Instructions to use Salesforce/blip-image-captioning-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Salesforce/blip-image-captioning-large with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-large") model = AutoModelForImageTextToText.from_pretrained("Salesforce/blip-image-captioning-large") - Notebooks
- Google Colab
- Kaggle
Get reproducable image features
Hello, I am new at using ML models and am experiencing an issue with the BLIP model.
I want to use a pretrained BLIP model for image feature extraction. My goal is to see how the pretrained version works on my particular data. I do this using the get_image_features function. However when extracting feature vectors from images I get different feature vectors for the same image each time I run the feature extraction. How do I make the feature extraction reproducable? Also I get a warning saying that some weights from the Blip Model are not initialized, eventhough I am using the pretrained version ... I assume this is the source of my issue... How do I initialize the pretrained weights?
Thanks for any help!