search

happinesslz / EPNet

EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection(ECCV 2020)
MIT License
230 stars 37 forks source link

Question about the inferring time? #4

Closed lihua213 closed 3 years ago

lihua213 commented 3 years ago

Thanks for your nice work. I have tested your code, I found it is very slow. However, you mentioned that the inferring speed is 10 FPS. Is it really 10 FPS?

happinesslz commented 3 years ago

@lihua213 Thanks for your attention. We test the code on Titan V, and also modify the TEST.RPN_POST_NMS_TOP_N from 100 to 64 to speed up the inference in the LI_Fusion_with_attention_use_ce_loss.yaml .

lihua213 commented 3 years ago

@lihua213 Thanks for your attention. We test the code on Titan V, and also modify the TEST.RPN_POST_NMS_TOP_N from 100 to 64 to speed up the inference in the LI_Fusion_with_attention_use_ce_loss.yaml .

Thanks so much. BTW, could you share the multi-class version?

happinesslz commented 3 years ago

@lihua213 Sorry, due to my busy studies，I will support the multi-class version in the near future.