search

zh-plus / video-to-pose3D

Convert video to 3D pose in one-key.
MIT License
646 stars 130 forks source link

Can we execute it in window environment with GPU utilization? #22

Closed sajjadafridi closed 4 years ago

sajjadafridi commented 4 years ago

Hi,

I tried the code to run in window. Everything was fine but the main issue i am facing is that the code doesn't utilize the GPU. I tried each and every possible solution but helpless. Any idea?

zh-plus commented 4 years ago

I'm afraid that I can't provide any idea since I didn't try to run it in windows environment.

Did you check the value of torch.cuda.is_available() here?

sajjadafridi commented 4 years ago

I'm afraid that I can't provide any idea since I didn't try to run it in windows environment.

Did you check the value of torch.cuda.is_available() here?

yes i debug this line of code. it returns true for this line but still, GPU is not utilizing. Is there any other way to handle this?

zh-plus commented 4 years ago

What GPU are you using? And how long did it cost to process this sample video?

I'm using Nvidia Tesla V100 to process it, which takes 101.25 seconds. If you're not utilizing any GPU, it's impossible to take less than 20 minutes.

sajjadafridi commented 4 years ago

What GPU are you using? And how long did it cost to process this sample video?

I'm using Nvidia Tesla V100 to process it, which takes 101.25 seconds. If you're not utilizing any GPU, it's impossible to take less than 20 minutes.

Well, I am using Nvidia-GeForce 1080- ti 11gb on ubuntu it works like a charm but on window os it doesn't show any GPU utilization. I am doing it for live webcam.

zh-plus commented 4 years ago

╮（╯＿╰）╭ No idea for that.