Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Question about the acc in log. #187

Closed
visionxyz opened this issue Apr 23, 2018 · 8 comments
Closed

Question about the acc in log. #187

visionxyz opened this issue Apr 23, 2018 · 8 comments

Comments

@visionxyz
Copy link

My acc is always like this "acc=0.144043", but the LFW Accuracy-Flip is already 0.99433+-0.00403, I don't change the code, is there anything wrong with my environment? Thanks!

@nttstar
Copy link
Collaborator

nttstar commented Apr 23, 2018

What are your network setting, training-data and batch-size respectively?

@visionxyz
Copy link
Author

I use CUDA_VISIBLE_DEVICES='0,1,2,3,4,5,6,7' python -u train_softmax.py --network r100 --loss-type 4 --margin-m 0.5 --data-dir ../datasets/faces_ms1m_112x112 --prefix ../model-r100 --lr 0.1 --per-batch-size 64

@KangolHsu
Copy link

I get the same error

INFO:root:Epoch[1] Batch [4900] Speed: 184.91 samples/sec acc=0.005469
INFO:root:Epoch[1] Batch [4920] Speed: 178.70 samples/sec acc=0.004883
INFO:root:Epoch[1] Batch [4940] Speed: 196.43 samples/sec acc=0.004102
INFO:root:Epoch[1] Batch [4960] Speed: 196.92 samples/sec acc=0.005859
INFO:root:Epoch[1] Batch [4980] Speed: 196.72 samples/sec acc=0.006250
INFO:root:Epoch[1] Batch [5000] Speed: 196.76 samples/sec acc=0.008008
INFO:root:Epoch[1] Batch [5020] Speed: 170.13 samples/sec acc=0.006055
INFO:root:Epoch[1] Batch [5040] Speed: 238.17 samples/sec acc=0.004883
INFO:root:Epoch[1] Batch [5060] Speed: 232.29 samples/sec acc=0.005273
INFO:root:Epoch[1] Batch [5080] Speed: 170.89 samples/sec acc=0.004883
INFO:root:Epoch[1] Batch [5100] Speed: 226.59 samples/sec acc=0.004297
INFO:root:Epoch[1] Batch [5120] Speed: 207.64 samples/sec acc=0.004297
lr-batch-epoch: 0.1 5137 1
testing verification..
(12000, 512)
infer time 43.11326
[lfw][20000]XNorm: 23.841703
[lfw][20000]Accuracy-Flip: 0.93500+-0.01698
testing verification..
(14000, 512)
infer time 53.073712
[cfp_fp][20000]XNorm: 21.599537
[cfp_fp][20000]Accuracy-Flip: 0.67171+-0.01099
testing verification..
(12000, 512)
infer time 44.275807
[agedb_30][20000]XNorm: 22.780737
[agedb_30][20000]Accuracy-Flip: 0.76767+-0.02175
[20000]Accuracy-Highest: 0.76767

@USTCSQQ
Copy link

USTCSQQ commented Aug 7, 2018

@KangolHsu @blessxu I have the same problem with you,have you solve it?

@shaoxiang
Copy link

@USTCSQQ @KangolHsu @blessxu The same problem, has anyone solved it?

@yxchng
Copy link

yxchng commented Mar 6, 2019

@blessxu @KangolHsu @USTCSQQ @shaoxiang Have you solved the problem? Is the code wrong?

@rocinant
Copy link

same problem here.

@ayush431
Copy link

[40]Accuracy-Highest:1.00000
getting this every time while runnig verifictaion ??
anyone can tell what's wrong here??

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

8 participants