Create app.py

app.py

@@ -0,0 +1,44 @@
+import streamlit as st
+import tensorflow as tf
+from PIL import Image
+import numpy as np
+
+# Load your trained model
+@st.cache_resource
+def load_model():
+    model = tf.keras.models.load_model("ocular_model.h5")
+    return model
+
+model = load_model()
+
+# Define the class names (adjust this based on your specific model's output)
+CLASS_NAMES = ['No Diabetes', 'Diabetes']
+
+# Preprocess the image
+def preprocess_image(image: Image.Image):
+    image = image.resize((224, 224))  # Resize image to the expected input size
+    image = np.array(image) / 255.0  # Normalize to [0, 1]
+    image = np.expand_dims(image, axis=0)  # Add batch dimension
+    return image
+
+# Streamlit UI
+st.title("Ocular to Diabetes Prediction")
+st.write("Upload an image of an eye to predict the risk of diabetes.")
+
+# Uploading the image
+uploaded_file = st.file_uploader("Choose an eye image...", type=["jpg", "jpeg", "png"])
+
+if uploaded_file is not None:
+    # Load and display the image
+    image = Image.open(uploaded_file)
+    st.image(image, caption='Uploaded Image', use_column_width=True)
+    
+    # Preprocess and predict
+    st.write("Processing the image...")
+    image = preprocess_image(image)
+    predictions = model.predict(image)
+    score = tf.nn.softmax(predictions[0])
+
+    # Display prediction result
+    st.write(f"Prediction: {CLASS_NAMES[np.argmax(score)]}")
+    st.write(f"Confidence: {100 * np.max(score):.2f}%")