facebook
/
timesformer-base-finetuned-k400
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
Niels Rogge 2022-12-06 09:56:11 +00:00 committed by huggingface-web
parent 0c5eb2c860
commit b5dfd1b518
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -20,13 +20,13 @@ You can use the raw model for video classification into one of the 400 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 VideoMAEFeatureExtractor, TimesformerForVideoClassification from transformers import AutoImageProcessor, TimesformerForVideoClassification
import numpy as np import numpy as np
import torch import torch
video = list(np.random.randn(8, 3, 224, 224)) video = list(np.random.randn(8, 3, 224, 224))
feature_extractor = VideoMAEFeatureExtractor.from_pretrained("MCG-NJU/videomae-base-finetuned-kinetics") feature_extractor = AutoImageProcessor.from_pretrained("MCG-NJU/videomae-base-finetuned-kinetics")
model = TimesformerForVideoClassification.from_pretrained("facebook/timesformer-base-finetuned-k400") model = TimesformerForVideoClassification.from_pretrained("facebook/timesformer-base-finetuned-k400")
inputs = feature_extractor(video, return_tensors="pt") inputs = feature_extractor(video, return_tensors="pt")