change the val dataset sampler from sequential to deterministically shuffled #29
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
Closed
yangapku
changed the title
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Outdated suggestions cannot be applied.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.
改动前的代码，在模型finetune时，对于验证集使用分布式顺序读取的样本sampler（训练集则使用shuffle的分布式样本sampler）。如果验证集中，图文对原始标注存在一条文本对应多个图片（如MUGE），在卡数较少的情况下（如单卡或两卡），容易出现验证时一张GPU上的local batch内几个图文对样本的文本相同的情况。现在我们训练中计算的验证集inbatch accuracy，是最简单的以样本自身的图文作为ground truth的机制，不能正确处理local batch里面，文对图一对多的这种情况，会导致其验证集inbatch accuracy呈现结果偏低（参见issue #28 ）。但是模型本身的训练和收敛不受任何影响，也完全不影响最终模型的Recall效果指标，只是finetune过程中打印的inbatch accuracy结果偏低。 因此，我们将验证集也按照固定的随机种子进行shuffle，规避掉这种特殊情况，从而能使inbatch accuracy正确反映模型的训练趋势。