Update app.py

app.py

@@ -1,20 +1,20 @@
-from fastai.vision.all import *
 import gradio as gr
+from fastai.vision.all import *
+import skimage
 
-# Load the trained model
 learn = load_learner('ripeorrotten_apple.pkl')
 
-# Define the prediction categories
-categories = ('ripe', 'rotten')
-
-# Define the prediction function
-def classify_image(img):
-    pred, idx, probs = learn.predict(img)
-    return dict(zip(categories, map(float, probs)))
-
-# Define the Gradio interface
-image = gr.inputs.Image(shape=(192, 192))
-label = gr.outputs.Label()
+labels = learn.dls.vocab
+def predict(img):
+    img = PILImage.create(img)
+    pred,pred_idx,probs = learn.predict(img)
+    return {labels[i]: float(probs[i]) for i in range(len(labels))}
+ 
+title = "Ripe or Rotten Apple Classifier"
+description = "A apple quality control classifier (AQCC) trained on web images with fastai."
+#article="<p style='text-align: center'><a href='https://tmabraham.github.io/blog/gradio_hf_spaces_tutorial' target='_blank'>Blog post</a></p>"
+examples = ['apple-fruit-ripe.jpg']
+interpretation='default'
+enable_queue=True
 
-intf = gr.Interface(fn=classify_image, inputs=image, outputs=label)
-intf.launch()
+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,interpretation=interpretation,enable_queue=enable_queue).launch()