Keras has a very minimalist configuration file. Let's load it with a vi session. The parameters are very simple:
| Parameters | Values |
| image_dim_ordering | Can be either tf for the TensorFlow image ordering or th for Theano image ordering |
| epsilon | The epsilon value used during computation |
| floatx | Can be either float32 or float64 |
| backend | Can be either tensorflow or theano |
The image_dim_ordering of th value gives you a somewhat non-intuitive dimension ordering for images (depth, width, and height), instead of (width, height, and depth), for tf. The following are the default parameters in my machine:
If you install a GPU-enabled TensorFlow version, then Keras will automatically use your configured GPU when TensorFlow is selected as the backend.
