spot92
spot92
I emailed them today about the API and they said there is no longer a release date, but it is planned for the future at some time.
I am running this on a 1080ti. Could I get some sort of print screen for what a successfully running train is? It has been sitting for awhile and I...
> @spot92 > Try changing `--checkpoint-iterations` to a lower value. It prints whenever it finishes that number of iterations Thanks! How many iterations are in an epoch?
Is it faster than this one? Because this one seems really solid. Edit: I see the one you linked doesn't work on windows.
I'll check it out
I have a 1080 ti and can get to 1500 using the L-BFGS, can then upres to 2560 using ADAM. This does vary depending on overall dimensions.
Check your version of tensorflow to make sure it's 1+
I'll look into them. I just thought it was weird that it only did it with specific combinations of images. Thanks!
Is there a fast way to go from this: checkpoint fns.ckpt.data-00000-of-00001 fns.ckpt.index fns.ckpt.meta to this: checkpoint fns.ckpt (19,675KB) fns.ckpt.meta WITHOUT retraining?
> The `.ckpt` model format was abandoned when Tensorflow moved to version 1.0+, so unfortunately, you'll need to keep the model's files in a folder rather than in a single...