-
Notifications
You must be signed in to change notification settings - Fork 5.5k
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
Comments
What are your network setting, training-data and batch-size respectively? |
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 |
I get the same error INFO:root:Epoch[1] Batch [4900] Speed: 184.91 samples/sec acc=0.005469 |
@KangolHsu @blessxu I have the same problem with you,have you solve it? |
@USTCSQQ @KangolHsu @blessxu The same problem, has anyone solved it? |
@blessxu @KangolHsu @USTCSQQ @shaoxiang Have you solved the problem? Is the code wrong? |
same problem here. |
[40]Accuracy-Highest:1.00000 |
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!
The text was updated successfully, but these errors were encountered: