Open
Conversation
Collaborator
|
잘 적어주셨습니다! inductive bias로 인한 데이터 효율성이라는 ResNet만의 장점이 있죠. 수고하셨습니다 예정님~ |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
pretrained=False로 설정했을 때 정확도가 89.8%(True)에서 50.5%(False)로 급격히 하락했다. 초기 1 epoch 학습량만 비교해도 88% vs 42%로 큰 차이가 났다. 그 이유는 ViT가 Inductive Bias가 부족한 구조이기 때문이다. CNN처럼 이미지의 특성을 자동으로 잘 잡아내지 못하기 때문에 Large-scale Data를 통해 이미지를 보는 법을 미리 엄청나게 학습시켜 놓지 않으면 CIFAR-10 같은 작은 데이터만으로는 모델이 수렴하기 어렵고 성능이 나오지 않는다.