Use the correct batch values in the output #2191
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
✅ Deploy Preview for pytorch-tutorials-preview ready!
To edit notification comments on pull requests, go to your Netlify site settings. |
|
@svekars thanks! The other thing I want to mention is that I couldn’t find a way to update the values in the |
|
Fixed merge conflict. |
The current logic uses enumerate counter (i.e. variable `batch`). It displays the loss for trained data in an increment of 100 using batch % 100 == 0. i.e. 1 batch, 101 batch, and so on for the given dataset. This maps to batch =0, 100, and so on). So for the first batch, the loss displayed should be [ 64/60000] instead of [ 0/60000]). For the second it should be [ 6464/60000] instead of [ 6400/60000] , and so on. The Output values, e.g. loss: 2.306185 [ 0/60000], read as a loss observed for zero input data which seems incorrect. This loss mentioned here was for the first batch, which was 64 input data. The second was for 101 batch which has 6464 input data, and so on.
|
thanks |
|
@svekars hello, considering the changes, I am wondering if I need to request review from any specific reviewer? No rush, I just thought good idea I ask in case it's needed. Thanks! |
|
@suraj813 yrw, and thank you so much for the review! |
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Outdated suggestions cannot be applied.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.
The current logic uses enumerate counter (i.e. variable
batch). It displays the loss for trained data in an increment of 100 usingif batch % 100 == 0. i.e. 1st batch, 101 stbatch, and so on for the given dataset. This maps to batch =0, 100, and so on). So for the first batch, the loss displayed should be[ 64/60000]instead of[ 0/60000]. For the second it should be[ 6464/60000]instead of[ 6400/60000], and so on. The values displayed in theOut:text box on the tutorial page, e.g.loss: 2.306185 [ 0/60000], read as a loss observed for zero input data which seems incorrect. This loss mentioned here was for the first batch, which was 64 input data. The second was for 101 batch which has 6464 input data, and so on.cc @suraj813