when I run the evaluation，there is no end，why？

BichenWuUCB / SqueezeSeg

Implementation of SqueezeSeg, convolutional neural networks for LiDAR point clout segmentation

BSD 2-Clause "Simplified" License

566 stars 239 forks source link

when I run the evaluation，there is no end，why？ #28

Open yileichen123 opened 6 years ago

yileichen123 commented 6 years ago

The sentence is constantly like this: Wait 60s for new checkpoints to be saved ... Wait 60s for new checkpoints to be saved ... Wait 60s for new checkpoints to be saved ...

jrbin commented 5 years ago

it's synchronous with the training, you can turn off it or set the args "--run_once True"