Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

It takes a lot of time to open the server. #8

Open
likestudy opened this issue Apr 29, 2019 · 4 comments
Open

It takes a lot of time to open the server. #8

likestudy opened this issue Apr 29, 2019 · 4 comments

Comments

@likestudy
Copy link

Thanks a lot for this great project !
Some problems have arisen here :
Problem 1 : After the first time when i run $ python server.py at the server computer , it shows 'Multi-Scale Temporal Relation Network Module in use ['8-frame relation', '7-frame relation', '6-frame relation', '5-frame relation', '4-frame relation', '3-frame relation', '2-frame relation']' . Then it takes about 10 minutes to show other information :
**'Freezing BatchNorm2D except the first one.
done

  • Serving Flask app "server" (lazy loading)
  • Environment: production
    WARNING: Do not use the development server in a production environment.
    Use a production WSGI server instead.
  • Debug mode: off
  • Running on http://0.0.0.0:80/ (Press CTRL+C to quit)
    '**
    Is this normal? How long does it take for everyone to open the server?(As my RAM is 16 G )

Problem 2 : After the server is start , i run $ python run_manual.py -s http://xx.xx.xx.xx:80 at my computer. I can start the recognition program with key 's' , but after the second ‘s’ there is no result. When I try to run 'run_frameDifferent.py' , I meet the same problem .
Maybe there is something wrong with the way that I set this project ? Or I missed some important details ?

Any answer will help me a lot . Thank you very much !

@govzhz
Copy link
Owner

govzhz commented May 6, 2019

Console output looks fine. python server.py will initialization TRN model, if the opening time is too long, maybe the performance of the machine is not enough, I am not sure.

About no prediction results, you can check if the client log has an upload log like 'upload ...' , you can also check if the image is correctly uploaded in the server/frames directory on the server.

@govzhz
Copy link
Owner

govzhz commented May 6, 2019

The running TRN model mainly depends on the gpu memory(not ram), please check if it is greater than 4g

@likestudy
Copy link
Author

Thanks very much for your reply.
1、As I have a GPU with 11G memory, I think this problem may has little to do with the configuration of the hardware.
2、Sometimes there are pictures in this folder, but most of the time there are no pictures. I think this may have something to do with my network settings? For the network, the server run at 0.0.0.0:80 and my computer connect the server at IP_of_the_server_under_the_LAN:80.
I will do more to solve this problem. Thanks again for your help.

@Pan-zhaoyu
Copy link

Thanks very much for your reply.
1、As I have a GPU with 11G memory, I think this problem may has little to do with the configuration of the hardware.
2、Sometimes there are pictures in this folder, but most of the time there are no pictures. I think this may have something to do with my network settings? For the network, the server run at 0.0.0.0:80 and my computer connect the server at IP_of_the_server_under_the_LAN:80.
I will do more to solve this problem. Thanks again for your help.

hello, I noticed that you run this code successfully. Do you have the weight file which the author mentioned in the model file? if you have it, would you send it to me? THX!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants