Yolov4 works fine on the local computer. I ran it on ubuntu using google cloud platform, but Object recognition is not possible. All environments required for ubuntu have been built. I am using yolo-v4 using only numpy and opencv. When I run it on ubuntu-18.04-LTS of gcp, the screen is printed well, but the object is not recognized. The path names of the weight file and cfg file are entered normally, and no error occurs. However, object recognition is not performed. I am using TIGERVNC for GUI environment. Is there a solution?
Asked
Active
Viewed 194 times
0
-
1Have you tried enabling Display device settings? it may help to improve your situation: https://cloud.google.com/compute/docs/instances/enable-instance-virtual-display#virtual-display-create – Jaime López May 06 '21 at 17:04
-
Thank you. I'll try. But I tried putting in a video file, and object recognition didn't work. Good on the local computer, but no object recognition in the cloud. – ygh May 07 '21 at 07:49