Replace "Learning PyTorch with Examples" with fitting sine function with a third order polynomial #1265
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! Built with commit 28f28d8 https://deploy-preview-1265--pytorch-tutorials-preview.netlify.app |
zasdfgbnm
changed the title
rodrigo-techera
pushed a commit
to Experience-Monks/tutorials
that referenced
this pull request
Nov 29, 2021
…ith a third order polynomial (pytorch#1265) * Replace tutorial with fitting sine function with third order polynomial * more * Save * save * save * fix * fix * fix * fix * no tensor.data * fix * P3 * save * save * save * save * fix * fix * fix
This was referenced Jan 15, 2022
brianjo
pushed a commit
that referenced
this pull request
Feb 3, 2022
The old artifacts are still accessible in the legacy form with broken layout. This commit redirects the old pages to the new pages and remove related assets. `tf_two_layer` was deleted in #1265 but I am not sure if it should be deleted, so not changing it in this commit.
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Outdated suggestions cannot be applied.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 original "fitting a 2-layer network to noise" example is replaced with fitting a third-order polynomial to the sine function.
The overall structure of the entire article is not changed. Some out-of-date statements are updated. The TensorFlow example is removed because now TF2 uses eager mode by default as well, therefore the comparing becomes obsolete.
The advantage of this is, it is a real fitting problem, rather than a "memorize the noise" problem. Using a real fitting problem makes sure that the final loss will not be sensitive to mantissa precision. Because the inability of the model for fitting ground truth will be much larger than rounding errors. Another advantage of this is, users can easily print and plot the resulting polynomial to evaluate the training.
cc: @soumith @ngimel @csarofeen @ptrblck