Create app.py

app.py

@@ -0,0 +1,30 @@
+def predict_input_image(img):
+    image_tensor = tf.convert_to_tensor(img)
+    # Resize the image to 28x28.
+    image_tensor = tf.image.resize(image_tensor, (224, 224))
+    # Cast the data to float32.
+    image_tensor = tf.cast(image_tensor, tf.float32)
+    # Add a batch dimension.
+    image_tensor = tf.expand_dims(image_tensor, 0)
+    # Normalize the data.
+    image_tensor = image_tensor / 255.0
+    
+    from keras.models import load_model
+    model = load_model('vgg16_model.h5')
+    
+    prediction = model.predict(image_tensor)[0]
+    
+    return {class_names[i]: float(prediction[i]) for i in range(4)}
+
+import gradio as gr
+
+demo = gr.Interface(fn = predict_input_image, 
+                    inputs = gr.Image(width = 224, height = 224), 
+                    outputs = gr.Label(num_top_classes = 4),
+                    title = 'A Eye: Eye Disease Classifier',
+                    description = 'This classifier is developed to classify cataracts, diabetic retinopathy, glaucoma and normal eyes through fundus images',
+                    cache_examples = False,
+                    allow_flagging = 'never',
+                   )
+
+demo.launch(debug='True')