BRD owlvit

app.py

@@ -19,11 +19,9 @@ model.eval()
 processor = OwlViTProcessor.from_pretrained("google/owlvit-large-patch14")
 
 
-def query_image(img_url, text_queries, score_threshold):
+def query_image(img, text_queries, score_threshold):
     text_queries = text_queries.split(",")
 
-    response = requests.get(img_url)
-    img = Image.open(BytesIO(response.content))
     img = np.array(img)
 
     target_sizes = torch.Tensor([img.shape[:2]])
@@ -56,9 +54,6 @@ def query_image(img_url, text_queries, score_threshold):
 
 
 description = """
-Gradio demo for <a href="https://huggingface.co/docs/transformers/main/en/model_doc/owlvit">OWL-ViT</a>,
-introduced in <a href="https://arxiv.org/abs/2205.06230">Simple Open-Vocabulary Object Detection
-with Vision Transformers</a>.
 \n\nYou can use OWL-ViT to query images with text descriptions of any object.
 To use it, simply input the URL of an image and enter comma separated text descriptions of objects you want to query the image for. You
 can also use the score threshold slider to set a threshold to filter out low probability predictions.
@@ -70,7 +65,9 @@ hence you can get better predictions by querying the image with text templates u
 """
 demo = gr.Interface(
     query_image, 
-    inputs=["text", "text", gr.Slider(0, 1, value=0.1)],
+    inputs=[gr.Image(source="upload"), 
+            "text", 
+            gr.Slider(0, 1, value=0.1)],
     outputs="image",
     title="Zero-Shot Object Detection with OWL-ViT",
     description=description,