Update app.py

app.py

@@ -3,22 +3,27 @@ from fastai.vision.all import *
 import skimage
 
 learn = load_learner('export.pkl')
-
 labels = learn.dls.vocab
+
 def predict(img):
     img = PILImage.create(img)
-    pred,pred_idx,probs = learn.predict(img)
-    prediction = str(pred)
-    
-    return prediction
-
+    pred, pred_idx, probs = learn.predict(img)
+    return {labels[i]: float(probs[i]) for i in range(len(labels))}
 
 title = "Breast cancer detection with Deep Transfer Learning(ResNet18)."
-description = "<p style='text-align: center<p>"
-article="<p style='text-align: center'>Web app is built and managed by Addai Fosberg<b></p>"
+description = "<p style='text-align: center'><b>As a radiologist or oncologist, it is crucial to know what is wrong with a breast x-ray image.</b><br><b>Upload the breast X-ray image to know what is wrong with a patient's breast with or without implant. This product is from the findings of my (Team) published research paper: <a href='https://iopscience.iop.org/article/10.1088/2057-1976/ad3cdf' target='_blank' style='color: blue;'>read paper</a>. Learn more about me: <a href='https://www.linkedin.com/in/fosberg-addai-53a6991a7/' target='_blank' style='color: blue;'>Fosberg Addai</a></b></p>"
+article = "<p style='text-align: center'><b>Web app is built and managed by Addai Fosberg</b></p>"
 examples = ['img1.jpeg', 'img2.jpeg']
-enable_queue=True
 
-#interpretation='default'
+iface = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(shape=(512, 512)),
+    outputs=gr.Label(num_top_classes=3),
+    title=title,
+    description=description,
+    article=article,
+    examples=examples,
+    enable_queue=True
+)
 
-gr.Interface(fn=predict,inputs=gr.inputs.Image(shape=(512, 512)),outputs=gr.outputs.Label(num_top_classes=3),title=title,description=description,article=article,examples=examples,enable_queue=enable_queue).launch()
+iface.launch()