Create app.py

app.py

@@ -0,0 +1,48 @@
+import streamlit as st
+import joblib
+import numpy as np
+from PIL import Image
+from tensorflow.keras.preprocessing.image import load_img, img_to_array
+from tensorflow.keras.applications.resnet50 import ResNet50, preprocess_input
+
+# Load the trained KNN model and class names
+knn = joblib.load('knn_model.pkl')  # Replace with the correct path
+class_names = joblib.load('class_names.pkl')  # Replace with the correct path
+
+# Function to extract features using ResNet50
+def extract_features(img):
+    # Load the pre-trained ResNet50 model (without the top layer)
+    model = ResNet50(weights='imagenet', include_top=False, pooling='avg')
+    # Extract features from the image
+    features = model.predict(img)
+    return features
+
+# Streamlit app title
+st.title("Animal Classification App")
+
+# Description of the app
+st.write("This app classifies animals based on uploaded images using a trained KNN model.")
+
+# Upload image
+uploaded_file = st.file_uploader("Upload an image of an animal", type=["jpg", "jpeg", "png"])
+
+# Process the uploaded image and predict
+if uploaded_file is not None:
+    # Open the image and display it
+    image = Image.open(uploaded_file)
+    st.image(image, caption="Uploaded Image", use_column_width=True)
+
+    # Resize and preprocess the image
+    image = image.resize((224, 224))  # Resize the image to 224x224
+    img_array = img_to_array(image)  # Convert image to array
+    img_array = np.expand_dims(img_array, axis=0)  # Expand dimensions to match ResNet50 input
+    img_array = preprocess_input(img_array)  # Preprocess for ResNet50
+
+    # Extract features using ResNet50
+    features = extract_features(img_array)
+
+    # Predict using the trained KNN model
+    prediction = knn.predict(features)
+
+    # Display the predicted class
+    st.write(f"Prediction: {class_names[prediction[0]]}")