🚀 focalnet_huge_fl4.ms_in22k 模型卡片
這是一個FocalNet圖像分類模型,由論文作者在ImageNet - 22k數據集上進行了預訓練,可用於圖像分類和特徵提取等任務。
🚀 快速開始
本模型可用於圖像分類、特徵圖提取和圖像嵌入等任務。以下是具體的使用示例。
✨ 主要特性
- 模型類型:圖像分類/特徵主幹網絡
- 模型統計信息:
- 參數數量(M):686.5
- GMACs:118.9
- 激活值數量(M):113.3
- 圖像尺寸:224 x 224
- 相關論文:
- Focal Modulation Networks: https://arxiv.org/abs/2203.11926
- 原始代碼庫:https://github.com/microsoft/FocalNet
- 訓練數據集:ImageNet - 22k
💻 使用示例
基礎用法 - 圖像分類
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()
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))
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
高級用法 - 特徵圖提取
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()
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))
for o in output:
print(o.shape)
高級用法 - 圖像嵌入
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,
)
model = model.eval()
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 = model.forward_features(transforms(img).unsqueeze(0))
output = model.forward_head(output, pre_logits=True)
📚 詳細文檔
可在timm 模型結果中查看本模型的數據集和運行時指標。
📄 許可證
本項目採用MIT許可證。
📖 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}}
}