Visual Question Answering 3

on VQA, DNN, RNN, CNN, Python, spaCy

Prepare for VQA in Ubuntu 14.04 x64 based on the project.
In this post, I’ll talk about installing spaCy, scikit-learn, progressbar to Ubuntu 14.04 x64, and clone the project from github.
spaCy is a library for industrial-strength natural language processing in Python and Cython.
scikit-learn is simple and efficient tools for data mining and data analysis.
progressbar is text progress bar library for Python.

Install spaCy with conda

$ conda install -c https://conda.anaconda.org/spacy spacy
$ conda install spacy
$ python -m spacy.en.download all --force

Install scikit-learn with conda

$ conda install scikit-learn

Install progressbar with pip

$ pip install progressbar

Clone the project from github and try example

# move to workspace and ..
$ git clone https://github.com/avisingh599/visual-qa.git
$ cd visual-qa/scripts
$ sh get_started.sh
error and solution
error
./download.sh: line 5: unzip: command not found
solution
$ sudo apt-get install unzip
error
Cloning into 'VQA'...
Warning: Permanently added the RSA host key for IP address '192.30.252.129' to the list of known hosts.
Permission denied (publickey).
fatal: Could not read from remote repository.

Please make sure you have the correct access rights
solution
# Change the ssh url to https url at visual-qa/3rdParty/download.sh

git clone git@github.com:VT-vision-lab/VQA.git
↓
git clone https://github.com/VT-vision-lab/VQA.git
error
IOError: [Errno 2] No such file or directory: u'~/miniconda2/lib/python2.7/site-packages/spacy/en/data/vocab/tag_map.json'
solution
$ python -m spacy.en.download all --force



References