This repository has been archived by the owner on Nov 17, 2023. It is now read-only.
Rebase #13757 to master #15189
Merged
Rebase #13757 to master #15189
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
https://github.com/apache/incubator-mxnet/blob/a38278ddebfcc9459d64237086cd7977ec20c70e/example/image-classification/train_imagenet.py#L42 When I try to train imagenet with this line commented, the train-accuracy reaches 99% while the validation-accuracy is only less than 50% (single machine, 8 GPUs, global batchsize=2048, Resnet50). Absolutely this is overfitting. Then I uncomment this line and try again with the same experiment settings. This time both train and validation accuracy converge to about 70%. Thus, it seems that this data augmentation is pretty important for ImageNet training. Perhaps it will be better to uncomment this as default, so that future developers won't get confused by the over-fit issue.
|
@ymjiang Can you make the PR title a bit more descriptive please ? |
|
@ymjiang Can you please retrigger CI build? |
|
@Roshrini Hi, I closed the issue and reopened it. Is that the correct way to re-trigger CI build? |
|
@mxnet-label-bot add [pr-awaiting-merge] |
|
Thanks for your contribution! |
shuo-ouyang
reviewed
May 28, 2021
| @@ -56,6 +54,8 @@ def set_imagenet_aug(aug): | |||
| dtype = 'float32' | |||
| ) | |||
| args = parser.parse_args() | |||
There was a problem hiding this comment.
Maybe we should rearrange line 56-58? It looks like set_imagenet_aug() does nothing on args.
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Description
This is a rebase version of https://github.com/apache/incubator-mxnet/pull/13757
Details
https://github.com/apache/incubator-mxnet/blob/a38278ddebfcc9459d64237086cd7977ec20c70e/example/image-classification/train_imagenet.py#L42
When I try to train imagenet with this line commented, the train-accuracy reaches 99% while the validation-accuracy is only less than 50% (single machine, 8 GPUs, global batchsize=2048, Resnet50, fp32). Absolutely this is overfitting.
Then I uncomment this line and try again with the same experiment settings. This time both train and validation accuracy converge to about 66%, which looks like normal result.
Thus, it seems that this data augmentation is pretty important for ImageNet training. Perhaps it will be better to uncomment this as default, so that future developers won't get confused by the overfitting issue.
My commits enable data-augmentation with command-line argument.