Implementation Issue for VQA

1. Jupyter Setup Issue


Traceback (most recent call last):
  File "/usr/local/bin/jupyter-notebook", line 7, in <module>
    from notebook.notebookapp import main
  File "/usr/local/lib/python2.7/dist-packages/notebook/",
line 45, in <module>
    raise ImportError(msg + ", but you have %s" % tornado.version)
ImportError: The Jupyter Notebook requires tornado >= 4.0, but you have 3.1.1
Answer: This problem will be seen, if u have installed both ipython-notebook and 

$It can be solved  by  uninstalling  ipython -notebook.

2. CuDNN problems

user@user-XPS-8500:~/neural-style$ th neural_style.lua -gpu 0 -backend cudnn
/home/user/torch/install/bin/luajit: /home/user/torch/install/share/lua/5.1/trepl/init.lua:384: /home/ben/torch/install/share/lua/5.1/trepl/init.lua:384: /home/user/torch/install/share/lua/5.1/cudnn/ffi.lua:1279: 'libcudnn (R4) not found in library path.
Please install CuDNN from
Then make sure files named as or libcudnn.4.dylib are placed in your library load path (for example /usr/local/lib , or manually add a path to LD_LIBRARY_PATH)

stack traceback:
    [C]: in function 'error'
    /home/user/torch/install/share/lua/5.1/trepl/init.lua:384: in function 'require'
    neural_style.lua:64: in function 'main'
    neural_style.lua:500: in main chunk
    [C]: in function 'dofile'
    .../user/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:145: in main chunk
    [C]: at 0x00406670
& Solution

After registering as a developer with NVIDIA, you can download cuDNN here. Make sure to download Version 4.

After dowloading, you can unpack and install cuDNN like this:

tar -xzvf cudnn-7.0-linux-x64-v4.0-prod.tgz
sudo cp cuda/lib64/libcudnn* /usr/local/cuda-7.0/lib64/
sudo cp cuda/include/cudnn.h /usr/local/cuda-7.0/include/

Also check your LD_LIBRARY_PATH:


You should see /usr/local/cuda-7.0/lib64 along with possibly other things.

if ur not getting like this then do

You need to add something like this to your .bashrc or other startup scripts.

export LD_LIBRARY_PATH=/usr/local/cuda-7.0/lib64:$LD_LIBRARY_PATH

then source ~/.bashrc.

Which can solve the problem.



One thought on “Implementation Issue for VQA

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s