledge Intensive Language Tasks☆937Updated 3 years ago
- [ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decode…☆845Updated last year
- [CVPR 2021 Best Student Paper Honorable Mention, Oral] Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning…☆718Updated last year
- Run Effective Large Batch Contrastive Learning Beyond GPU/TPU Memory Constraint☆384Updated last year
- Oscar and VinVL☆1,047Updated last year
- GIT: A Generative Image-to-text Transformer for Vision and Language☆563Updated last year
- [ICLR 2022] code for "How Much Can CLIP Benefit Vision-and-Language Tasks?" https://arxiv.org/abs/2107.06383☆411Updated 2 years ago
- Multi Task Vision and Language☆811Updated 3 years ago
- Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm☆649Updated 2 years ago
- TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.☆1,569Updated this week