blue

I'm running into the same problem. This has already been reported in #223

Hey Nick, You're right, after converting my input data to .tiff, training works as expected. I thought I'd trained on .pngs before but must have mixed something up! Inference from...

Inferring from a .png using the pre-trained XDXD network does seem to work (i.e. does not throw an error), but the output is not binary as it's probably supposed to...

I'm not sure I understand - you're saying binarisation does run automatically in the polygonisation phase of inference, right? Wouldn't a default threshold of 0 then return a white image,...

I'm afraid not but it could well have been an oversight on my part! (a colleague ran into a similar error when they ran Trainer on a .yml configured for...

Hey that sounds like it could very well be the reason for my problem! I did train the model on 500x500 images, though, without a problem IIRC. The error occured...

That was a quick response! The input image I enclosed is not from the Atlanta dataset. I will look into image normalisation. Thank you for the suggestion!

I should also add that I set `p` to 0 under `inference_augmentation --> DropChannel` on line 81 of xdxd_spacenet4.yml, because otherwise an error was thrown about a channel that could...

Hi Nick, Thanks for your communication and transparency. I'd like to ask a few more questions regarding inference which I hope you have the time to answer. It is my...