facebook
/
timesformer-hr-finetuned-ssv2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix a typo in code snippet (#2) 

- fix a typo in code snippet (3753aeee87a9b3b11c8e4fcff74f0c824a4cafed)
- Update README.md (048d3c90f3f8c5343255801578a89ee6e1caad71)


Co-authored-by: Fatih <fcakyon@users.noreply.huggingface.co>
This commit is contained in:
Niels Rogge 2022-12-06 08:17:01 +00:00 committed by system
parent 113f762324
commit eed8700e24
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -20,16 +20,16 @@ You can use the raw model for video classification into one of the 174 possible
Here is how to use this model to classify a video: Here is how to use this model to classify a video:
```python ```python
from transformers import TimesformerFeatureExtractor, TimesformerForVideoClassification from transformers import AutoImageProcessor, TimesformerForVideoClassification
import numpy as np import numpy as np
import torch import torch
video = list(np.random.randn(16, 3, 448, 448)) video = list(np.random.randn(16, 3, 448, 448))
feature_extractor = TimesformerFeatureExtractor.from_pretrained("facebook/timesformer-hr-finetuned-ssv2") processor = AutoImageProcessor.from_pretrained("facebook/timesformer-hr-finetuned-ssv2")
model = TimesformerForVideoClassification.from_pretrained("facebook/timesformer-hr-finetuned-ssv22") model = TimesformerForVideoClassification.from_pretrained("facebook/timesformer-hr-finetuned-ssv2")
inputs = feature_extractor(video, return_tensors="pt") inputs = feature_extractor(images=video, return_tensors="pt")
with torch.no_grad(): with torch.no_grad():
outputs = model(**inputs) outputs = model(**inputs)