Create app.py

app.py

@@ -0,0 +1,58 @@
+import gradio as gr
+import numpy as np
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing import image
+from PIL import Image
+# Fixed image URL
+fixed_image_url = "222.PNG"
+
+# Example images and their descriptions
+examples = [
+    ["Avulsion fracture.jpg", "Avulsion fracture."]
+# Load your trained model
+model = load_model("bone_break_classification_model.h5")
+
+# Define your class names dictionary
+class_names_dict = {
+    0: 'Avulsion fracture',
+    1: 'Comminuted fracture',
+    2: 'Fracture Dislocation',
+    3: 'Greenstick fracture',
+    4: 'Hairline Fracture',
+    5: 'Imapacted fracture',
+    6: 'Longitudinal fracture',
+    7: 'Oblique fracture',
+    8: 'Pathological fracture',
+    9: 'Spiral Fracture'
+}
+
+def predict_image(img_path):
+    # Load the image using PIL
+    img = Image.open(img_path)
+    img = img.resize((256, 256))  # Resize the image
+    img_array = np.array(img) / 255.0  # Normalize
+    img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension
+
+    # Make prediction
+    prediction = model.predict(img_array)
+    predicted_class_index = np.argmax(prediction, axis=-1)[0]
+    predicted_class_name = class_names_dict.get(predicted_class_index, "Unknown Class")
+
+    return predicted_class_name ,fixed_image_url
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=predict_image,
+    inputs=gr.Image(type="filepath", label="Upload an Image"),
+    outputs=[
+        gr.Textbox(label="Prediction"),
+        gr.Image(label=" Bone Fracture Detection ", value=fixed_image_url)  
+    ],
+    title="Bone Break Classification",
+    description="Upload an X-ray image, and the model will predict the type of bone break.",
+    theme="ParityError/Interstellar",
+    examples=examples,
+)
+
+# Launch the interface
+iface.launch(debug=True)