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
Doesn't train actually. #31
Comments
Refer #20 , Try training fcn-8s without polynomial learning rate. Should work fine. |
@meetshah1995 trained SEGNET with disabled polynomial learning rate (commented out two lines): #iter = len(trainloader)*epoch + i as well I had to change here like this:
It may be because I'm using python3, or because you previously made a conversion So, now I'm waiting util fcn-8s get trained to see results without polynomial learning rate. |
hi, why does your results looks much worse than the examples? |
PolyLR doesn't seem to work with FCN. FCN-8s in default settings work fine, with mIoU > 60 |
hi, @chichivica if you want to train SegNet, you should set batch_size and l_rate, because of the BN layer. For example , you can set batch_size=16 and l_rate=1e-4. |
I am getting the same (bad) results as @chichivica, with SegNet, even with the settings @HelloAlone suggested. My GTX1080Ti just could not handle a batch size of 16, so I used a batch size of 14 instead. Also, the noise on my training curves increases significantly over time. |
@chichivica @Galto2000 |
Many thanks for great opensource implementation of the semantic segmentation in pytorch ever!
I'm trying to proceed through training 'segnet' model on 'pascal' dataset.
What I've done:
started training as:
training successfully started and going looks well:
after completion, generated 100 segnet_pascal_1_%2d.pkl files
But result is quite wrong:
for some reasons, output resolution differ and segmentation was not produced correctly.
Could you please give me some advises what I'm doing wrong?
Many thanks,
Ivan
The text was updated successfully, but these errors were encountered: