Create app.py

app.py

@@ -0,0 +1,39 @@
+import tensorflow as tf
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing import image
+import numpy as np
+import gradio as gr
+
+# ✅ Load the trained model
+model = load_model("lead_pipe_cnn.h5")
+
+# ✅ Define the same image size as during training
+IMG_SIZE = (256, 256)
+
+# ✅ Class names (adjust to your dataset labels)
+class_names = ['Lead', 'Non-Lead', 'Other']
+
+def predict(img):
+    # Convert to array
+    img = img.resize(IMG_SIZE)
+    img_array = image.img_to_array(img)
+    img_array = np.expand_dims(img_array, axis=0) / 255.0
+
+    # Make prediction
+    preds = model.predict(img_array)
+    pred_class = class_names[np.argmax(preds)]
+    confidence = np.max(preds) * 100
+
+    return {pred_class: float(confidence)}
+
+# ✅ Gradio UI
+demo = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="pil", label="Upload Pipe Image"),
+    outputs=gr.Label(num_top_classes=3, label="Prediction"),
+    title="PipeSense CNN - Lead Detection",
+    description="Upload an image of a pipe to detect if it's Lead or Non-Lead."
+)
+
+if __name__ == "__main__":
+    demo.launch()