smash.Net#

class smash.Net[source]#

Artificial Neural Network initialization.

Examples

>>> net = smash.Net()
>>> net
The network does not contain layers or has not been compiled yet
Attributes:
history

A dictionary saving the training and validation losses.

layers

List of Layer objects defining the graph of the network.

Methods

add(layer, options)

Add layers to the neural network.

compile([optimizer, options, random_state])

Compile the network and set optimizer.

copy()

Make a deepcopy of the Net.

set_trainable(trainable)

Method which enables to train or freeze the weights and biases of the network's layers.