-
Notifications
You must be signed in to change notification settings - Fork 23
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Finetune TinySAM on custom dataset #22
Comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hello, Im trying to fine-tune the mask decoder of tiny sam on a custom dataset while freezing the weights of the image_encoder and prompt_encoder. Im having an issue in my training loop where the sam.forward() requires a "multimask_output" argument but the MaskDecoder.forward() doesn't accept a "multitask_output" argument.
Im not an ML Engineer so I don't know much about the underlying code. If anyone with more knowledge than me has some insight into how I can resolve this issue I would appreciate it, thanks!
here is how im freezing the image encoder and prompt encoder to maintain the original weights:
I am also providing bounding box Prompts as the input. Here is my custom class for Dataset creation:
error when I DONT provide multitask_output:
error when I do provide the multitask_output argument:
The text was updated successfully, but these errors were encountered: