Update app.py

app.py

@@ -1,28 +1,34 @@
-import os
-os.environ["CUDA_VISIBLE_DEVICES"] = "-1"  # Disable GPU usage
 import gradio as gr
 import tensorflow as tf
 from tensorflow.keras.preprocessing import image
 import numpy as np
-from transformers import pipeline
+from PIL import Image
 
-# Load image classification model from Hugging Face
-model = pipeline("image-classification", model="icputrd/gelderman_decomposition_classification")
+# Load your trained Xception model
+model = tf.keras.models.load_model("your_xception_model.h5")
 
+# Define the labels for your classification (example: if you have 3 classes)
+class_labels = ['class1', 'class2', 'class3']  # Replace with your actual class names
 
 def classify_image(img):
-    # Preprocess the image
-    img = img.resize((299, 299))  # Resize to the input shape of Xception
-    img_array = image.img_to_array(img)  # Convert image to array
-    img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension
-    img_array /= 255.0  # Normalize the image
+    # Preprocess the image to fit the model input shape
+    img = img.resize((299, 299))  # Xception takes 299x299 input size
+    img = np.array(img) / 255.0   # Normalize the image
+    img = np.expand_dims(img, axis=0)
 
     # Make prediction
-    predictions = model.predict(img_array)
-    predicted_class = np.argmax(predictions, axis=-1)[0]  # Get the predicted class index
-    
-    return str(predicted_class)  # Return the class index as a string
+    predictions = model.predict(img)
+    predicted_class = np.argmax(predictions, axis=1)[0]
+    confidence = np.max(predictions)
+    return {class_labels[i]: float(predictions[0][i]) for i in range(len(class_labels))}, confidence
 
-# Gradio interface for image classification
-demo = gr.Interface(fn=classify_image, inputs=gr.inputs.Image(type="pil"), outputs="label")
-demo.launch()
+# Gradio interface
+demo = gr.Interface(
+    fn=classify_image,
+    inputs=gr.inputs.Image(type="pil"),
+    outputs=[gr.outputs.Label(num_top_classes=len(class_labels)), "number"],
+    live=True
+)
+
+if __name__ == "__main__":
+    demo.launch()