Modify finetune function #69
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
LorenzLamm
reviewed
Sep 16, 2024
| os.path.splitext(os.path.basename(label_path))[0] + "_skel.mrc", | ||
| ) | ||
|
|
||
| store_tomogram(filename=out_file, tomogram=ske) |
There was a problem hiding this comment.
As raised in #82, this will lose the information of the header.
Can we load the tomogram before calling skeletonization and pass it instead of label path?
load_tomogram gives you a Tomogram instance (
). If you simply alter tomo.data, you can pass the Tomogram intostore_tomogram instead of ske
LorenzLamm
reviewed
Sep 16, 2024
| def on_epoch_start(self, trainer, pl_module): | ||
| current_lr = trainer.optimizers[0].param_groups[0]["lr"] | ||
| print(f"Epoch {trainer.current_epoch}: Learning Rate = {current_lr}") | ||
|
|
||
| print_lr_cb = PrintLearningRate() |
There was a problem hiding this comment.
Do we need this callback in the standard function for the user?
LorenzLamm
reviewed
Sep 16, 2024
| @@ -266,3 +272,112 @@ def forward( | |||
| # Normalize loss | |||
| loss = loss / sum(self.weights) | |||
| return loss | |||
|
|
|||
|
|
|||
| class PrintLearningRate(Callback): | |||
There was a problem hiding this comment.
Okay to keep this here, but I think this is not necessary to have actively used in the fine-tune functionality. I guess this is only useful for debugging
LorenzLamm
added a commit
that referenced
this pull request
Sep 17, 2024
* add skeletonization code * Second commit * Second commit * Second commit * Second commit * Third commit * Third commit * Fourth commit * Fourth commit * Fix data type warning and absolute value error * Add finetune function * Modify finetune function * Add Fine-tuning.md file --------- Co-authored-by: Hanyi11 <[email protected]> Co-authored-by: Hanyi Zhang <[email protected]> Co-authored-by: Hanyi Zhang <[email protected]> Co-authored-by: Hanyi Zhang <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Main Changes:
tomo.datais now passed into skeletonization, and the resulting skeleton replaces the originaltomo.datafor saving.PrintLearningRatecallback from the fine-tuning function.