[fix] Remove SmoothL1Loss from Tutorial #1298
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
judussoari
added
type:bug
judussoari
changed the title
Model Benchmark
Model training plotsModel TrainingPeytonManningYosemiteTempsAirPassengers |
Codecov Report
📣 This organization is not using Codecov’s GitHub App Integration. We recommend you install it so Codecov can continue to function properly for your repositories. Learn more @@ Coverage Diff @@
## main #1298 +/- ##
=======================================
Coverage 89.85% 89.86%
=======================================
Files 38 38
Lines 5128 5131 +3
=======================================
+ Hits 4608 4611 +3
Misses 520 520
Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. |
judussoari
commented
Apr 21, 2023
| @@ -793,6 +793,9 @@ def test_step(self, batch, batch_idx): | |||
| loss, reg_loss = self.loss_func(inputs, predicted, targets) | |||
| # Metrics | |||
| if self.metrics_enabled: | |||
| predicted_denorm = self.denormalize(predicted[:, :, 0]) | |||
| target_denorm = self.denormalize(targets.squeeze(dim=2)) | |||
| self.log_dict(self.metrics_val(predicted_denorm, target_denorm), **self.log_args) | |||
| self.log("Loss_test", loss, **self.log_args) | |||
There was a problem hiding this comment.
This is to log (and eventually return) the error metrics specified by the user. those 3 lines are in validation_step and training_step, but (apparently) have been forgottten here
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Outdated suggestions cannot be applied.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.
🔬 Background
Closes #1234
SmoothL1Loss is not supported by Torchmetrics. With the lightning migration, we only use those, however.
Also,
m.test()does not return error metrics specified by the user.🔮 Key changes
📋 Review Checklist