Skip to content

qx-teo/self-training-image-rec

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

self-training-image-rec

Setup:

Check python version 3.7.6

pip3 install virtualenv
virtualenv venv --python=python3
source venv/bin/activate
pip3 install -r requirements.txt

Running

Running tutorial.py runs through a code tutorial of tensorflow for an image classifier for dogs and cats.

Running data/stl10_input.py will download the stl10 dataset and save it to disk. It also contains various utils for loading the dataset in python.

Running Train.py will train a model using the train/test split for the stl10 dataset. Currently, it solves the binary classification problem between animal and machine.

TODO

Save / load model to disk.

Incorporate data augmentation steps featured in tutorial.py to increase performance.

Implement self-training data augmentation.

Implement variable learning rate.

Results

Currently, top accuracy for the binary classification problem is at 0.9305 for the validation set.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%