A reimplementation of ArXiv paper 1712.00580 using TF 2.0's high level APIs.
- Implement model saving
- Implement test set metrics
Requires TF 2.0 and Python 3.
- Download the Fruits360 dataset.
- Place Training and Test folders within
pip install -r requirements.txt
cd model && python train.py
- Tensorboard logs will be under
TF 2.0 APIs Used
- lazy fetched dataset!
(pulled from the original paper)
I did not write the paper or create the dataset. Most of the work was done by the paper authors. I implemented their network in TF 2.0 using the Keras API as a learning exercise.