模型:

facebook/timesformer-hr-finetuned-k600

英文

TimeSformer (基础大小模型,在Kinetics-600上微调)

TimeSformer模型是在 Kinetics-600 上进行预训练的。它是由Tong等人在 TimeSformer: Is Space-Time Attention All You Need for Video Understanding? 的论文中介绍,并于 this repository 首次发布的。

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

预期用途和限制

您可以使用原始模型将视频分类为600种可能的Kinetics-600标签之一。

如何使用

这是如何使用此模型对视频进行分类的示例:

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-k600")
model = TimesformerForVideoClassification.from_pretrained("facebook/timesformer-hr-finetuned-k600")

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])

如需更多代码示例,请参阅 documentation

BibTeX条目和引用信息

@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}
}