Instructions to use microsoft/BiomedVLP-BioViL-T with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/BiomedVLP-BioViL-T with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="microsoft/BiomedVLP-BioViL-T", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("microsoft/BiomedVLP-BioViL-T", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
How to use this model for image classificaiton
Thanks for this amazing work. The description page states that this model can be used in image classification tasks. But, I couldn't figure out "how to use this model for image classification purposes". I want to train/fine-tune this model for CXR (edema, plural enfusion, cardiomegaly.... 15 classes) x-ray image classificaiton. Thanks
Hello, I have the same question. @murat-gunay , were you able to find an answer? Best.
@ozanoktay sorry for bothering you but I still couldn't figure out how to use this model as image classification
Hi both. I believe you can use something like this for zero-shot classification. You could also fine-tune the encoder if needed. Does that help?
Closing due to inactivity. Feel free to reopen if you need help.