google-research / big_vision
Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.
☆2,843Updated last month
Alternatives and similar repositories for big_vision:
Users that are interested in big_vision are comparing it to the libraries listed below
- Scenic: A Jax Library for Computer Vision Research and Beyond☆3,529Updated this week
- Grounded Language-Image Pre-training☆2,394Updated last year
- TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.☆1,591Updated this week
- EVA Series: Visual Representation Fantasies from BAAI☆2,479Updated 9 months ago
- ICLR2024 Spotlight: curation/training code, metadata, distribution and pre-trained models for MetaCLIP; CVPR 2024: MoDE: CLIP Data Expert…☆1,430Updated last month
- A method to increase the speed and lower the memory footprint of existing vision transformers.☆1,049Updated 10 months ago
- Efficient vision foundation models for high-resolution generation and perception.☆2,842Updated 2 weeks ago
- Hiera: A fast, powerful, and simple hierarchical vision transformer.☆979Updated last year
- A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)''☆1,288Updated last year
- 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (i…☆8,673Updated this week
- This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects.☆1,275Updated 2 weeks ago
- 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch☆2,128Updated 5 months ago
- ☆3,763Updated 2 months ago
- An open source implementation of CLIP.☆11,654Updated 2 weeks ago
- Official DeiT repository☆4,190Updated last year
- An open-source framework for training large multimodal models.☆3,906Updated 8 months ago
- A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.☆2,585Updated this week
- Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024☆1,502Updated 10 months ago
- Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence L…☆2,502Updated last year
- Code release for ConvNeXt V2 model☆1,719Updated 8 months ago
- VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and clou…☆3,201Updated last week
- Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch☆1,240Updated 2 years ago
- PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation☆5,224Updated 9 months ago
- 4M: Massively Multimodal Masked Modeling☆1,719Updated 2 months ago
- PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO☆6,817Updated 10 months ago
- Official repository for "AM-RADIO: Reduce All Domains Into One"☆1,141Updated 2 weeks ago
- Meta-Transformer for Unified Multimodal Learning☆1,595Updated last year
- [ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention☆849Updated last month
- Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.☆4,017Updated 9 months ago
- Awesome list for research on CLIP (Contrastive Language-Image Pre-Training).☆1,195Updated 10 months ago