Updated calculation of train_loss and valid_loss #336
Merged
Conversation
This file contains hidden or 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
Using len(train_loader.dataset) and len(valid_loader.dataset) will result in wrong values as they return size of 'train_data' (i.e 60000 images). This is the reason for such difference in train_loss and valid_loss. 'train_loader' actually has size of 0.8*train_data (i.e 48000 images) and valid_loader actually has size of 0.2*train_data (i.e 12000 images). Hence calculate avg batch loss in each batch and divide by total batches. This works because all the batches in both the dataloaders are of 20(reason: 48000%20=0 and 12000%20=0)
abhiojha8
approved these changes
Jul 5, 2021
mxagar
pushed a commit
to mxagar/deep-learning-v2-pytorch
that referenced
this pull request
Jul 1, 2022
Updated calculation of train_loss and valid_loss
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Using len(train_loader.dataset) and len(valid_loader.dataset) will result in wrong values as they return size of 'train_data' (i.e 60000 images). This is the reason for such difference in train_loss and valid_loss.
'train_loader' actually has size of 0.8*train_data (i.e 48000 images) and valid_loader actually has size of 0.2*train_data (i.e 12000 images).
Hence calculate avg batch loss in each batch and divide by total batches. This works because all the batches in both the Dataloaders are of size 20(reason: 48000%20=0 and 12000%20=0)