AbstractPhil commited on
Commit
5d2fd42
·
verified ·
1 Parent(s): 1f5705d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -22,6 +22,8 @@ The answer is... maybe. More research required.
22
 
23
  I used the 32 dim geometric vocab; as it seemed to be the weakest with flow-match euler-discreet to test the hypothesis that a small dimensional geometry could in fact be used in substitution of a high-geometric variation.
24
 
 
 
25
  The output model is much larger than I wanted; which defeats the purpose of the overall structure - but it's paired directly at the knee with clip-vit-base-patch32, so I'll prepare a decoupled version here in a bit.
26
 
27
 
 
22
 
23
  I used the 32 dim geometric vocab; as it seemed to be the weakest with flow-match euler-discreet to test the hypothesis that a small dimensional geometry could in fact be used in substitution of a high-geometric variation.
24
 
25
+ For obvious reasons the 512 dim vocab managed to handle a higher accuracy than the 32d; however not for the reason you would think.
26
+
27
  The output model is much larger than I wanted; which defeats the purpose of the overall structure - but it's paired directly at the knee with clip-vit-base-patch32, so I'll prepare a decoupled version here in a bit.
28
 
29