Dino Resnet 50

🚀 DINO ResNet-50

DINO ResNet-50 是使用 DINO 進行預訓練的 ResNet-50 模型。DINO 出自論文 Emerging Properties in Self-Supervised Vision Transformers，而 ResNet 則出自 Deep Residual Learning for Image Recognition。DINO ResNet-50 的官方實現可在 此處 找到。

本項目的權重是使用 此腳本 從官方 DINO ResNet 轉換而來。

有關最新的模型卡片信息，請參閱 原始倉庫。

🚀 快速開始

模型使用

⚠️ 重要提示

本倉庫中的特徵提取器是從 microsoft/resnet-50 複製而來。我們尚未驗證此圖像預處理方法是否適用於 DINO ResNet-50。

from transformers import AutoFeatureExtractor, ResNetModel
from PIL import Image
import requests

url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)

feature_extractor = AutoFeatureExtractor.from_pretrained('Ramos-Ramos/dino-resnet-50')
model = ResNetModel.from_pretrained('Ramos-Ramos/dino-resnet-50')
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
last_hidden_states = outputs.last_hidden_state

BibTeX 引用信息

@article{DBLP:journals/corr/abs-2104-14294,
  author    = {Mathilde Caron and
               Hugo Touvron and
               Ishan Misra and
               Herv{\'{e}} J{\'{e}}gou and
               Julien Mairal and
               Piotr Bojanowski and
               Armand Joulin},
  title     = {Emerging Properties in Self-Supervised Vision Transformers},
  journal   = {CoRR},
  volume    = {abs/2104.14294},
  year      = {2021},
  url       = {https://arxiv.org/abs/2104.14294},
  archivePrefix = {arXiv},
  eprint    = {2104.14294},
  timestamp = {Tue, 04 May 2021 15:12:43 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2104-14294.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{he2016deep,
  title={Deep residual learning for image recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={770--778},
  year={2016}
}

📄 信息表格