Update app.py

app.py

@@ -1,7 +1,8 @@
+from io import BytesIO
 import requests
+from PIL import Image
 
 import torch
-from PIL import Image
 from transformers import AutoProcessor, AutoModelForZeroShotObjectDetection 
 
 model_id = "IDEA-Research/grounding-dino-tiny"
@@ -10,11 +11,19 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 processor = AutoProcessor.from_pretrained(model_id)
 model = AutoModelForZeroShotObjectDetection.from_pretrained(model_id).to(device)
 
-image_url = "http://images.cocodataset.org/val2017/000000039769.jpg"
-image = Image.open(requests.get(image_url, stream=True).raw)
+image_url = "https://pub-44a464d4394a43d6834ffdc08038cb38.r2.dev/static/img/guess_a_capsule.jpeg"
+
+headers = {
+    "User-Agent": "Mozilla/5.0"
+}
+
+response = requests.get(image_url)
+response.raise_for_status()
+
+image = Image.open(BytesIO(response.content)).convert("RGB")
 # Check for cats and remote controls
 # VERY important: text queries need to be lowercased + end with a dot
-text = "a cat. a remote control."
+text = "a capsule."
 
 inputs = processor(images=image, text=text, return_tensors="pt").to(device)
 with torch.no_grad():