deepinsight / deepinsight/insightface
how many datasets to evalution? 3.1 LResNet100E-IR,ArcFace@ms1m-refine-v2
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
How much megaface data is used for testing？
I have test **`LResNet100E-IR,ArcFace@ms1m-refine-v2`** in model zoon,
however I just get rank 1: 0.059101, however the result l in model zoon is heigher.
pelease help me to understand it, Thanks so much.
```
Done matching! Score matrix size: 3530 1000000
Saving to ../../insight_r100_results/otherFiles/facescrub_megaface_insight_r100_1000000_1.bin
Computing test results with 1000000 images for set 1
Loaded 3530 probes spanning 80 classes
Loading from ../../insight_r100_results/otherFiles/facescrub_facescrub_insight_r100.bin
Probe score matrix size: 3530 3530
distractor score matrix size: 3530 1000000
Done loading. Time to compute some stats!
Finding top distractors!
Done sorting distractor scores
Making gallery!
Done Making Gallery!
Allocating ranks (1000080)
Rank 1: 0.059101
``` @yingfeng @nttstar @ppwwyyxx @leondgarse @jiankangdeng
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.