performance issue about inference (0.5~1 fps)

[DellBrother]

hi, Kwotsin Thank you so much for the implementation! I trained the model with my data and got much better mIOU comparing to legacy method.

However, the inference performance is not good as the stats from the paper. My result is about 0.5~1 fps for 1280x720 image, on GeForce GTX 1080. My class number is 2 so it might save much MIPS. I run the inference with OpenCV real-time images.

Any idea about the root cause?

thanks a lot, BRS, Dell

[DellBrother]

Sorry, I just measured the ENet inference timing. it is about 80ms-90ms for 1 frame. Might need more optimization also.

Thanks, BRS, Dell

[msson]

@DellBrother Hi, how did you check the enet inference timing exactly? I also see 0.5~1 fps for 1024x768 image. Thanks.

[xiaoerlaigeid]

@DellBrother How did optimized ENet ? Could tell me how to reducing the inference time ?