Skip to content

dxlnr/dps

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Digital Product School

This work is done for the Digital Product School in Munich. In order to apply for the position of Artificial Intelligence Engineer, this repository is provided. The challenge is to use the Auto MPG dataset from Kaggle (https://www.kaggle.com/uciml/autompg-dataset) to predict the fuel efficiency of a vehicle using a basic regression with TensorFlow.

Installation

Create a new conda environment:

conda create -n tensor python=3.8
source activate tensor

Download and install the package:

git clone https://github.com/frommwonderland/dps.git
cd dps
pip install --upgrade pip
pip install -r requirements.txt

Running

Running the little program by simply

python main.py

Results

The main goal is to predict the 'mpg' parameter based on various others as fuel efficiency (MPG) is a function of many different other parameters. The first image shows some general information about the data.

The model is a simple multi-layer-perceptron. One example run with the loss and the result is shown in the following:

MPG prediction: 13.5

About

Using Auto MPG dataset from Kaggle to predict the fuel efficiency of a vehicle using a basic regression with TensorFlow

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages