How to use SeriYann/MicroscopyCLIP with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="SeriYann/MicroscopyCLIP") 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("SeriYann/MicroscopyCLIP") model = AutoModelForZeroShotImageClassification.from_pretrained("SeriYann/MicroscopyCLIP", device_map="auto")
Fine-tuned from openai/clip-vit-base-patch32 on microscopy image-text pairs (full-parameter fine-tuning).
openai/clip-vit-base-patch32
Files info
Base model
