Update app.py

app.py

@@ -1,9 +1,8 @@
 import gradio as gr
 import torch
 from transformers import AutoImageProcessor, AutoModelForImageClassification
-from torchvision.transforms import Compose, Resize, ToTensor, Normalize
+from torchvision.transforms import Compose, Resize, ToTensor, Normalize,RandomHorizontalFlip, RandomRotation
 from PIL import Image
-import traceback
 
 # Load model and processor
 model_name = "riyadifirman/klasifikasiburung"
@@ -14,45 +13,28 @@ model = AutoModelForImageClassification.from_pretrained(model_name)
 normalize = Normalize(mean=processor.image_mean, std=processor.image_std)
 transform = Compose([
     Resize((224, 224)),
+    RandomHorizontalFlip(),
+    RandomRotation(10),
     ToTensor(),
     normalize,
 ])
 
 def predict(image):
-    try:
-        image = Image.fromarray(image)
-        inputs = transform(image).unsqueeze(0)
-        outputs = model(inputs)
-        logits = outputs.logits
-        predicted_class_idx = logits.argmax(-1).item()
-        return processor.decode(predicted_class_idx)
-    except Exception as e:
-        print("An error occurred:", e)
-        print(traceback.format_exc())
-        return "An error occurred while processing your request."
-
-def predict_function(input_data):
-    try: 
-        # model 
-        output = f"Processed input: {input_data}"  # Gantilah dengan model 
-        return output
-    except Exception as e:
-        # Menampilkan error
-        print("An error occurred:", e)
-        print(traceback.format_exc())  # Ini akan print error secara detail
-        return "An error occurred while processing your request."
+    image = Image.fromarray(image)
+    inputs = transform(image).unsqueeze(0)
+    outputs = model(inputs)
+    logits = outputs.logits
+    predicted_class_idx = logits.argmax(-1).item()
+    return processor.decode(predicted_class_idx)
 
 # Create Gradio interface
 interface = gr.Interface(
     fn=predict,
-    inputs=gr.Image(type="numpy"), # Changed from gr.inputs.Image to gr.Image
+    inputs=gr.inputs.Image(type="numpy"),
     outputs="text",
     title="Bird Classification",
     description="Upload an image of a bird to classify it."
 )
 
-iface = gr.Interface(fn=predict_function, inputs="text", outputs="text")
-
 if __name__ == "__main__":
     interface.launch()
-    iface.launch()