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

model size and parameter #10

Open
CVencode opened this issue Jul 12, 2020 · 1 comment
Open

model size and parameter #10

CVencode opened this issue Jul 12, 2020 · 1 comment

Comments

@CVencode
Copy link

CVencode commented Jul 12, 2020

Hello,
how were the model sizes and parameters mentioned in the paper table2 calculated?
How long was the training time of the model?

@CVencode CVencode changed the title Model size and performance model size and parameter Jul 12, 2020
@HarukiYqM
Copy link
Collaborator

Hi, the x2 model size in the paper is calculated using the following code in main.py:
print('Total params: %.2fM' % (sum(p.numel() for p in _model.parameters())/1000000.0))

Training time depends on certain computation resources. It will roughly take about 5~6 days on 4 V100 GPUs.

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

2 participants