birm / models Goto Github PK

The mlpack models repository provides ready-to-use implementations of popular and cutting-edge machine learning models---mostly deep learning models. The implementations in this repository are intended to be compiled into command-line programs and bindings to Python and other languages.

(This README contains various TODO comments like this one , so if you are helping with the transition from the examples/ repository, be sure to look for comments like this one. Once the transition is done, we can remove this comment (and the others).)

(If we have functionality to download datasets and also to download pretrained model weights, we should put a comment about that here in the main description of the repository.)

(If this repository gets set up as a submodule to the main mlpack repository and that is how everything in it should be compiled, then we should point that out here!)

1. Introduction
2. Dependencies
3. Building-From-Source
4. Running Models
5. Current Models
6. Datasets

This repository contains a number of different models implemented in C++ using mlpack. To understand more about mlpack, refer to the mlpack repository or the mlpack website.

In order to compile and build the programs in this repository, you'll need to make sure that you have the same dependencies available that mlpack requires, in addition to mlpack itself.

(If this should only be built as a submodule, we should probably remove this part about dependencies and instruct users to build this as a submodule of the main mlpack repository.)

  mlpack
  Armadillo      >= 8.400.0
  Boost (program_options, math_c99, unit_test_framework, serialization,
         spirit) >= 1.58
  CMake          >= 3.3.2
  ensmallen      >= 2.10.0

To install mlpack refer to the installation guide that's available in the mlpack documentation.

All of those dependencies should be available in your distribution's package manager. If not, you will have to compile each of them by hand. See the documentation for each of those packages for more information.

To install this project run the following command.

mkdir build && cd build && cmake ../

Use the optional command -D DEBUG=ON to enable debugging.

Once CMake is configured, compile:

make

You can also build with multiple cores using the -j option. For example, building with 4 cores can be done with the following command:

make -j4

(This section needs significant overhaul once we clean up our build system.)

(This section also needs some cleanup once we know what we're keeping and what we're not keeping.)

Currently model-zoo project has the following models implemented:

• Simple Convolutional Neural Network on MNIST dataset.
• Multivariate Time Series prediction using LSTM on Google Stock Prices.
• Univariate Time Series prediction using LSTM on Electricity Consumption Dataset.
• Variational Auto-Encoder on MNIST dataset.
• Variational Convolutional Auto-Encoder on MNIST.

(This section will also need to be overhauled, but we should wait until we overhaul the sections above too.)

Model-Zoo project has the following datasets available:

MNIST("Modified National Institute of Standards and Technology") is the de facto “hello world” dataset of computer vision. Since its release in 1999, this classic dataset of handwritten images has served as the basis for benchmarking classification algorithms. As new machine learning techniques emerge, MNIST remains a reliable resource for researchers and learners alike.

Each image is 28 pixels in height and 28 pixels in width, for a total of 784 pixels in total. Each pixel has a single pixel- value associated with it, indicating the lightness or darkness of that pixel, with higher numbers meaning darker. This pixel- value is an integer between 0 and 255, inclusive. The training data set, (train.csv), has 785 columns. The first column, called "label", is the digit that was drawn by the user. The rest of the columns contain the pixel-values of the associated image. For more information refer to this MNIST Database.

Google Stock-Prices Dataset consists of stock prices for each day from 27th June, 2016 to 27th June, 2019. Each tuple is seperated from its adjacent tuple by 1 day. It consists of following rows that indicate opening, closing, volume and high and low of stocks associated with Google on that day.

Contains electricity consumption of a city for 2011 to 2012, where each tuple is seperated from its adjacent tuple by 1 day.
Each tuple has consumption in kWH and binary values for each Off-peak, Mid-peak, On-peak rows.