ZF/insightface
1
0
Fork 0
mirror of https://github.com/deepinsight/insightface.git synced 2025-12-30 08:02:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Jia Guo
2019-01-18 16:06:17 +08:00
committed by GitHub
parent 73e7ca01e9
commit 067f64815f
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
recognition/README.md
View File

@@ -51,14 +51,14 @@ This model can achieve *LFW 99.80+* and *MegaFace 98.3%+*.
CUDA_VISIBLE_DEVICES='0,1,2,3' python -u train.py --network r50 --loss cosface --dataset emore
```
(3). Train Softmax with MNasNet0.5-GDC.
(3). Train Softmax with MobileFaceNet.
```Shell
CUDA_VISIBLE_DEVICES='0,1,2,3' python -u train.py --network mnas05 --loss softmax --dataset emore
CUDA_VISIBLE_DEVICES='0,1,2,3' python -u train.py --network y1 --loss softmax --dataset emore
```
(4). Fine-turn the above Softmax model with Triplet loss.
```Shell
CUDA_VISIBLE_DEVICES='0,1,2,3' python -u train.py --network mnas05 --loss triplet --lr 0.005 --pretrained ./models/mnas05-softmax-emore,1
CUDA_VISIBLE_DEVICES='0,1,2,3' python -u train.py --network mnas05 --loss triplet --lr 0.005 --pretrained ./models/y1-softmax-emore,1
```