Instructions to use microsoft/colipri with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- COLIPRI
How to use microsoft/colipri with COLIPRI:
pip install colipri
from colipri import get_model from colipri import get_processor from colipri import load_sample_ct from colipri import ZeroShotImageClassificationPipeline model = get_model().cuda() processor = get_processor() pipeline = ZeroShotImageClassificationPipeline("microsoft/colipri", processor) image = load_sample_ct() pipeline(image, ["No lung nodules", "Lung nodules"]) - Notebooks
- Google Colab
- Kaggle
Can i use it for report generation?
Thank you for the great work and for releasing this model 😀
According to the paper, report generation involves a decoder and processed CT–Finding pairs, but I couldn’t find those components in this release.
Do you have any plans to also publish them for report generation?
Thanks for your response!
I noticed that the English reports in the CT-RATE dataset were translated from Turkish using GPT-4o. Since the Hugging Face repository currently provides only the English versions, I was wondering where I could access the original Turkish reports that were used as the source for these translations.
Could you please let me know if the original Turkish data is available for download or where I might be able to find it?"