metadata
license: apache-2.0
Model Card for Model ID
This is a Swin Transformer model fine-tuned on the REFUGE challenge dataset. It is able to classify an retinal fundns image into glaucoma and non-glaucoma.
Model Details
Model Description
Model Sources [optional]
- Repository: [More Information Needed]
- Paper [optional]: [More Information Needed]
- Demo [optional]: [More Information Needed]
Uses
You can use the raw model for glaucoma classification based on retinal fundus images.
Bias, Risks, and Limitations
The model is trained/fine-tuned on retinal fundus images only, and was intended to classify glaucoma and non-glaucoma images. Thus please make sure to feed only fundus image into the model to obtain reasonable results.
How to Get Started with the Model
Use the code below to get started with the model.
from transformers import AutoImageProcessor, Swinv2ForImageClassification
import torch
from datasets import load_dataset
dataset = load_dataset("huggingface/cats-image")
image = dataset["test"]["image"][0]
processor = AutoImageProcessor.from_pretrained("pamixsun/swinv2_tiny_for_glaucoma_classification")
model = Swinv2ForImageClassification.from_pretrained("pamixsun/swinv2_tiny_for_glaucoma_classification")
inputs = processor(image, return_tensors="pt")
with torch.no_grad():
logits = model(**inputs).logits
# model predicts one of the 1000 ImageNet classes
predicted_label = logits.argmax(-1).item()
print(model.config.id2label[predicted_label])
Citation [optional]
BibTeX:
[More Information Needed]
APA:
[More Information Needed]