ZF/insightface
1
0
Fork 0
mirror of https://github.com/deepinsight/insightface.git synced 2026-05-20 00:10:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Jia Guo
2021-05-08 11:39:33 +08:00
committed by GitHub
parent a4f83a4209
commit 7fdffa261d
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
challenges/iccv21-mfr/README.md
View File

@@ -88,8 +88,10 @@ Inference time was evaluated on Tesla V100 GPU, using onnxruntime-gpu==1.6.
6. Matching score is measured by cosine similarity.
7. Model size should be not larger than 1GB.
8. For Track A: feature length should be not larger than 512, and the inference time should be not larger than 10ms on Tesla V100 GPU.
9. For Track A: feature length should be not larger than 1024, and the inference time should be not larger than 20ms on Tesla V100 GPU.
9. For Track B: feature length should be not larger than 1024, and the inference time should be not larger than 20ms on Tesla V100 GPU.
10. The input size of submission model should be 112x112.
11. Online evaluation server uses onnxruntime-gpu==1.6, cuda==10.2, cudnn==8.0.5.
## Submission
Coming soon