Image Classification
Transformers
LiteRT
ONNX
Safetensors
English
siglip
zero-shot-image-classification
vision
cervical-cancer
diagnosis
# Load model directly
from transformers import AutoProcessor, AutoModelForZeroShotImageClassification
processor = AutoProcessor.from_pretrained("KhanyiTapiwa00/medsiglip-diagnosis")
model = AutoModelForZeroShotImageClassification.from_pretrained("KhanyiTapiwa00/medsiglip-diagnosis", device_map="auto")Quick Links
🩺 MedSigLip Diagnosis Model
This repository contains MedSigLip, a deep learning model for cervical cancer image diagnosis.
It takes colposcopy images as input and predicts the most likely stage/class of the condition.
📊 Model Details
- Task: Image Classification
- Domain: Healthcare – Cervical Cancer Diagnosis
- Framework: Hugging Face Transformers / PyTorch
- Author: Khanyi Tapiwa Magagula (AI Eswatini)
🚀 Inference API
Once the Inference API is enabled, you can run predictions without any setup. Example:
from huggingface_hub import InferenceClient
# Replace with your repo name
client = InferenceClient("KhanyiTapiwa00/medsiglip-diagnosis")
# Run image classification
result = client.image_classification("1_10.jpg")
print(result)
- Downloads last month
- 55
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="KhanyiTapiwa00/medsiglip-diagnosis") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")