Setup IRC Channel

Make sure you refer my previous post on getting started with IRC. This is a quick guide to create a channel on Freenode. Step 1: Eligibility Freenode is primarily a network for people involved in open source software. Read Freenode's guidelines to determine whether you are on topic before getting started. Although we are a... Continue Reading →


C++ Modern Formatting Library (cppformat) Setup

String formatting is a core need in whatever code you write. You always want your printed content should appear as intended and especially when printing stuff like date and time. If you use iostream you know how painful it is to format strings and so many still use printf. Unfortunately printf comes with lot of... Continue Reading →

Oh-my-zsh and Powerline Fonts setup for Awesome Terminal in Ubuntu 16.04

Step 1: Installing General Requirements Install Git sudo apt-get install git Install Curl sudo apt-get install curl Install pip curl --silent --show-error --retry 5 | sudo python2.7 Features: It is written in Python language, which makes it extensible and feature rich. Stable and testable code base, which works well with Python 2.6+ and Python... Continue Reading →

Installing NVIDIA Drivers and CUDA 8 Toolkit on Ubuntu 16.04

Step 1: Update and upgrade your system apt-get update && apt-get upgrade -y Step 2: Install Linux Headers (for installing aptitude "apt install aptitude") aptitude -r install linux-headers-$(uname -r) Step 3: apt-get purge nvidia-* Step 4: add-apt-repository ppa:graphics-drivers/ppa Step 5: apt-get update Step 6: apt-get install nvidia-375 Step 7: Create a file and paste the... Continue Reading →

Installing TensorFlow GPU version on Ubuntu 16.04

NVIDIA requirements to run TensorFlow with GPU support CUDA┬« Toolkit 8.0. For details, see NVIDIA's documentation. Ensure that you append the relevant Cuda pathnames to the LD_LIBRARY_PATH environment variable as described in the NVIDIA documentation. The NVIDIA drivers associated with CUDA Toolkit 8.0. cuDNN v5.1. For details, see NVIDIA's documentation. Ensure that you create the... Continue Reading →

Setup DIGITS (Deep Learning GPU Training System) on Ubuntu 16.04

DIGITS (the Deep Learning GPU Training System) is a webapp for training deep learning models. The currently supported frameworks are: Caffe, Torch, and Tensorflow. Since DIGITS itself is a pure Python project, installation is usually pretty trivial regardless of the platform. The difficulty comes from installing all the required dependencies for Caffe and/or Torch7 and... Continue Reading →

Setup char-rnn and torch-rnn for character level language model in Torch

Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch Requirements This code is written in Lua and requires Torch. So Follow the tutorial provided in my previous blog post for installing Torch. Lua Pre-requisite # Install most things using luarocks luarocks install torch luarocks install nn luarocks install optim luarocks... Continue Reading →

Installing Overfeat: CNN based feature extractor and classifier on Ubuntu 16.04

Step 1: Download the archive from the link below Step 2: Extract and prepare tar -xvzf overfeat-v04-2.tgz cd overfeat python git pull Step 3: A simple test of the pre-compiled binaries can be done with following command #for 64bit OS ./bin/linux_64/overfeat -n 3 samples/bee.jpg Step 3: Overfeat can run without BLAS, however it... Continue Reading →

Setup Theano and Keras with CUDA support on Ubuntu 16.04

Make sure you have installed Nvidia drivers and cuda toolkit on your system. Also follow caffe setup for preliminary setup of libraries. Step 1: Install Dependencies sudo apt-get install python-numpy python-scipy python-dev python-pip python-nose g++ libopenblas-dev liblapack-dev gfortran git Step 2: Now Install Theano sudo pip install Theano Step 3: Work around for a glibc... Continue Reading →

Blog at

Up ↑

%d bloggers like this: