Update app.py

app.py

@@ -94,11 +94,25 @@ def evaluate_model_with_report(val_loader):
 # Performance metrics
 def generate_performance_metrics():
     model.eval()  # Set model to evaluation mode
-    
-    y_pred = [] 
+
+    y_true = []  # True labels
+    y_pred = []  # Predicted labels
+
+    with torch.no_grad():
+        for batch in val_loader:
+            inputs = {key: val.to(device) for key, val in batch.items()}
+            labels = inputs.pop("labels").to(device)
+
+            outputs = model(**inputs)
+            prediction = torch.argmax(outputs.logits, dim=1).item()
+
+            y_true.append(label)
+            y_pred.append(prediction)
+
+    # Compute accuracy and classification report
     accuracy = accuracy_score(y_true, y_pred)
     report = classification_report(y_true, y_pred, output_dict=True)
-    
+
     return {
         "accuracy": f"{accuracy:.2%}",
         "precision": f"{report['1']['precision']:.2%}",
@@ -106,7 +120,6 @@ def generate_performance_metrics():
         "f1_score": f"{report['1']['f1-score']:.2%}",
     }
 
-
 # Gradio Interface
 
 def create_interface():