Cross-Scale-Non-Local-Attention icon indicating copy to clipboard operation
Cross-Scale-Non-Local-Attention copied to clipboard

model size and parameter

Open CVencode opened this issue 4 years ago • 1 comments

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

CVencode avatar Jul 12 '20 08:07 CVencode

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.

HarukiYqM avatar Jul 13 '20 05:07 HarukiYqM