Instructions to use openai/clip-vit-large-patch14-336 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/clip-vit-large-patch14-336 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="openai/clip-vit-large-patch14-336") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("openai/clip-vit-large-patch14-336") model = AutoModelForZeroShotImageClassification.from_pretrained("openai/clip-vit-large-patch14-336") - Notebooks
- Google Colab
- Kaggle
HuggingFace CLIP image preprocessing differs slightly from what's in CLIP repository
#9
by thadd3us - opened
This causes slight variation in the embeddings generated.
Here's a Google Colab demonstrating when I mean: https://colab.research.google.com/drive/1pPHiwHUnM3zmTLtMcNL2zTu2M6FdKtRK?usp=sharing
thadd3us changed discussion title from HuggingFace CLIP Preprocessing differs slightly from what's in CLIP repository to HuggingFace CLIP image preprocessing differs slightly from what's in CLIP repository