Shengyi Qian commited on
Commit
a2752e2
1 Parent(s): b61616c

add notice

Browse files
Files changed (1) hide show
  1. app.py +2 -1
app.py CHANGED
@@ -222,7 +222,8 @@ description = """
222
  Gradio demo for Understanding 3D Object Interaction from a Single Image. \n
223
  You may click on of the examples or upload your own image. \n
224
  After having the image, you can click on the image to create a single query point. You can then hit Run.\n
225
- Our approach can predict 3D object interaction from a single image, including Movable (one hand or two hands), Rigid, Articulation type and axis, Action, Bounding box, Mask, Affordance and Depth.
 
226
  """
227
 
228
  def change_language(lang_select, description_controller, run_button):
 
222
  Gradio demo for Understanding 3D Object Interaction from a Single Image. \n
223
  You may click on of the examples or upload your own image. \n
224
  After having the image, you can click on the image to create a single query point. You can then hit Run.\n
225
+ Our approach can predict 3D object interaction from a single image, including Movable (one hand or two hands), Rigid, Articulation type and axis, Action, Bounding box, Mask, Affordance and Depth.\n
226
+ Since the demo is run on cpu, it needs approximately 30 seconds to inference, which is slow. You can either fork the huggingface space, or visit https://openxlab.org.cn/apps/detail/JasonQSY/3DOI for the same demo with Nvidia A10G.
227
  """
228
 
229
  def change_language(lang_select, description_controller, run_button):