tied_weights=False)
train_2 = Train(
dA_1_out,
dA_2,
algorithm=sgd.SGD(learning_rate=.05, batch_size=10, termination_criterion=EpochCounter(30), cost=cost_ae.MeanSquaredReconstructionError(), monitoring_batches=5, monitoring_dataset=dA_1_out)
)
train_2.main_loop()
#######################
#### Fine tuning ####
#######################
### defining each layers ###
layer_1 = mlp.PretrainedLayer('layer_1', dA_1)
layer_2 = mlp.PretrainedLayer('layer_2', dA_2)
output_layer = mlp.Softmax(2, 'output', irange=.1)
### run fine tuning ###
layers = [layer_1, layer_2, output_layer]
main_mlp = mlp.MLP(layers, nvis=2)
train = Train(
dataset,
main_mlp,
algorithm=sgd.SGD(learning_rate=.05, batch_size=10, termination_criterion=EpochCounter(400), monitoring_batches=5, monitoring_dataset=dataset)
)
train.main_loop()
###################
#### Testing ####
###################
dataset.test(main_mlp)
from XOR import XOR ############################### #### Setting for dataset #### ############################### dataset = XOR() ########################## #### Setting for NN #### ########################## # create layers hidden_layer = mlp.Sigmoid(layer_name='hidden', dim=3, irange=.1, init_bias=1.) output_layer = mlp.Softmax(2, 'output', irange=.1) layers = [hidden_layer, output_layer] model = mlp.MLP(layers, nvis=2) #################### #### Training #### #################### train = Train( dataset, model, algorithm=sgd.SGD(learning_rate=.05, batch_size=10, termination_criterion=EpochCounter(400)) ) train.main_loop() ################# ### Testing ### ################# dataset.test(model)