Text-to-Video
Transformers
PyTorch
Safetensors
clip
zero-shot-image-classification
text
vision
video
Instructions to use Searchium-ai/clip4clip-webvid150k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Searchium-ai/clip4clip-webvid150k with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("Searchium-ai/clip4clip-webvid150k") model = AutoModelForZeroShotImageClassification.from_pretrained("Searchium-ai/clip4clip-webvid150k", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Model Training on Custom dataset
#6 opened about 1 year ago
by
ZenithWisp
How the model processes multiple batches of videos simultaneously?
4
#5 opened almost 2 years ago
by
Crilias