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

How to use it? #1

Closed
yzk0281 opened this issue Apr 28, 2016 · 8 comments
Closed

How to use it? #1

yzk0281 opened this issue Apr 28, 2016 · 8 comments

Comments

@yzk0281
Copy link

yzk0281 commented Apr 28, 2016

Hello,
how to use your tripletloss python layer?
I 'make pycaffe' and put the folder 'tripletloss' in /usr/lib/python2.7/dist-packages,
but when I start to train with tripletloss-master/example_layer/model/solver.prototxt,
it says:
Creating layer norm2
ImportError: No module named tripletloss.norm2layer
Could give me some advise please?

@yzk0281
Copy link
Author

yzk0281 commented Apr 28, 2016

I also tried :
make distribute
and:
export PYTHONPATH=/root/cnn/caffe-master/distribute/python:$PYTHONPATH
in ~/.bashrc
source ~/.bashrc

@luhaofang
Copy link
Owner

Hi,
You may insert folder path to your PYTHONPATH path.

import sys
sys.path.insert(0,'$ your tripletloss root path $')

@yzk0281
Copy link
Author

yzk0281 commented Apr 28, 2016

still same problem...I train it via this :
./build/tools/caffe train -solver python/tripletloss-master/example_layer/model/solver.prototxt -weights examples/vgg_face_caffe/VGG_FACE.caffemodel
is it ok?

@luhaofang
Copy link
Owner

Please ,try train.py

@yzk0281
Copy link
Author

yzk0281 commented Apr 28, 2016

ok...

@yzk0281
Copy link
Author

yzk0281 commented Apr 28, 2016

Did you trained VGGFACE with it? How is the accuracy?

@luhaofang
Copy link
Owner

Maybe I'll give you my proposal's result,several days' later~ : )

@yzk0281
Copy link
Author

yzk0281 commented Apr 28, 2016

cool~

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

2 participants