ThePrecoder
ThePrecoder
THANKS A LOT!I check the train.txt,it was my mistake.I did not carefully examine the contents of the document.It's okay now.
Another question about parameter of num_nodes,I have no idea that what it does.I have never used pytorch_lightning.
> > Another question about parameter of num_nodes,I have no idea that what it does.I have never used pytorch_lightning. > > In distributed training the number of nodes correspond to...
> The val_check_interval error means that your epoch (9636) is smaller than when you would like to run the validation (10000). > > To fix this, change the `VAL_FREQ: 10000.0`...
And intrinsics calculated by colmap are different in different pictures.