Create app.py

app.py

@@ -0,0 +1,37 @@
+import streamlit as st
+import numpy as np
+import pickle
+from tensorflow.keras.applications.mobilenet_v2 import MobileNetV2, preprocess_input
+from tensorflow.keras.preprocessing.image import img_to_array
+from tensorflow.keras.models import Model
+from PIL import Image
+
+# Load saved model and class names
+with open("knn_model.pkl", "rb") as f:
+    knn = pickle.load(f)
+
+with open("class_mapping.pkl", "rb") as f:
+    classes = pickle.load(f)
+
+# Load MobileNetV2 feature extractor
+base_model = MobileNetV2(weights="imagenet", include_top=False, pooling="avg", input_shape=(224, 224, 3))
+
+st.title("🐾 Animal Classifier using KNN & MobileNetV2")
+
+uploaded_file = st.file_uploader("Upload an animal image", type=["jpg", "jpeg", "png"])
+
+if uploaded_file is not None:
+    img = Image.open(uploaded_file).convert("RGB")
+    st.image(img, caption="Uploaded Image", use_column_width=True)
+
+    # Preprocess and extract features
+    img = img.resize((224, 224))
+    img_array = img_to_array(img)
+    img_array = preprocess_input(img_array)
+    features = base_model.predict(np.expand_dims(img_array, axis=0), verbose=0)
+    
+    # Predict using KNN
+    pred = knn.predict(features)[0]
+    predicted_class = classes[pred]
+
+    st.markdown(f"### 🔍 Predicted Class: `{predicted_class}`")