Keras¶
Higher-level layer abstractions built on TF Encrypted.
-
class
tf_encrypted.keras.Sequential(layers=None, name=None)[source]¶ Model defined by a stack of layers in sequence.
TODO
-
add(layer)[source]¶ Adds a layer instance on top of the layer stack.
- Parameters
layer – layer instance.
- Raises
TypeError – If layer is not a layer instance.
ValueError – In case the layer argument does not know its input shape.
ValueError – In case the layer argument has multiple output tensors, or is already connected somewhere else (forbidden in Sequential models).
-
call(inputs, training=None, mask=None)[source]¶ This is where the layer’s logic lives. :param inputs: Input tensor, or list/tuple of input tensors.
- Returns
A tensor or list/tuple of tensors.
-
compile(optimizer, loss)[source]¶ Configures the model for training.
- Parameters
optimizer – Optimizer instance
loss – Objective function
-
fit(x, y, epochs=1, steps_per_epoch=1)[source]¶ Trains the model for a given number of epochs (iterations on a dataset).
- Parameters
x – Private tensor of training data
y – Private tensor of target (label) data
epochs – Integer. Number of epochs to train the model.
steps_per_epoch – Integer. Total number of steps (batches of samples) before declaring one epoch finished and starting the next epoch.
-
fit_batch(x, y)[source]¶ Trains the model on a single batch.
- Parameters
x – Private tensor of training data
y – Private tensor of target (label) data
-
classmethod
from_config(config)[source]¶ Instantiates a TFE Keras model from its config.
- Parameters
config – Configuration dictionary matching the output of model.get_weights().
- Returns
A TFE Keras Sequential instance.
-
property
layers¶ Historically, sequential.layers only returns layers that were added via add, and omits the auto-generated InputLayer that comes at the bottom of the stack.
-