Check python version 3.7.6
pip3 install virtualenv
virtualenv venv --python=python3
source venv/bin/activate
pip3 install -r requirements.txt
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.
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.
Currently, top accuracy for the binary classification problem is at 0.9305 for the validation set.