Replies: 1 comment
-
Hi. It should use the weights which were randomly initialized to start the training. As you are not using pretrained weights, they won't be replaced. They also won't be updated, since you have frozen the backbone. |
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,
just a quick question: What happens when I put "backbone_pretrained": False AND freeze_backbone=True ?
What weights will the model use for the backbone?
Best regards,
Boran
Beta Was this translation helpful? Give feedback.
All reactions