vit base patch8 224.augreg2 in21k ft in1k

提供商timm
分类image-classification
许可证apache-2.0
下载量1.8K
星标0

简介

这是一个基于 ViT-Base 架构的图像分类预训练模型，由 timm 库提供。它采用了 8x8 的 Patch 分割尺寸，并在 ImageNet-21k 大规模数据集上进行了预训练，随后在 ImageNet-1k 上进行了微调。相比于标准的 ViT，该版本通过增强正则化（augreg）提升了泛化能力。对于开发者而言，它是一个极佳的视觉特征提取底座，非常适合用于迁移学习，在处理复杂场景的图像识别或作为下游任务的 Encoder 时，性能通常优于直接从 1k 数据集训练的模型。

核心亮点

  • 基于 ImageNet-21k 预训练，特征表达能力强
  • 采用 8x8 Patch 尺寸，捕捉图像细节更精细
  • 通过增强正则化提升，模型泛化性能更稳健
  • timm 库原生支持，一行代码即可快速加载

使用方法

安装依赖
# 安装 Hugging Face transformers
pip install transformers torch
SDK 使用
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("timm/vit_base_patch8_224.augreg2_in21k_ft_in1k")
tokenizer = AutoTokenizer.from_pretrained("timm/vit_base_patch8_224.augreg2_in21k_ft_in1k")

Hugging Face 下载

我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 huggingface_hub：

操作指引 
pip install -U huggingface_hub

命令行下载

下载完整模型库

下载完整模型库 
huggingface-cli download timm/vit_base_patch8_224.augreg2_in21k_ft_in1k

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例）

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例） 
huggingface-cli download timm/vit_base_patch8_224.augreg2_in21k_ft_in1k config.json --local-dir ./dir

更多命令行下载选项，可参见官方文档

SDK 下载

SDK 下载 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('timm/vit_base_patch8_224.augreg2_in21k_ft_in1k')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://huggingface.co/timm/vit_base_patch8_224.augreg2_in21k_ft_in1k

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/timm/vit_base_patch8_224.augreg2_in21k_ft_in1k

模型文件托管在 Hugging Face Hub，使用 HF CLI / SDK / Git 直接下载，不经过本站。

PyTorch / Transformers 使用

安装 Transformers

安装 Transformers 
pip install -U transformers torch

模型加载和推理

模型加载和推理 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('timm/vit_base_patch8_224.augreg2_in21k_ft_in1k')
tokenizer = AutoTokenizer.from_pretrained('timm/vit_base_patch8_224.augreg2_in21k_ft_in1k')

模型下载

我们推荐使用命令行或者 ModelScope SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 ModelScope：

操作指引 
pip install modelscope

命令行下载

下载完整模型库

下载完整模型库 
modelscope download --model timm/vit_base_patch8_224.augreg2_in21k_ft_in1k

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例）

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例） 
modelscope download --model timm/vit_base_patch8_224.augreg2_in21k_ft_in1k README.md --local_dir ./dir

更多更丰富的命令行下载选项，可参见具体文档

SDK 下载

SDK 下载 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('timm/vit_base_patch8_224.augreg2_in21k_ft_in1k')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://www.modelscope.cn/timm/vit_base_patch8_224.augreg2_in21k_ft_in1k.git

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/timm/vit_base_patch8_224.augreg2_in21k_ft_in1k.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook 快速开发

下载并安装 ModelScope library

下载并安装 ModelScope library 
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

模型加载和推理

模型加载和推理 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'timm/vit_base_patch8_224.augreg2_in21k_ft_in1k')

完整文档

来源: HuggingFace

---
tags:

  • image-classification

  • timm

  • transformers

library_name: timm
license: apache-2.0
datasets:
  • imagenet-1k

  • imagenet-21k

---

Model card for vit_base_patch8_224.augreg2_in21k_ft_in1k

A Vision Transformer (ViT) image classification model. Trained on ImageNet-21k by paper authors and (re) fine-tuned on ImageNet-1k with additional augmentation and regularization by Ross Wightman.

Model Details

  • Model Type: Image classification / feature backbone
  • Model Stats:
- Params (M): 86.6 - GMACs: 66.9 - Activations (M): 65.7 - Image size: 224 x 224
  • Papers:
- How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers: https://arxiv.org/abs/2106.10270 - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
  • Dataset: ImageNet-1k
  • Pretrain Dataset: ImageNet-21k
  • Original: https://github.com/google-research/vision_transformer

Model Usage

Image Classification

python
from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))


model = timm.create_model('vit_base_patch8_224.augreg2_in21k_ft_in1k', pretrained=True)
model = model.eval()


get model specific transforms (normalization, resize)

data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1


top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)

Image Embeddings

python
from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))


model = timm.create_model(
    'vit_base_patch8_224.augreg2_in21k_ft_in1k',
    pretrained=True,
    num_classes=0,  # remove classifier nn.Linear
)
model = model.eval()


get model specific transforms (normalization, resize)

data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor


or equivalently (without needing to set num_classes=0)


output = model.forward_features(transforms(img).unsqueeze(0))
output is unpooled, a (1, 785, 768) shaped tensor


output = model.forward_head(output, pre_logits=True)
output is a (1, num_features) shaped tensor

Model Comparison

Explore the dataset and runtime metrics of this model in timm model results.

Citation

bibtex
@article{steiner2021augreg,
  title={How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers},
  author={Steiner, Andreas and Kolesnikov, Alexander and and Zhai, Xiaohua and Wightman, Ross and Uszkoreit, Jakob and Beyer, Lucas},
  journal={arXiv preprint arXiv:2106.10270},
  year={2021}
}
bibtex
@article{dosovitskiy2020vit,
  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
  author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and  Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
  journal={ICLR},
  year={2021}
}
bibtex
@misc{rw2019timm,
  author = {Ross Wightman},
  title = {PyTorch Image Models},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
查看官方来源