README.md
| 1 | --- |
| 2 | license: "cc-by-nc-4.0" |
| 3 | tags: |
| 4 | - vision |
| 5 | - video-classification |
| 6 | --- |
| 7 | |
| 8 | # TimeSformer (base-sized model, fine-tuned on Kinetics-600) |
| 9 | |
| 10 | TimeSformer model pre-trained on [Kinetics-600](https://www.deepmind.com/open-source/kinetics). It was introduced in the paper [TimeSformer: Is Space-Time Attention All You Need for Video Understanding?](https://arxiv.org/abs/2102.05095) by Tong et al. and first released in [this repository](https://github.com/facebookresearch/TimeSformer). |
| 11 | |
| 12 | Disclaimer: The team releasing TimeSformer did not write a model card for this model so this model card has been written by [fcakyon](https://github.com/fcakyon). |
| 13 | |
| 14 | ## Intended uses & limitations |
| 15 | |
| 16 | You can use the raw model for video classification into one of the 600 possible Kinetics-600 labels. |
| 17 | |
| 18 | ### How to use |
| 19 | |
| 20 | Here is how to use this model to classify a video: |
| 21 | |
| 22 | ```python |
| 23 | from transformers import AutoImageProcessor, TimesformerForVideoClassification |
| 24 | import numpy as np |
| 25 | import torch |
| 26 | |
| 27 | video = list(np.random.randn(8, 3, 224, 224)) |
| 28 | |
| 29 | processor = AutoImageProcessor.from_pretrained("facebook/timesformer-base-finetuned-k600") |
| 30 | model = TimesformerForVideoClassification.from_pretrained("facebook/timesformer-base-finetuned-k600") |
| 31 | |
| 32 | inputs = processor(images=video, return_tensors="pt") |
| 33 | |
| 34 | with torch.no_grad(): |
| 35 | outputs = model(**inputs) |
| 36 | logits = outputs.logits |
| 37 | |
| 38 | predicted_class_idx = logits.argmax(-1).item() |
| 39 | print("Predicted class:", model.config.id2label[predicted_class_idx]) |
| 40 | ``` |
| 41 | |
| 42 | For more code examples, we refer to the [documentation](https://huggingface.co/transformers/main/model_doc/timesformer.html#). |
| 43 | |
| 44 | ### BibTeX entry and citation info |
| 45 | |
| 46 | ```bibtex |
| 47 | @inproceedings{bertasius2021space, |
| 48 | title={Is Space-Time Attention All You Need for Video Understanding?}, |
| 49 | author={Bertasius, Gedas and Wang, Heng and Torresani, Lorenzo}, |
| 50 | booktitle={International Conference on Machine Learning}, |
| 51 | pages={813--824}, |
| 52 | year={2021}, |
| 53 | organization={PMLR} |
| 54 | } |
| 55 | ``` |