Update app.py

app.py

@@ -1,27 +1,23 @@
-import os
-import numpy as np
 import streamlit as st
-from PIL import Image
 from tensorflow.keras.models import load_model
-from tensorflow.keras.preprocessing.image import img_to_array
-from huggingface_hub import notebook_login, hf_hub_download
-
+from tensorflow.keras.preprocessing.image import img_to_array  # Import this function
+from PIL import Image
+import numpy as np
+import os
+from huggingface_hub import hf_hub_download, login
 
 # Title of the Streamlit app
 st.title("Yellow Rust Severity Prediction")
 
-authkey= os.getenv('YellowRust')
-from huggingface_hub import login 
-
+# Authentication using Hugging Face token
+authkey = os.getenv('YellowRust')
 login(token=authkey)
 
-
 # Download the model file from Hugging Face
 model_path = hf_hub_download(repo_id="shaheer-data/Yellow-Rust-Prediction", filename="final_meta_model.keras")
 
-
-
-loaded_model = load_model(model_path)  # Load model using tf.keras directly
+# Load the pre-trained model
+loaded_model = load_model(model_path)
 
 # Function to preprocess the uploaded image
 def preprocess_image(image):
@@ -36,7 +32,7 @@ def preprocess_image(image):
 uploaded_file = st.file_uploader("Upload a wheat leaf image", type=["jpg", "jpeg", "png"])
 
 if uploaded_file is not None:
-    # Display the uploaded image
+    st.subheader("Uploaded Image")
     image = Image.open(uploaded_file)
     st.image(image, caption="Uploaded Image", use_container_width=True)
 
@@ -48,4 +44,28 @@ if uploaded_file is not None:
         prediction = loaded_model.predict(processed_image)
         predicted_class = np.argmax(prediction, axis=1)[0]  # Get the class index
         class_labels = ['0', 'MR', 'MRMS', 'MS', 'R', 'S']  # Update based on your classes
-        st.success(f"Predicted Severity Class: {class_labels[predicted_class]}")
+        
+        if predicted_class == 0:
+            st.write("Predicted Severity Class: Healthy")
+            st.write("**Advice:** The leaf appears healthy. Continue monitoring as needed.")
+        elif predicted_class == 1:
+            st.write("Predicted Severity Class: Mild Rust (MR)")
+            st.write("**Advice:** Apply fungicides to control mild rust development.")
+        elif predicted_class == 2:
+            st.write("Predicted Severity Class: Moderate Rust (MRMS)")
+            st.write("**Advice:** Monitor regularly and treat with appropriate fungicides.")
+        elif predicted_class == 3:
+            st.write("Predicted Severity Class: Severe Rust (MS)")
+            st.write("**Advice:** Apply fungicides promptly and continue monitoring.")
+        elif predicted_class == 4:
+            st.write("Predicted Severity Class: Very Severe Rust (R)")
+            st.write("**Advice:** Implement intensive control measures and frequent monitoring.")
+        elif predicted_class == 5:
+            st.write("Predicted Severity Class: Extremely Severe Rust (S)")
+            st.write("**Advice:** Apply aggressive control strategies and seek expert advice.")
+        
+        confidence = np.max(prediction) * 100
+        st.write(f"**Confidence Level:** {confidence:.2f}%")
+
+# Footer
+st.sidebar.info("Powered by Streamlit and TensorFlow")