Update app.py

app.py

@@ -2,95 +2,55 @@ import gradio as gr
 import tensorflow as tf
 import numpy as np
 from PIL import Image
-import google.generativeai as genai 
+import google.generativeai as genai
 import os
 import markdown2
 
-# Load the TensorFlow model
-model_path = 'model'
-model = tf.saved_model.load(model_path)
-
-# Configure Gemini API
-api_key = os.getenv("GOOGLE_API_KEY") 
-api_key = "AIzaSyClC-moPGp4ONPUQ0FnNjMPh035AN7oqtY"  
-
-genai.configure(api_key=api_key)
-
-
+# Load TensorFlow model
+model = tf.saved_model.load('model')
 labels = ['cataract', 'diabetic_retinopathy', 'glaucoma', 'normal']
 
-def get_disease_detail(disease_name):
-    if disease_name == "normal":
-        prompt = (
-            "Create a text that congratulates having healthy eyes and gives bullet point tips to keep eyes healthy."
-        )
-    else:
-        prompt = (
-            f"Diagnosis: {disease_name}\n\n"
-            "What is it?\n(Description about {disease_name})\n\n"
-            "What causes it?\n(Explain what causes {disease_name})\n\n"
-            "Suggestion\n(Suggestion to user)\n\n"
-            "Reminder: Always seek professional help, such as a doctor."
-        )
+# Configure Gemini API
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+
+# Generate AI-based explanation for the predicted disease
+def get_disease_detail(disease):
+    prompt = (
+        "Create a text congratulating on healthy eyes with tips to keep them healthy."
+        if disease == "normal" else
+        f"Diagnosis: {disease}\n\n"
+        f"What is {disease}?\nCauses and suggestions to prevent {disease}."
+    )
     try:
         response = genai.GenerativeModel("gemini-1.5-flash").generate_content(prompt)
-        return markdown2.markdown(response.text.strip())
+        return markdown2.markdown(response.text.strip() if response and response.text else "No response.")
     except Exception as e:
         return f"Error: {e}"
 
+# Process and predict uploaded image
 def predict_image(image):
-    image_resized = image.resize((224, 224))
-    image_array = np.array(image_resized).astype(np.float32) / 255.0
-    image_array = np.expand_dims(image_array, axis=0)
-
-    predictions = model.signatures['serving_default'](tf.convert_to_tensor(image_array, dtype=tf.float32))['output_0']
-    
-    # Highest prediction
-    top_index = np.argmax(predictions.numpy(), axis=1)[0]
-    top_label = labels[top_index]
-    top_probability = predictions.numpy()[0][top_index]
+    img_array = np.expand_dims(np.array(image.resize((224, 224))).astype(np.float32) / 255.0, axis=0)
+    predictions = model.signatures['serving_default'](tf.convert_to_tensor(img_array, dtype=tf.float32))['output_0']
 
+    top_label = labels[np.argmax(predictions.numpy())]
     explanation = get_disease_detail(top_label)
 
-    return {top_label: top_probability}, explanation
+    return {top_label: predictions.numpy().max()}, explanation
 
 # Example images
-example_images = [
-    ["exp_eye_images/0_right_h.png"],
-    ["exp_eye_images/03fd50da928d_dr.png"],
-    ["exp_eye_images/108_right_h.png"],
-    ["exp_eye_images/1062_right_c.png"],
-    ["exp_eye_images/1084_right_c.png"],
-    ["exp_eye_images/image_1002_g.jpg"]
-]
-
-# Custom CSS for HTML height
-css = """
-.scrollable-html {
-    height: 206px;
-    overflow-y: auto;  
-    border: 1px solid #ccc;  
-    padding: 10px;  
-    box-sizing: border-box;
-}
-"""
+example_images = [[f"exp_eye_images/{img}"] for img in ["0_right_h.png", "03fd50da928d_dr.png", "108_right_h.png", "1062_right_c.png", "1084_right_c.png", "image_1002_g.jpg"]]
 
 # Gradio Interface
 interface = gr.Interface(
     fn=predict_image,
     inputs=gr.Image(type="pil"),
-    outputs=[
-        gr.Label(num_top_classes=1, label="Prediction"), 
-        gr.HTML(label="Explanation", elem_classes=["scrollable-html"])
-    ],
+    outputs=[gr.Label(num_top_classes=1, label="Prediction"), gr.HTML(label="Explanation", elem_classes=["scrollable-html"])],
     examples=example_images,
-    title="DR PREDICTOR",
-    description=(
-        "Upload an image of an eye fundus, and the model will predict it.\n\n"
-        "**Disclaimer:** This model is intended as a form of learning process in the field of health-related machine learning and was trained with a limited amount and variety of data with a total of about 4000 data, so the prediction results may not always be correct. There is still a lot of room for improvisation on this model in the future."
-    ),
+    title="DR Predictor",
+    description=("Upload an eye fundus image, and the model predicts the condition. This model is for educational use only."),
     allow_flagging="never",
-    css=css
+    css=".scrollable-html {height: 206px; overflow-y: auto; border: 1px solid #ccc; padding: 10px; box-sizing: border-box;}"
 )
 
 interface.launch(share=True)
+