Create app.py

app.py

@@ -0,0 +1,46 @@
+import streamlit as st
+from PIL import Image
+import requests
+from io import BytesIO
+import numpy as np
+from tensorflow.keras.models import load_model
+from tensorflow.keras.utils import img_to_array
+
+# Load the pre-trained model
+@st.cache_resource
+def load_animal_model():
+    model_url = "https://huggingface.co/shaktibiplab/Animal-Classification/resolve/main/best_model.weights.h5"
+    response = requests.get(model_url)
+    model_path = "best_model.weights.h5"
+    with open(model_path, "wb") as f:
+        f.write(response.content)
+    model = load_model(model_path)
+    return model
+
+model = load_animal_model()
+
+# Define class labels
+class_labels = ['cat', 'dog', 'horse', 'lion', 'tiger', 'elephant']
+
+# Streamlit app
+st.title("Animal Detection App")
+st.write("Upload an image to classify the animal.")
+
+uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
+
+if uploaded_file is not None:
+    image = Image.open(uploaded_file)
+    st.image(image, caption='Uploaded Image.', use_column_width=True)
+    st.write("Classifying...")
+    
+    # Preprocess the image
+    img = image.resize((256, 256))
+    img_array = img_to_array(img) / 255.0
+    img_array = np.expand_dims(img_array, axis=0)
+    
+    # Make prediction
+    predictions = model.predict(img_array)
+    predicted_class = class_labels[np.argmax(predictions)]
+    confidence = np.max(predictions)
+    
+    st.write(f"Prediction: {predicted_class} ({confidence:.2%} confidence)")