Timesformer Hr Finetuned K400

🚀 TimeSformer（高分辨率变体，在Kinetics - 400上微调）

TimeSformer模型在Kinetics - 400数据集上进行了预训练。它由Tong等人在论文TimeSformer: Is Space - Time Attention All You Need for Video Understanding?中提出，并首次在此仓库发布。

免责声明：发布TimeSformer的团队未为此模型编写模型卡片，此模型卡片由fcakyon编写。

🚀 快速开始

你可以使用该原始模型将视频分类为400种可能的Kinetics - 400标签之一。

💻 使用示例

基础用法

from transformers import AutoImageProcessor, TimesformerForVideoClassification
import numpy as np
import torch

video = list(np.random.randn(16, 3, 448, 448))

processor = AutoImageProcessor.from_pretrained("facebook/timesformer-hr-finetuned-k400")
model = TimesformerForVideoClassification.from_pretrained("facebook/timesformer-hr-finetuned-k400")

inputs = processor(images=video, return_tensors="pt")

with torch.no_grad():
  outputs = model(**inputs)
  logits = outputs.logits

predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:", model.config.id2label[predicted_class_idx])

更多代码示例请参考文档。

📄 许可证

本模型采用CC - BY - NC - 4.0许可证。

📚 详细文档

BibTeX引用和引用信息

@inproceedings{bertasius2021space,
  title={Is Space-Time Attention All You Need for Video Understanding?},
  author={Bertasius, Gedas and Wang, Heng and Torresani, Lorenzo},
  booktitle={International Conference on Machine Learning},
  pages={813--824},
  year={2021},
  organization={PMLR}
}