Sapiens - SEG - 0.6B - TorchScript open-source visual model, accurately handling human-centered visual tasks

Sapiens Seg 0.6b Torchscript

Developed by facebook

Sapiens is a family of vision Transformer models pre-trained on 300 million 1024x1024 resolution human images, focusing on human-centric vision tasks.

Image Segmentation English#High-Resolution Human Segmentation #28-Class Part Recognition #Synthetic Data Generalization

Downloads 25

Release Time : 9/9/2024

Model Overview

This model is used for 28-class human body part segmentation, supporting 1K high-resolution inference, and demonstrates exceptional generalization to real data even with scarce annotations or fully synthetic conditions.

Model Features

High-Resolution Support

Natively supports 1K high-resolution inference with an image size of 1024x768.

Strong Generalization

Demonstrates exceptional generalization to real data even with scarce annotations or fully synthetic conditions.

Large-Scale Pre-Training

Pre-trained on 300 million 1024x1024 resolution human images.

Model Capabilities

Human Image Segmentation

High-Resolution Image Processing

28-Class Body Part Recognition

Use Cases

Medical Imaging

Body Part Segmentation

Used for precise segmentation of human body parts in medical imaging.

Can recognize 28 classes of body parts

Virtual Reality

Virtual Avatar Creation

Used to create high-precision virtual human avatars.

🚀 Seg-Sapiens-0.6B-Torchscript

Seg-Sapiens-0.6B-Torchscript is a vision transformer model for image segmentation, pretrained on a large - scale human image dataset and capable of high - resolution inference.

🚀 Quick Start

This model is designed for image segmentation tasks, especially for human body part segmentation. It can efficiently handle high - resolution images and generalize well to real - world scenarios.

✨ Features

Sapiens is a family of vision transformers pretrained on 300 million human images at 1024 x 1024 image resolution. When finetuned for human - centric vision tasks, it can generalize to in - the - wild conditions.
Sapiens - 0.6B natively support 1K high - resolution inference. The models show remarkable generalization to in - the - wild data, even with scarce labeled data or entirely synthetic data.
The Seg 0.6B model can perform 28 - class body part segmentation on human images.

📚 Documentation

Model Details

Developed by: Meta
Model type: Vision Transformer
License: Creative Commons Attribution - NonCommercial 4.0
Task: seg
Format: torchscript
File: sapiens_0.6b_goliath_best_goliath_mIoU_7777_epoch_178_torchscript.pt2

Property	Details
Model Type	Vision Transformer
License	Creative Commons Attribution - NonCommercial 4.0
Task	seg
Format	torchscript
File	sapiens_0.6b_goliath_best_goliath_mIoU_7777_epoch_178_torchscript.pt2

Model Card

Property	Details
Image Size	1024 x 768 (H x W)
Num Parameters	0.664 B
FLOPs	2.583 TFLOPs
Patch Size	16 x 16
Embedding Dimensions	1280
Num Layers	32
Num Heads	16
Feedforward Channels	5120

More Resources

Repository: https://github.com/facebookresearch/sapiens
Paper: https://arxiv.org/abs/2408.12569
Demo: https://huggingface.co/spaces/facebook/sapiens-seg
Project Page: https://about.meta.com/realitylabs/codecavatars/sapiens
Additional Results: https://rawalkhirodkar.github.io/sapiens
HuggingFace Collection: https://huggingface.co/collections/facebook/sapiens-66d22047daa6402d565cb2fc

📄 License

This project is licensed under the Creative Commons Attribution - NonCommercial 4.0 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご