facebookresearch / facebookresearch/moco
Question regarding the paper
Open
- Dominant language
- No language data
- Stars
- 5.1k
- Forks
- 802
- PR merge metrics
- No merged PRs in 30d
Description
Hey guys, awesome paper!
Am I correct to think of it as follows: at each iteration (for each sample in batch) we have 1 positive part ([augmented(image), augmented(image])) and 65k negative samples (the whole queue)?
Contributor guide
Assessment
This issue has not been assessed yet.