app.py

import gradio as gr
from transformers import ViTFeatureExtractor, ViTForImageClassification
from hugsvision.inference.VisionClassifierInference import VisionClassifierInference

# Load the pre-trained ViT model
path = "mrm8488/vit-base-patch16-224_finetuned-kvasirv2-colonoscopy"
classifier = VisionClassifierInference(
    feature_extractor=ViTFeatureExtractor.from_pretrained(path),
    model=ViTForImageClassification.from_pretrained(path),
)

# Define a Gradio interface
def classify_image(image_file):
    label = classifier.predict(img_path=image_file.name)
    return f"Predicted class: {label}"

iface = gr.Interface(
    fn=classify_image,
    inputs=gr.inputs.Image(type="filepath", label="Upload an image"),
    outputs="text",
    title="Image Classifier",
    description="Classify images using a pre-trained ViT model",
)

# Launch the Gradio app
iface.launch()