|
|
|
|
|
|
|
|
|
from fastai.vision.all import * |
|
import gradio as gr |
|
|
|
|
|
def is_pneumonia(x): |
|
return (x.find('virus')!=-1 or x.find('bacteria')!=-1) |
|
|
|
|
|
|
|
|
|
learn = load_learner('model.pkl') |
|
|
|
|
|
|
|
categories = ('Pneumonia', 'Normal') |
|
|
|
def predict(img): |
|
pred, idx, probs = learn.predict(img) |
|
return dict(zip(categories, map(float, probs))) |
|
|
|
|
|
title = "Pediatric Pneumonia or Normal Chest X-Ray Predictor" |
|
|
|
description = "A pediatric pneumonia or normal chest x-ray predictor model trained on the chest-xray-pneumonia dataset with fastai. The dataset is from: <a href='https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia' target='_blank'>Chest X-Ray Images (Pneumonia)</a> and the associated scientific journal paper is <a href='https://www.cell.com/cell/fulltext/S0092-8674(18)30154-5' target='_blank'>Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning</a>. The accuracy of the model is: 81.25%" |
|
|
|
|
|
article = "<p style='text-align: center'><span style='font-size: 15pt;'>Pediatric Pneumonia or Normal Chest X-Ray Predictor. Zakia Salod. 2022. </span></p>" |
|
|
|
|
|
image = gr.inputs.Image(shape=(512, 512)) |
|
label = gr.outputs.Label() |
|
examples = [ |
|
['person1_virus_6.jpeg'], |
|
['NORMAL2-IM-0285-0001.jpeg'], |
|
['person82_bacteria_404.jpeg'], |
|
['NORMAL2-IM-0373-0001.jpeg'], |
|
['person1618_virus_2805.jpeg'], |
|
['NORMAL2-IM-0381-0001.jpeg'], |
|
['person159_bacteria_747.jpeg'], |
|
['NORMAL2-IM-0222-0001.jpeg'], |
|
] |
|
interpretation = 'default' |
|
enable_queue = True |
|
|
|
|
|
|
|
|
|
iface = gr.Interface( |
|
fn=predict, |
|
title=title, |
|
description=description, |
|
article=article, |
|
inputs=image, |
|
outputs=label, |
|
theme="default", |
|
examples=examples, |
|
interpretation=interpretation, |
|
enable_queue=enable_queue |
|
) |
|
|
|
|
|
|
|
iface.launch(inline=False) |
|
|
