diff options
| author | Gustaf Rydholm <gustaf.rydholm@gmail.com> | 2022-09-13 22:01:36 +0200 |
|---|---|---|
| committer | Gustaf Rydholm <gustaf.rydholm@gmail.com> | 2022-09-13 22:01:36 +0200 |
| commit | 46c8fb98581b1a9de1ab07d1b0e9ac52f382b00c (patch) | |
| tree | 0be3386157e8559e1cf872bc2c26f8bb16d98302 | |
| parent | 3ac94b63f3f2a8e9880958eb8c9862e0b1ffe3fd (diff) | |
Update README
| -rw-r--r-- | README.md | 2 |
1 files changed, 1 insertions, 1 deletions
@@ -59,7 +59,7 @@ Ideas of mine that did not work unfortunately: - Tests with various compressions did not show any performance increase compared to training directly e2e, more like decrease to be honest - This is very unfortunate as I really hoped that this idea would work :( - I still really like this idea, and I might not have given up just yet... - - I have no given up... :( ConvNext ftw + - I have now given up... :( ConvNext ftw * Axial Transformer Encoder - Added a lot of extra parameters with no gain in performance |