You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I use the command 'python compute_coordinates.py' to detect the poses of target images. Everything goes well but I get all -1 results. Is there any requirement for input person image (e.g. resolution)?
The text was updated successfully, but these errors were encountered:
I use openpose checkpoint for detecting. So they asume images like in ms coco. But it generalize to other resolutions. Do you get -1 in all the images? You can try to change treshold th1 and th2 in compute coordinates script.
I use the command 'python compute_coordinates.py' to detect the poses of target images. Everything goes well but I get all -1 results. Is there any requirement for input person image (e.g. resolution)?
The text was updated successfully, but these errors were encountered: