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

there is no _caffe.so after make pycaffe #11

Closed
maolin23 opened this issue Jul 18, 2016 · 5 comments
Closed

there is no _caffe.so after make pycaffe #11

maolin23 opened this issue Jul 18, 2016 · 5 comments

Comments

@maolin23
Copy link

maolin23 commented Jul 18, 2016

hi,

When I

make all
make test
make pycaffe

there is no _caffe.so in caffe-dilation/python/caffe

and I try the predict.py
there is an error
ImportError: libcaffe.so.1.0.0-rc3: cannot open shared object file: No such file or directory

I have already added the build_master/python into my PYTHONPATH

Does anyone know how to solve this problem?

Cheers,
Mao

@fyu
Copy link
Owner

fyu commented Jul 19, 2016

is there _caffe.so in build_master/python?

@maolin23
Copy link
Author

maolin23 commented Jul 19, 2016

thanks to your reply!

yes,
but when I copy _caffe.so to caffe-dilation/python/caffe
the errror is
ImportError: libcaffe.so.1.0.0-rc3: cannot open shared object file: No such file or directory

if i don't copy _caffe.so to caffe-dilation/python/caffe
the error is
ImportError: no module named _caffe

@maolin23
Copy link
Author

solve!!
I do this
export LD_LIBRARY_PATH={CAFFE-DILATION_DIR}/build_master/lib:${LD_LIBRARY_PATH}

but i have another question about the image list
the images in the image list are original or they are padded to 900*900?
or i should do anything else to the images?

@fyu
Copy link
Owner

fyu commented Jul 19, 2016

The input images for training and testing should be original.

@fyu fyu closed this as completed Jul 19, 2016
@maolin23
Copy link
Author

Sorry, I have another question
Could you tell me about the loss during training?
When I use your code to training, my loss is about 2、3 in the first 15 iteration.
After that, my loss increase to 50 ~ 80 and be stabled.
After 20K iterations, it is still about 60~80.
I'm not sure the correctness of this situation....
Could you tell me this situation is normal or not?
What loss is correct?
(My training/testing input images are all original.)

Thanks a lot,
Mao

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