Skip to content

Latest commit

 

History

History
33 lines (21 loc) · 1.49 KB

README.md

File metadata and controls

33 lines (21 loc) · 1.49 KB

Practice CNNs with Destiny 2 🌎 🌌

destiny

The purpose of this repository is practice design and construction of Convolutional neural networks(CNN) using a dataset created from Destiny 2 website is expected 4 projects using the same datasets or derivatives,if you have any suggestions you can write to me

Project 1

The objective of this project is the classification of the armors of Destiny 2 game in 4 types of armors using a Convolutional neural network(CNN)

  • Arms
  • Chest
  • Helmet
  • Legs

The model was trained in a GPU 1660 Super using Python 3.7.4 🐍 and Keras

The images are like this... Examples

The plot of the training result is the next...

The accuracy in the test set was of 95.78%

plot

The structure of the prediction model used is...

modelplot

The prediction results are the following images..

res1

res2