Update app.py

app.py

@@ -15,7 +15,7 @@ model = Owlv2ForObjectDetection.from_pretrained("google/owlv2-base-patch16").to(
 def detect_objects_in_frame(image, target):
     draw = ImageDraw.Draw(image)
     texts = [[target]]
-    inputs = processor(text=texts, images=image, return_tensors="pt").to(device)
+    inputs = processor(text=texts, images=image, return_tensors="pt", padding=True).to(device)
     outputs = model(**inputs)
 
     target_sizes = torch.Tensor([image.size[::-1]])
@@ -98,7 +98,7 @@ def gradio_app():
         target_input = gr.Textbox(label="Target Object")
         output_video = gr.Video(label="Output Video")
         error_output = gr.Textbox(label="Error Messages", visible=False)
-        sample_video_frame = gr.Image(value=load_sample_frame("Drone Video of African Wildlife Wild Botswan.mp4"), label="Sample Video Frame")
+        sample_video_frame = gr.Image(value=load_sample_frame("Drone Video of African Wildlife Wild Botswan.webm"), label="Sample Video Frame")
         use_sample_button = gr.Button("Use Sample Video")
 
         video_path = gr.State(None)
@@ -115,7 +115,7 @@ def gradio_app():
                            outputs=[output_video, error_output])
 
         def use_sample_video():
-            sample_video_path = "Drone Video of African Wildlife Wild Botswan.mp4"
+            sample_video_path = "Drone Video of African Wildlife Wild Botswan.webm"
             return process_and_update(sample_video_path, "animal")
 
         use_sample_button.click(use_sample_video,