resmlp_big_24_224.fb_in22k_ft_in1k 的模型卡片

一个用于图像分类的 ResMLP 模型。由论文作者在 ImageNet-22k 上进行预训练，并在 ImageNet-1k 上进行微调。

模型详细信息

• 模型类型：图像分类 / 特征骨干
• 模型统计信息：
  • 参数量 (M)：129.1
  • GMACs：100.2
  • 激活函数数量 (M)：87.3
  • 图像尺寸：224 x 224
• 相关论文：
  • ResMLP：用于图像分类的前馈网络及其高效数据训练： https://arxiv.org/abs/2105.03404
• 原始论文编号： https://github.com/facebookresearch/deit
• 数据集：ImageNet-1k
• 预训练数据集：ImageNet-21k

模型使用方式

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('resmlp_big_24_224.fb_in22k_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(
    'resmlp_big_24_224.fb_in22k_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, 784, 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 中探索此模型的数据集和运行时指标： model results

引用

@article{touvron2021resmlp,
  title={ResMLP: Feedforward networks for image classification with data-efficient training},
  author={Hugo Touvron and Piotr Bojanowski and Mathilde Caron and Matthieu Cord and Alaaeldin El-Nouby and Edouard Grave and Gautier Izacard and Armand Joulin and Gabriel Synnaeve and Jakob Verbeek and Herv'e J'egou},
  journal={arXiv preprint arXiv:2105.03404},
  year={2021},
}

@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}}
}