scenic
Computer Vision Toolkit
A collection of libraries and projects focused on research around attention-based models for computer vision and beyond, providing optimized tools and baselines.
Scenic: A Jax Library for Computer Vision Research and Beyond
3k stars
39 watching
444 forks
Language: Python
last commit: almost 2 years agoLinked from 1 awesome list
attentioncomputer-visiondeep-learningjaxresearchtransformersvision-transformer
n2cholas/awesome-jaxRelated projects:
| Repository | Description | Stars |
|---|---|---|
| google-research/vision_transformer | Provides pre-trained models and code for training vision transformers and mixers using JAX/Flax | 10,620 |
 roboflow/notebooks | This repository contains tutorials and examples on using state-of-the-art computer vision models and techniques | 5,678 |
| google-research/big_vision | Supports large-scale vision model training on GPU machines or Google Cloud TPUs using scalable input pipelines. | 2,439 |
 jshilong/gpt4roi | Training and deploying large language models on computer vision tasks using region-of-interest inputs | 517 |
 uber-research/upsnet | Develops an instance segmentation and panoptic segmentation model for computer vision tasks. | 648 |
 haotian-liu/llava | A system that uses large language and vision models to generate and process visual instructions | 20,683 |
| google-research/cad-estate | A large dataset of 3D object and room layout annotations on RGB videos, designed to test automatic scene understanding methods. | 106 |
| google-research/big_transfer | Pre-trained models and code for fine-tuning image recognition tasks using deep learning frameworks | 1,516 |
 google/jaxopt | An open-source project providing hardware accelerated, batchable and differentiable optimizers in JAX for deep learning. | 941 |
 nexusapoorvacus/deepvariationstructuredrl | An implementation of reinforcement learning for visual relationship and attribute detection using PyTorch. | 63 |
 huggingface/transformers | A collection of pre-trained machine learning models for various natural language and computer vision tasks, enabling developers to fine-tune and deploy these models on their own projects. | 136,357 |
 deepseek-ai/deepseek-vl | A multimodal AI model that enables real-world vision-language understanding applications | 2,145 |
 rastapasta/react-native-gl-model-view | A React Native component that displays and animates 3D models loaded from Wavefront OBJ files. | 419 |
 vision-cair/minigpt-4 | Enabling vision-language understanding by fine-tuning large language models on visual data. | 25,490 |
 matthias-wright/flaxmodels | Provides pre-trained deep learning models for the Jax/Flax ecosystem. | 240 |