search

dusty-nv / jetson-inference

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
https://developer.nvidia.com/embedded/twodaystoademo
MIT License
7.53k stars 2.94k forks source link

cudaEventElapsedTime device not ready (error 600) (hex 0x258) #1821

Open akshaydhame2001 opened 3 months ago

akshaydhame2001 commented 3 months ago

Detection is working but console is writing this error in between detection constantly. Confidence: 0.97998 ClassID: 1 Left: 275.938 Top: 188.086 Right: 832.5 Bottom: 714.023 Width: 556.562 Height: 525.938 Area: 292717 Center: (554.219, 451.055) Sending YAW movement command with heading: -1.730313 I Sending XYZ movement command with v_x(forward/backward): -0.138160 v_y(right/lef t): 0.000000

[cuda] cudaEventElapsedTime(&cuda_time, mEventsGPU [evt], mEventsGPU[evt+1]) [cuda] device not ready (error 600) (hex 0x258) [cuda] /home/akshay/jetson-inference/build/aarch64/include/jetson-inference /tensorNet.h:769

gaochuanchao commented 2 months ago

I think the issue is that some data is not ready that fast. letting the system sleep for 1ms usually can solve this issue (I hope it works for your case), i.e., time.sleep(0.001).