From 55a29c6c707c289449445c7f15964e9dbbdcf818 Mon Sep 17 00:00:00 2001 From: Gustaf Rydholm Date: Tue, 13 Sep 2022 21:56:59 +0200 Subject: Update README --- README.md | 1 + 1 file changed, 1 insertion(+) (limited to 'README.md') diff --git a/README.md b/README.md index d308bd9..304f185 100644 --- a/README.md +++ b/README.md @@ -53,6 +53,7 @@ Ideas of mine that did not work unfortunately: * Efficientnet was apparently a terrible choice of an encoder - A ConvNext module heavily copied from lucidrains [x-unet](https://github.com/lucidrains/x-unet) + was incredibly much better at encoding the images to a better representation. * Use VQVAE to create pre-train a good latent representation - Tests with various compressions did not show any performance increase compared to training directly e2e, more like decrease to be honest -- cgit v1.2.3-70-g09d2