deepinsight / deepinsight/insightface
How to perform evaluate_1N on "out of memory" datasets?
Open
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
Hello everyone,
I am having a scenario where gallery contains 10000 Identities,and probe is from the megaface testset. Lets say i take a subset,around 50000 of these Identities for testing,i am getting out of memory error to store a 50000x10000 matrix. How to handle such large scale datasets? Is there any implementation for Identification & Verification evaluation in python ?
regards
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.