Simulated+Unsupervised (S+U) in TensorFlow

TensorFlow implementation of Learning from Simulated and Unsupervised Images through Adversarial Training.

(in progress)

Requirements

• Python 2.7
• TensorFlow 0.12.0+
• SciPy
• pillow
• tqdm

Usage

To generate synthetic dataset:

1. Run UnityEyes with changing Camera parameters to [0, 0, 20, 40].
2. ...

To train a model:

$ python main.py --data_set gaze
$ python main.py --data_set hand

To test with an existing model:

$ python main.py --data_set gaze --test
$ python main.py --data_set hand --test

Results

(in progress)

Author

Taehoon Kim / @carpedm20