You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on May 12, 2024. It is now read-only.
first of all thanks for the great repo @PINTO0309 !
I want to achieve the following:
Convert the segm_full_v679.tflite to a trainable format, finetune it on my own data, and then recreate the exact original graph as before just with my new weights.
The thing I'm struggling with it that custom operations (in this case Convolution2DTransposeBias) are being converted. Is it possible to get thos optimized operations back after I finetune the network?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hello everyone,
first of all thanks for the great repo @PINTO0309 !
I want to achieve the following:
Convert the segm_full_v679.tflite to a trainable format, finetune it on my own data, and then recreate the exact original graph as before just with my new weights.
The thing I'm struggling with it that custom operations (in this case Convolution2DTransposeBias) are being converted. Is it possible to get thos optimized operations back after I finetune the network?
Thanks in advance!
Beta Was this translation helpful? Give feedback.
All reactions