dinov2-small facebook

Type: model
Task: image-feature-extraction
Framework: transformers
Downloads: 4,664,473
Likes: 71
Access: public
Files: 0

Tags

视觉模型
图像特征提取
图像分类
计算机视觉
自监督学习
深度学习
transformers
PyTorch

README

--- license: apache-2.0 tags: - dino - vision --- # Vision Transformer (small-sized model) trained using DINOv2 Vision Transformer (ViT) model trained using the DINOv2 method. It was introduced in the paper [DINOv2: Learning Robust Visual Features without Supervision](https://arxiv.org/abs/2304.071…

查看完整页面 · 查看原文