Create app.py

app.py

@@ -0,0 +1,64 @@
+import os
+import streamlit as st
+import tensorflow as tf
+import numpy as np
+
+# Loading the saved model
+model = tf.keras.models.load_model('model.h5')
+
+def predict(input_image):
+    try:
+        # Preprocessing
+        input_image = tf.convert_to_tensor(input_image)
+        input_image = tf.image.resize(input_image, [224, 224])
+        input_image = tf.expand_dims(input_image, 0) / 255.0
+
+        # Prediction
+        predictions = model.predict(input_image)
+        labels = ['Cataract', 'Conjunctivitis', 'Glaucoma', 'Normal']
+
+        # Get confidence score for each class
+        disease_confidence = {label: np.round(predictions[0][idx] * 100, 3) for idx, label in enumerate(labels)}
+
+        # Get confidence percentage for the "Normal" class
+        normal_confidence = disease_confidence['Normal']
+
+        # Check if Normal confidence is greater than 50%
+        if normal_confidence > 50:
+            return f"""Congrats! no disease detected 
+            Normal with confidence: {normal_confidence}%"""
+
+
+        output_lines = [f"\n{disease}: {confidence}%" for disease, confidence in disease_confidence.items()]
+        output_string = "\n".join(output_lines[:-1])
+        return output_string
+
+
+    except Exception as e:
+        return f"An error occurred: {e}"
+
+# Example images directory
+examples = [os.path.join("example", file) for file in os.listdir("example")]
+
+# Streamlit app
+st.title("👁️ Eye Disease Detection")
+st.write("This model identifies common eye diseases such as Cataract, Conjunctivitis, and Glaucoma. Upload an eye image to see how the model classifies its condition.")
+
+uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "png"])
+
+if uploaded_file is not None:
+    # Display the uploaded image
+    image = tf.image.decode_image(uploaded_file.read(), channels=3)
+    image_np = image.numpy()
+    st.image(image_np, caption='Uploaded Image.', use_column_width=True)
+
+    # Perform prediction
+    prediction = predict(image_np)
+    st.write("Prediction:")
+    st.write(prediction)
+
+# Display examples images
+st.write("Examples:")
+cols = st.columns(len(examples))
+for idx, example in enumerate(examples):
+    cols[idx].image(example, caption=os.path.basename(example))