Update app.py

app.py

@@ -0,0 +1,74 @@
+import streamlit as st
+import numpy as np
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing.image import img_to_array
+from PIL import Image, UnidentifiedImageError
+
+# 🔧 Configure Streamlit
+st.set_page_config(
+    page_title="Animal Classifier",
+    layout="centered",
+    initial_sidebar_state="auto"
+)
+
+# 📦 Load model and class labels
+@st.cache_resource
+def load_model_once():
+    return load_model("animal_model.keras")
+
+@st.cache_data
+def load_labels():
+    return np.load("class_labels.npy", allow_pickle=True).item()
+
+model = load_model_once()
+class_indices = load_labels()
+class_labels = list(class_indices.keys())
+
+# 🏷 App Title
+st.title("🐾 Animal Image Classifier")
+st.markdown("Upload up to **3 images** and get predictions")
+
+# 📤 Upload Images
+uploaded_files = st.file_uploader(
+    "Upload animal images",
+    type=["jpg", "jpeg", "png"],
+    accept_multiple_files=True
+)
+
+if uploaded_files:
+    uploaded_files = uploaded_files[:3]  # Limit to 3
+    cols = st.columns(len(uploaded_files))
+
+    for idx, uploaded_file in enumerate(uploaded_files):
+        with cols[idx]:
+            st.markdown(f"### Image {idx + 1}")
+            try:
+                # 🖼️ Load & preview image
+                image = Image.open(uploaded_file).convert("RGB")
+                preview = image.copy()
+                preview.thumbnail((150, 150))
+                st.image(preview, caption="Preview", use_container_width=True)
+
+                # 🧪 Preprocess image
+                resized = image.resize((128, 128))  # Adjust size as per your model
+                img_array = img_to_array(resized) / 255.0
+                img_array = np.expand_dims(img_array, axis=0)
+
+                # 🔮 Predict
+                preds = model.predict(img_array)[0]
+                top_indices = preds.argsort()[-3:][::-1]
+                top_labels = [class_labels[i] for i in top_indices]
+                top_scores = [preds[i] for i in top_indices]
+
+                # ✅ Display Predictions
+                st.success(f"**🔮 Top Prediction:** {top_labels[0].capitalize()}")
+                st.markdown("##### 📊 Top 3 Predictions:")
+                for label, score in zip(top_labels, top_scores):
+                    st.write(f"**{label.capitalize()}** — {score:.4f}")
+
+            except UnidentifiedImageError:
+                st.error("❌ Error: Invalid image file.")
+
+# 📌 Footer message
+st.sidebar.markdown("---")
+st.sidebar.markdown("Built with ❤️ using Streamlit and Keras.")