Focalnet Huge Fl4.ms In22k

🚀 focalnet_huge_fl4.ms_in22k 模型卡片

这是一个FocalNet图像分类模型，由论文作者在ImageNet - 22k数据集上进行了预训练，可用于图像分类和特征提取等任务。

🚀 快速开始

本模型可用于图像分类、特征图提取和图像嵌入等任务。以下是具体的使用示例。

✨ 主要特性

• 模型类型：图像分类/特征主干网络
• 模型统计信息：
  • 参数数量（M）：686.5
  • GMACs：118.9
  • 激活值数量（M）：113.3
  • 图像尺寸：224 x 224
• 相关论文：
  • Focal Modulation Networks: https://arxiv.org/abs/2203.11926
• 原始代码库：https://github.com/microsoft/FocalNet
• 训练数据集：ImageNet - 22k

💻 使用示例

基础用法 - 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('focalnet_huge_fl4.ms_in22k', 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)

高级用法 - 特征图提取

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(
    'focalnet_huge_fl4.ms_in22k',
    pretrained=True,
    features_only=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

for o in output:
    # print shape of each feature map in output
    # e.g. for focalnet_base_srf: 
    #  torch.Size([1, 128, 56, 56])
    #  torch.Size([1, 256, 28, 28])
    #  torch.Size([1, 512, 14, 14])
    #  torch.Size([1, 1024, 7, 7])
    print(o.shape)

高级用法 - 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(
    'focalnet_huge_fl4.ms_in22k',
    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 (ie.e a (batch_size, num_features, H, W) tensor)

output = model.forward_head(output, pre_logits=True)
# output is (batch_size, num_features) tensor

📚 详细文档

可在timm 模型结果中查看本模型的数据集和运行时指标。

📄 许可证

本项目采用MIT许可证。

📖 引用

@misc{yang2022focal,
  title={Focal Modulation Networks}, 
  author={Jianwei Yang and Chunyuan Li and Xiyang Dai and Jianfeng Gao},
  journal={Advances in Neural Information Processing Systems (NeurIPS)},
  year={2022}
}

@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}}
}