Fix kernel dimensions for LeNet model code example #2192
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
Signed-off-by: Kiersten Stokes <kierstenstokes@gmail.com>
✅ Deploy Preview for pytorch-tutorials-preview ready!
To edit notification comments on pull requests, go to your Netlify site settings. |
|
I'm just realizing that there's already an open issue for this: #2104. Apologies if I didn't give enough time for the issue's author to open a PR for it |
|
@suraj813 can you please take a look? Thanks! |
subramen
approved these changes
Feb 13, 2023
svekars
pushed a commit
to mthrok/tutorials
that referenced
this pull request
Feb 14, 2023
* Change kernel to 5x5 in 1st Conv2d layer in model init Signed-off-by: Kiersten Stokes <kierstenstokes@gmail.com> * Change kernel to 5x5 in 2nd Conv2d layer in model init * Fix dimensions of 1st Linear layer to match new expected size --------- Signed-off-by: Kiersten Stokes <kierstenstokes@gmail.com> Co-authored-by: Suraj Subramanian <5676233+suraj813@users.noreply.github.com> Co-authored-by: Svetlana Karslioglu <svekars@fb.com>
svekars
pushed a commit
that referenced
this pull request
Mar 31, 2023
* Change kernel to 5x5 in 1st Conv2d layer in model init Signed-off-by: Kiersten Stokes <kierstenstokes@gmail.com> * Change kernel to 5x5 in 2nd Conv2d layer in model init * Fix dimensions of 1st Linear layer to match new expected size --------- Signed-off-by: Kiersten Stokes <kierstenstokes@gmail.com> Co-authored-by: Suraj Subramanian <5676233+suraj813@users.noreply.github.com> Co-authored-by: Svetlana Karslioglu <svekars@fb.com>
malfet
added a commit
that referenced
this pull request
Apr 11, 2023
) * Fix kernel dimensions for LeNet model code example (#2192) * Change kernel to 5x5 in 1st Conv2d layer in model init Signed-off-by: Kiersten Stokes <kierstenstokes@gmail.com> * Change kernel to 5x5 in 2nd Conv2d layer in model init * Fix dimensions of 1st Linear layer to match new expected size --------- Signed-off-by: Kiersten Stokes <kierstenstokes@gmail.com> Co-authored-by: Suraj Subramanian <5676233+suraj813@users.noreply.github.com> Co-authored-by: Svetlana Karslioglu <svekars@fb.com> * Update pyspelling for all beginner tutorials in Python * Update * Update * Fix template tutorial, update gitignore * Apply suggestions from code review --------- Signed-off-by: Kiersten Stokes <kierstenstokes@gmail.com> Co-authored-by: Kiersten Stokes <kierstenstokes@gmail.com> Co-authored-by: Suraj Subramanian <5676233+suraj813@users.noreply.github.com> Co-authored-by: Nikita Shulga <nshulga@meta.com>
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.
Fixes #2104
In going through the YouTube Intro tutorial, I noticed that the dimensions in the LeNet diagram don't match up with code that immediately follows it. Namely, the kernel size should be 5x5 rather than the 3x3 that's given. (And I believe the same should be true for the second convolutional layer?) While not really necessary for the point the tutorial is making, it may reduce confusion for those with no experience with this model (myself included 😄). Especially when comparing with the same network in this blitz tutorial that has the correct kernel size.
cc @suraj813