mixer_b16_224.miil_in21k_ft_in1k的模型卡片

一种MLP-Mixer图像分类模型。在ImageNet-21k上进行预训练，并由 Alibaba-MIIL 进行ImageNet-1k的微调。

模型详情

• 模型类型：图像分类/特征骨干
• 模型统计：
  • 参数（M）：59.9
  • GMACs：12.6
  • 激活数（M）：14.5
  • 图像尺寸：224 x 224
• 论文：
  • MLP-Mixer：一种全MLP架构用于视觉： https://arxiv.org/abs/2105.01601
  • 面向大众的ImageNet-21K预训练： https://arxiv.org/abs/2104.10972
• 原作者： https://github.com/Alibaba-MIIL/ImageNet21K
• 数据集：ImageNet-1k
• 预训练数据集：ImageNet-21k

模型用途

图像分类

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('mixer_b16_224.miil_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)

图像嵌入

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(
    'mixer_b16_224.miil_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, 196, 768) shaped tensor

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

模型比较

在timm中探索该模型的数据集和运行时指标： model results

引用

@article{tolstikhin2021mixer,
  title={MLP-Mixer: An all-MLP Architecture for Vision},
  author={Tolstikhin, Ilya and Houlsby, Neil and Kolesnikov, Alexander and Beyer, Lucas and Zhai, Xiaohua and Unterthiner, Thomas and Yung, Jessica and Steiner, Andreas and Keysers, Daniel and Uszkoreit, Jakob and Lucic, Mario and Dosovitskiy, Alexey},
  journal={arXiv preprint arXiv:2105.01601},
  year={2021}
}

@misc{ridnik2021imagenet21k,
  title={ImageNet-21K Pretraining for the Masses}, 
  author={Tal Ridnik and Emanuel Ben-Baruch and Asaf Noy and Lihi Zelnik-Manor},
  year={2021},
  eprint={2104.10972},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

@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}}
}