Skip to content

Experimentation with TensorFlow and CNNs to identify Pokémon's.

Notifications You must be signed in to change notification settings

boasmeier/cnn-pokedex

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CNN-Pokedex

A smallerVGGNet-Model (pyimagesearch.com) was trained to classify five diefferent pokemons (pikachu, bulbasaur, charmander, mewtwo, squirtle). You can either start the GUI or run the classify.py script in the CLI.

Train

The python script train.py creates a trained model, a lb.pickle file and polts the train results.

python train.py --dataset [path to dataset] --model [name of model to create] --labelbin [name of lb.pickel to create]

Example:

python train.py --dataset dataset --model pokedex.model --labelbin lb.pickle

Classify

The script classify.py classifies an example image and shows the image with the result.

python classify.py --model [path to trained model] --labelbin [path to pickle file] --image [path to image]

Example:

python classify.py --model pokedex.model --labelbin lb.pickle --image examples\pikachu.png

GUI

The script index.py starts the GUI.


gui

This project was built following along this tutorial: https://www.pyimagesearch.com/2018/04/16/keras-and-convolutional-neural-networks-cnns/

About

Experimentation with TensorFlow and CNNs to identify Pokémon's.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages