Create app.py

app.py

@@ -0,0 +1,36 @@
+import gradio as gr
+import tensorflow as tf
+import numpy as np
+from tensorflow.keras.preprocessing import image
+import cv2
+
+# Load the trained model
+model = tf.keras.models.load_model("chest_xray_model.h5")
+class_labels = ["NORMAL", "PNEUMONIA"]  # Update if you have more classes
+
+# Preprocessing function for uploaded images
+def preprocess_image(img):
+    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+    img = cv2.resize(img, (150, 150)) / 255.0
+    img = np.expand_dims(img, axis=0)
+    return img
+
+# Prediction function
+def predict_chest_xray(img):
+    processed_img = preprocess_image(img)
+    prediction = model.predict(processed_img)[0]
+    predicted_class = class_labels[np.argmax(prediction)]
+    confidence = round(100 * np.max(prediction), 2)
+    return f"Prediction: {predicted_class} (Confidence: {confidence}%)"
+
+# Create Gradio UI
+interface = gr.Interface(
+    fn=predict_chest_xray,
+    inputs=gr.Image(type="numpy"),
+    outputs="text",
+    title="Chest X-Ray Diagnosis",
+    description="Upload a chest X-ray image to get a diagnosis prediction."
+)
+
+if __name__ == "__main__":
+    interface.launch()