Update app.py

app.py

@@ -1,15 +1,24 @@
+# Import necessary libraries
 import gradio as gr
 from fastai.vision.all import *
 import skimage
 
+# Load a pre-trained deep learning model for image classification
 learn = load_learner('export.pkl')
 
+# Get the labels (classes) for the model's predictions
 labels = learn.dls.vocab
+
+# Define a function to make predictions on input images
 def predict(img):
+    # Create a PIL image from the input image
     img = PILImage.create(img)
+    # Use the loaded model to make predictions on the image
     pred,pred_idx,probs = learn.predict(img)
+    # Create a dictionary to map labels to their corresponding probabilities
     return {labels[i]: float(probs[i]) for i in range(len(labels))}
 
+# Set up the Gradio interface with relevant information
 title = "What's my Pet Breed?"
 description = "A pet breed classifier trained on the Oxford Pets dataset with fastai. Created as a demo for Gradio and HuggingFace Spaces."
 article="<p style='text-align: center'><a href='https://tmabraham.github.io/blog/gradio_hf_spaces_tutorial' target='_blank'>Blog post</a></p>"
@@ -17,4 +26,5 @@ examples = ['cat.jpeg']
 interpretation='default'
 enable_queue=True
 
+# Launch the Gradio interface with the predict function for image classification
 gr.Interface(fn=predict,inputs="image",outputs="label").launch()