Views
No views yet
| 指标 | 数值 |
|---|---|
| Top-1 准确率 | 84.2% |
| 总类别数 | 31,770 |
| 参数量 | ~100M |
| 训练轮数 | 80 epochs |
pip install torch torchvision timm1import torch
2from timm.models import create_model
3
4# 加载模型
5model = create_model('lsnet_t_artist', pretrained=True, num_classes=31770)
6model.eval()
7
8# 推理
9with torch.no_grad():
10 output = model(input_tensor)
11 probabilities = torch.softmax(output, dim=1)1@misc{wang2025lsnetlargefocussmall,
2 title={LSNet: See Large, Focus Small},
3 author={Ao Wang and Hui Chen and Zijia Lin and Jungong Han and Guiguang Ding},
4 year={2025},
5 eprint={2503.23135},
6 archivePrefix={arXiv},
7 primaryClass={cs.CV},
8 url={https://arxiv.org/abs/2503.23135},
9}