VQA Slides

github VQA

https://github.com/JamesChuanggg/awesome-vqa

https://github.com/ChristosChristofidis/awesome-deep-learning

https://github.com/k-kawakami/vqa

https://github.com/VT-vision-lab

http://www.visualqa.org/download.html

https://github.com/jiasenlu/HieCoAttenVQA

https://github.com/soumith/cudnn.torch

https://github.com/JamesChuanggg/awesome-vqa

https://github.com/iamaaditya/VQA_Demo

https://github.com/kevjshih/wtl_vqa


 

 

Torch

https://github.com/torch/torch7/wiki/Cheatsheet

http://torch.ch/docs/getting-started.html#_

Optimizing Recurrent Neural Networks in cuDNN 5

http://korbonits.github.io/2015/06/28/Torch-bleeding-edge-DNN-research.html

https://github.com/kjw0612/awesome-rnn

https://github.com/Element-Research/rnn

https://github.com/jcjohnson/torch-rnn

https://github.com/lisa-lab/DeepLearningTutorials

http://deeplearning.net/tutorial/

http://deeplearning.net/tutorial/logreg.html#logreg

https://www.lua.org/wshop13/Muhammad.pdf

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

http://arxiv.org/pdf/1511.02274.pdf

 

Reference

Mat_1

Learning to Answer Questions from Image Using Convolutional Neural Network Lin Ma, Zhengdong Lu, and Hang Li Huawei Noah’s Ark Lab, Hong Kong

http://slideplayer.com/slide/10879690/

 

http://www.ee.cuhk.edu.hk/~lma/

http://conviqa.noahlab.com.hk/project.html

 



Mat_2

https://github.com/imatge-upc/vqa-2016-cvprw

http://imatge-upc.github.io/vqa-2016-cvprw/

 


 

https://www.google.co.in/imgres?imgurl=https%3A%2F%2Fcamo.githubusercontent.com%2Fc369855a52126470fe0435552166b84a38715489%2F687474703a2f2f692e696d6775722e636f6d2f555841506c71652e706e67&imgrefurl=https%3A%2F%2Fgithub.com%2Fabhshkdz%2Fneural-vqa&docid=IqAeHJEcc6DfAM&tbnid=NXS6zgVSVhPd-M%3A&w=584&h=361&ved=0ahUKEwjJtKe4nJjOAhWMvY8KHcxIBfQ4ZBAzCDooODA4&iact=mrc&uact=8&biw=1329&bih=683#h=361&imgdii=NXS6zgVSVhPd-M%3A%3BNXS6zgVSVhPd-M%3A%3BNMiGtNdrUsY20M%3A&w=584


 

https://www.google.co.in/search?q=Hierarchical+Question-Image+Co-Attention+for+Visual+Question+Answering&source=lnms&tbm=isch&sa=X&ved=0ahUKEwjYk7fesJjOAhWMpY8KHcG_CBkQ_AUICCgB&biw=1329&bih=683

 

https://www.google.co.in/imgres?imgurl=http%3A%2F%2Fimage.slidesharecdn.com%2Fnlpguestlect15-151203142113-lva1-app6891%2F95%2Fdeep-learning-for-natural-language-processing-word-embeddings-80-638.jpg%3Fcb%3D1449152666&imgrefurl=http%3A%2F%2Fwww.slideshare.net%2Froelofp%2Fdeep-learning-for-natural-language-processing-word-embeddings&docid=TjT-MXx3yMsFuM&tbnid=leFymavoSEIF0M%3A&w=638&h=479&ved=0ahUKEwiL5e_osJjOAhVLpY8KHetmBAkQMwhoKDowOg&iact=mrc&uact=8&biw=1329&bih=683#h=479&imgdii=leFymavoSEIF0M%3A%3BleFymavoSEIF0M%3A%3BKsCSlq-Ks6ildM%3A&w=638

 

 

https://www.google.co.in/imgres?imgurl=https%3A%2F%2Fai2-s2-public.s3.amazonaws.com%2Ffigures%2F2016-03-25%2F228db5326a10cd67605ce103a7948207a65feeb1%2F2-Figure4-1.png&imgrefurl=https%3A%2F%2Fwww.semanticscholar.org%2Fpaper%2FStacked-Attention-Networks-for-Image-Question-Yang-He%2F228db5326a10cd67605ce103a7948207a65feeb1&docid=ZPEEiBq9aWESpM&tbnid=1SZLW08T6gs6ZM%3A&w=731&h=439&ved=0ahUKEwiL5e_osJjOAhVLpY8KHetmBAkQMwgnKAkwCQ&iact=mrc&uact=8&biw=1329&bih=683

https://www.google.co.in/imgres?imgurl=http%3A%2F%2Fimages.slideplayer.com%2F39%2F10879690%2Fslides%2Fslide_6.jpg&imgrefurl=http%3A%2F%2Fslideplayer.com%2Fslide%2F10879690%2F&docid=WxeUW9VwToZVuM&tbnid=FnG-nmooYcGiBM%3A&w=960&h=720&ved=0ahUKEwjJtKe4nJjOAhWMvY8KHcxIBfQ4ZBAzCAYoBDAE&iact=mrc&uact=8&biw=1329&bih=683

 

http://arxiv.org/pdf/1604.01485.pdf

http://arxiv.org/pdf/1511.02274.pdf

 

 

 

CuDNN problems

 


 

user@user-XPS-8500:~/neural-style$ th neural_style.lua -gpu 0 -backend cudnn
nil 
/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 https://developer.nvidia.com/cuDNN
Then make sure files named as libcudnn.so.4 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
user@user-XPS-8500:~/neural-style$ 
-----------------------------------------------

Solution

https://github.com/jcjohnson/neural-style/blob/master/INSTALL.md

https://github.com/jcjohnson/neural-style/issues/154

Advertisements

Leave a Reply

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

WordPress.com Logo

You are commenting using your WordPress.com 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 )

Google+ photo

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

Connecting to %s