-
Notifications
You must be signed in to change notification settings - Fork 0
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
Solveig branch #32
Solveig branch #32
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This looks really good. I'll just add a quick remark that PR #31 changes the way we initialize our models from taking a in_channels: int
to a input_shape: tuple[int, int, int]
, representing a single image with dimensions [channel, height, width]
.
I think it makes sense to accept your current model, then you can modify it later in PR #31 like Jan, I and soon Johan have.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks a lot for the reminder. I will change my model initialization and adjust it accordingly before merging
Also you should try to format your code again with |
I didn't know about isort but thanks for the tip I will format it properly. |
Now the files are properly formatted and the model is updated. |
Nice work! |
Moved my metric test function into the test directory. Updated the load files with my classes. Updated the choices in the main file.