Installation

This page covers installation steps that is:

1. git clone the code
2. Create Python virtualenv
3. Install requirements
4. Register and login to Neptune

Prerequisites

1. Python 3.5
2. Ubuntu OS (open solution is developed and tested on Ubuntu 16.04 machines only)

Get the code

Clone or download DSB open solution code. Type:

$ cd your/working/directory
$ git clone https://github.com/neptune-ml/data-science-bowl-2018

Note that you must have writing permission in your working directory.

Setup virtualenv

1. Create virtualenv:

$ cd your/working/directory
$ virtualenv dsb_open_solution -p python3.5

Note that you must have writing permission in your working directory.

2. Activate newly created environment:

$ source dsb_open_solution/bin/activate

Install PyTorch

DSB open solution uses PyTorch, which comes with GPU acceleration or without it. Note that it is highly recommended to train your solution on GPU. You can install PyTorch, by following PyTorch Get Started. Make sure that you picked python 3.5 and appropriate CUDA version (or no CUDA if you want to work on CPUs).

Install open solution requirements

While your environment is activated (check Setup virtualenv section), install remaining requirements:

$ cd path/to/open_solution/code
$ pip3 install -r requirements.txt

Register in Neptune (optional)

Neptune is our experiments monitoring system. It allows you to easily track the progress of your experiments and check intermediate results (check Image channel inside 😃).

To work with Neptune:

1. Go to https://neptune.ml/ and create your account.
2. Go to Neptune Dashboard and create a project called data_science_bowl with key DSB.
3. Any time you want to make sure you are logged in to Neptune, type:

$ neptune login

At this point you are all set 😃