Aimv2 Large Patch14 Native

🚀 AIMv2视觉模型库

AIMv2是一系列基于多模态自回归目标进行预训练的视觉模型，训练过程简单直接，可有效进行扩展。该模型在多模态理解基准测试、开放词汇目标检测等多个任务中表现出色。

🚀 快速开始

我们引入了通过多模态自回归目标进行预训练的AIMv2系列视觉模型。AIMv2的预训练过程简单直接，能够有效进行训练和扩展。AIMv2的一些亮点包括：

1. 在大多数多模态理解基准测试中，性能优于OAI CLIP和SigLIP。
2. 在开放词汇目标检测和指代表达理解任务中，性能优于DINOv2。
3. 展现出强大的识别性能，AIMv2 - 3B在使用冻结主干网络的情况下，在ImageNet上达到了*89.5%*的准确率。

💻 使用示例

基础用法

PyTorch

import requests
from PIL import Image
from transformers import AutoImageProcessor, AutoModel

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

processor = AutoImageProcessor.from_pretrained(
    "apple/aimv2-large-patch14-native",
)
model = AutoModel.from_pretrained(
    "apple/aimv2-large-patch14-native",
    trust_remote_code=True,
)

inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)

JAX

import requests
from PIL import Image
from transformers import AutoImageProcessor, FlaxAutoModel

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

processor = AutoImageProcessor.from_pretrained(
    "apple/aimv2-large-patch14-native",
)
model = FlaxAutoModel.from_pretrained(
    "apple/aimv2-large-patch14-native",
    trust_remote_code=True,
)

inputs = processor(images=image, return_tensors="jax")
outputs = model(**inputs)

📄 许可证

本项目采用apple-amlr许可证。

📚 详细文档

[AIMv2论文] [BibTeX]

📚 引用

如果您觉得我们的工作有用，请考虑按以下方式引用：

@misc{fini2024multimodalautoregressivepretraininglarge,
  author      = {Fini, Enrico and Shukor, Mustafa and Li, Xiujun and Dufter, Philipp and Klein, Michal and Haldimann, David and Aitharaju, Sai and da Costa, Victor Guilherme Turrisi and Béthune, Louis and Gan, Zhe and Toshev, Alexander T and Eichner, Marcin and Nabi, Moin and Yang, Yinfei and Susskind, Joshua M. and El-Nouby, Alaaeldin},
  url         = {https://arxiv.org/abs/2411.14402},
  eprint      = {2411.14402},
  eprintclass = {cs.CV},
  eprinttype  = {arXiv},
  title       = {Multimodal Autoregressive Pre-training of Large Vision Encoders},
  year        = {2024},
}

📦 模型信息