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

About BatchNormalization #3

Open
RainPot opened this issue Apr 22, 2019 · 8 comments
Open

About BatchNormalization #3

RainPot opened this issue Apr 22, 2019 · 8 comments

Comments

@RainPot
Copy link

RainPot commented Apr 22, 2019

hi
by running your project,I can reach high mIoU,but when the Batchnormlization is setting all SYNC in ResNet,the mIoU can just reach 70%,why is that?

@RainPot RainPot changed the title About Normalization About BatchNormalization Apr 22, 2019
@RainPot
Copy link
Author

RainPot commented Apr 22, 2019

thanks for great code btw

@sonack
Copy link

sonack commented May 6, 2019

@Cynicsss How did you control the BN sync or not sync? I found the bn in resnet is original all sync already? What do you mean by ,but when the Batchnormlization is setting all SYNC in ResNet,the mIoU can just reach 70%

@RainPot
Copy link
Author

RainPot commented May 6, 2019

@Cynicsss How did you control the BN sync or not sync? I found the bn in resnet is original all sync already? What do you mean by ,but when the Batchnormlization is setting all SYNC in ResNet,the mIoU can just reach 70%

self.bn3 = nn.BatchNorm2d(out_chan)

@sonack
Copy link

sonack commented May 7, 2019

@Cynicsss How did you control the BN sync or not sync? I found the bn in resnet is original all sync already? What do you mean by ,but when the Batchnormlization is setting all SYNC in ResNet,the mIoU can just reach 70%

self.bn3 = nn.BatchNorm2d(out_chan)

Do you know why the author need to use the original nn.BatchNorm2drather than synced bn here ?

@codermckee
Copy link

@Cynicsss Hi, how long did it take you to reach 70% mIoU? I tried the code, but it takes one night just training about 12000 iterations.

@codermckee
Copy link

@Cynicsss I use 3 *1080ti to train on CityScapes without any change, but just reaching 70.23% mIoU. Is there something I should change in order to reach higher mIoU? BTW, it costed me about 2.5 days to train 41000 iterations..so sad.

@LetsGoFir
Copy link

LetsGoFir commented Jan 12, 2020

@Cynicsss I use 3 *1080ti to train on CityScapes without any change, but just reaching 70.23% mIoU. Is there something I should change in order to reach higher mIoU? BTW, it costed me about 2.5 days to train 41000 iterations..so sad.

It takes me 4 hours to train 15000 iterations with 2 RTX2080 and finally I got 78.2 mIoU.

@prachigarg23
Copy link

@LetsGoFir can you please confirm if this repository is reproducible for cityscapes? I'm also using 2RTX 2080 GPUs and facing issues getting 75%+ mIoU on CS. Also any idea if there are any differences between this implementation and the official implementation?

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

5 participants