Update app.py

app.py

@@ -78,10 +78,19 @@ def generate_gemini_response(input_prompt, image):
 
 # Object detection part
 def detect_objects(image):
+    # Ensure the image is in RGB mode
+    if image.mode != "RGB":
+        image = image.convert("RGB")
+    
+    # Convert the image to a numpy array
+    image_np = np.array(image)
+    
+    # Load the processor and model
     processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
     model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
-
-    inputs = processor(images=image, return_tensors="pt")
+    
+    # Process the image for detection
+    inputs = processor(images=image_np, return_tensors="pt")
     outputs = model(**inputs)
 
     target_sizes = torch.tensor([image.size[::-1]])
@@ -106,6 +115,7 @@ def detect_objects(image):
     
     return image, detected_cars
 
+
 def image_to_bytes(img):
     # Convert a PIL image to bytes
     from io import BytesIO