Zero-Shot Image Classification
Transformers
English
medical
multimodal
vision-language pre-training
chest x-ray
Instructions to use pykale/MeDSLIP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pykale/MeDSLIP with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="pykale/MeDSLIP") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("pykale/MeDSLIP", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download PreTrain_MeDSLIP/scheduler/__init__.py from pykale/MeDSLIP: direct link, hf CLI and curl.
- Browser
- Download file 206 Bytes
-
https://huggingface.co/pykale/MeDSLIP/resolve/main/PreTrain_MeDSLIP/scheduler/__init__.py
- Command line
-
hf download hf://pykale/MeDSLIP/PreTrain_MeDSLIP/scheduler/__init__.py
-
curl -L -o __init__.py https://huggingface.co/pykale/MeDSLIP/resolve/main/PreTrain_MeDSLIP/scheduler/__init__.py
206 Bytes
| from .cosine_lr import CosineLRScheduler | |
| from .plateau_lr import PlateauLRScheduler | |
| from .step_lr import StepLRScheduler | |
| from .tanh_lr import TanhLRScheduler | |
| from .scheduler_factory import create_scheduler | |