update default parameters as suggested in #1606 #1611
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
fmassa
approved these changes
Nov 25, 2019
There was a problem hiding this comment.
Thanks a lot!
Can you also create a README in this folder in a follow-up PR with commands used to run the code, similar to https://github.com/pytorch/vision/tree/master/references/classification?
|
Sure, I sent a follow-up PR #1612 :) |
fmassa
pushed a commit
to fmassa/vision-1
that referenced
this pull request
Dec 18, 2019
facebook-github-bot
pushed a commit
that referenced
this pull request
Dec 19, 2019
Summary: Pull Request resolved: #1684 Reviewed By: cpuhrsch Differential Revision: D19156997 Pulled By: fmassa fbshipit-source-id: dca753d7e1e9041a9973f0c45a8046358e687188
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Outdated suggestions cannot be applied.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.
As discussed in #1606 the default hyperparameters in detection/train.py are different from those used to train Faster/Mask/Keypoint R-CNNs.
Following a PR suggestion from @fmassa, I updated the default hyperparameters, and added some comments so that we can have a better idea as we train them by ourselves e.g., using different datasets, models, etc.
Thank you!