Browse Source

Updating readme to reflect bug fix.

Jason Antic 6 years ago
parent
commit
f482afe8d3
1 changed files with 1 additions and 1 deletions
  1. 1 1
      README.md

+ 1 - 1
README.md

@@ -165,7 +165,7 @@ I'm sure I screwed up something putting this up, so [please let me know](https:/
 * You'll have to **play around with the size of the image** a bit to get the best result output.  The model clearly has some dependence on aspect ratio/size when generating images. It used to be much worse but the situation improved greatly with lighting/contrast augmentation and introducing progressive training.  I'd like to eliminate this issue entirely and will obsess about it but in the meantime – don't despair if the image looks over-saturated or has weird glitches at the first go. There's a good chance that it'll look right with a slightly different size.  Generally, over-saturated means go bigger.
 * To expand on the above- Getting the best images really boils down to the **art of selection**.  Yes, results are cherry picked.  I'm very happy with the quality of the outputs and there's a pretty good amount of consistency, but it's not perfect.  This is still an ongoing project!  I'd consider this tool at this point fit for the "AI artist" but not something I'd deploy as a general purpose tool for all consumers.  It's just not there yet.
 * To complicate matters – this model is a **memory hog** currently, so on my 1080TI I can only do 500-600px max on the sz parameter for the images.  I'm betting there's plenty of low-hanging fruit to get some wins on this but I just haven't done it yet.
-* I added zero padding in the Unet generator for whenever the pretrained resnet winds up passing up a tensor that doesn't match expected dimensions (namely so I could throw any arbitrarily-sized image at it).  This was a super-quick hack and it results in **stupid right and bottom borders on the outputs** for those arbitrarily-sized test images. I'm sure there's a better way, but I  haven't gotten around to addressing it yet.  
+* A small portion of the bottom and right sides of images will be removed in the process.   
 * The model *loves* blue clothing.  Not quite sure what the answer is yet, but I'll be on the lookout for a solution!
 
 ### Want More?