Protgnn update #19
Merged
Protgnn update #19
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
Jeratt
force-pushed
the
protgnn_update
branch
from
e7053aa to
bb02ce0
Compare
src/models_builder/gnn_models.py
Outdated
| early_stop_count = 0 | ||
| best_prots = prot_layer.prototype_graphs | ||
| # data_indices = train_loader.dataset.indices | ||
| def train_complete(self, gen_dataset, steps=None, pbar=None, metrics=None, **kwargs): |
There was a problem hiding this comment.
train_complete его наличие кажется необязательным
There was a problem hiding this comment.
Если train_complete нужен только, чтобы early_stooping запустить после after_epoch, то необходимо просто переписать early_stooping, а не train_complete
src/models_builder/gnn_models.py
Outdated
| loss.backward() | ||
| torch.nn.utils.clip_grad_value_(self.gnn.parameters(), clip_value=2.0) | ||
| self.optimizer.step() | ||
| return loss | ||
|
|
||
| def run_model(self, gen_dataset, mask='test', out='answers'): |
There was a problem hiding this comment.
run_model его наличие кажется необязательным. (Скорее всего дублирует код родительского класса, если так, то надо убрать)
| self.early_stop_count = 0 | ||
| self.gnn.best_prots = self.prot_layer.prototype_graphs | ||
| self.best_acc = 0.0 | ||
|
|
There was a problem hiding this comment.
Также проверить evaluate_model его наличие кажется необязательным. (Скорее всего дублирует код родительского класса, если так, то надо убрать)
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Outdated suggestions cannot be applied.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.
Fix ProtGNN train due to new train procedure. Tested on back and tested on front - got reasonable prots and acc.