How to use google/vivit-b-16x2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("video-classification", model="google/vivit-b-16x2")
# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForVideoClassification processor = AutoImageProcessor.from_pretrained("google/vivit-b-16x2") model = AutoModelForVideoClassification.from_pretrained("google/vivit-b-16x2", device_map="auto")
SFconvertbot