Replies: 1 comment
-
|
Maybe https://github.com/qubvel/ttach can help you with this |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hi! I don't see much documentations on this, so just wanted to seek some advice on how TTA should be implemented when using timm?
As far as I can see in
train.py,args.ttaonly affects thereduce_factoron the output after the inference pass during validation. Will we have to create a validation loader that does augmentationargs.ttatimes on each test image? Any recommended functions in timm/external libraries/guidelines to implement our own TTA?Beta Was this translation helpful? Give feedback.
All reactions