Closed samantha0-ops closed 4 years ago
I am such a idiot. Actually I am running demo.py on a non-graphic server, so when it comes to cv2.imshow(), the program will report a error. And according to demo.py, I have to define "output" to ensure the result are saved in a folder, otherwise it will go to the code "cv2.imshow()".
I'm running demo.py like this:
python demo/demo.py \ --config-file configs/BAText/TotalText/attn_R_50.yaml \ --input datasets/ctw1500/test/text_image/ \ --opts MODEL.WEIGHTS tt_e2e_attn_R_50.pth
and after showing:
datasets/ctw1500/test/text_image/1263.jpg: detected 11 instances in 0.16s
there is a error:
Fontconfig error: failed reading config file: cannot connect to X server /home/xsb/.conda/envs/detectron2_1/lib/python3.6/multiprocessing/semaphore_tracker.py:143: UserWarning: semaphore_tracker: There appear to be 1 leaked semaphores to clean up at shutdown
I am running on pytorch 1.4.0, tensorvision 0.5.0, cuda 10.0 on a linux server , can anyone help me? I am new to detectron2, so I am totally confused.