Create app.py

app.py

@@ -0,0 +1,44 @@
+import gradio as gr
+import pickle
+import cv2
+import numpy as np
+from skimage.transform import resize
+
+# Load the trained KNN model and class names
+with open("knn_model.pkl", "rb") as f:
+    knn_model = pickle.load(f)
+
+with open("class_names.pkl", "rb") as f:
+    class_names = pickle.load(f)
+
+# Image Preprocessing Function
+def preprocess_image(image):
+    """Resizes and flattens the image for model prediction."""
+    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)  # Convert RGB to BGR for OpenCV
+    image_resized = resize(image, (224, 224))  # Resize to match training size
+    image_flattened = image_resized.flatten().reshape(1, -1)  # Flatten to 1D
+    return image_flattened
+
+# Prediction Function
+def predict_animal(image):
+    """Predicts the class of the uploaded image."""
+    processed_image = preprocess_image(image)
+    prediction = knn_model.predict(processed_image)[0]
+    return f"Predicted Animal: {class_names[prediction]}"
+
+# Gradio UI
+title = "Animal Image Classifier 🐾"
+description = "Upload an image of an animal and click 'Identify' to predict the species."
+
+app = gr.Interface(
+    fn=predict_animal,
+    inputs=gr.Image(type="numpy"),
+    outputs="text",
+    title=title,
+    description=description,
+    theme="huggingface",
+)
+
+# Run the app
+if __name__ == "__main__":
+    app.launch()