zhang943 / lpn-pytorch Goto Github PK

why the speed of fps in the paper of v1 is 33 fps, but in v2 is 17fps

Hello,

Sorry for the noob question, is this a top down or bottom up approach?

thanks for your best work. but i have a question about "config.TEST.BIAS".
what is the function of this parameter?
in your paper, i don't find anything about the introduction about this parameter.
Looking forward to your reply

Can you upload the training code for this amazing work? Thanks!

hi,bro,do you have train.py in this repo?

Hi @zhang943
I want to check your model on my rtsp video, so how to run inference. What is approximate speed FPS, i can get on Nvidia 1650 GPU?

Hello, I want to test the inference speed of LPN50. Where is the inference speed in the log file?
if i want to test our method based on Simplebaseline, how to test the inference speed?
Thank you

Has anyone reproduced successfully? I used the training files in HR-NET to train an LPN50, but the results were far from ideal.

Hello, I used your code to train an LPN50 on the COCO dataset. The train.py used is from HR-NET.But the result is not very good, what is the reason?

where is the code of Iterative Training Strategy, and how many steps is the appropriate choise？