#create models and optimizers
def model_relu():
return Sequential(Linear(2,25),Relu(),Linear(25,25),
Relu(),Linear(25,25), Relu(),Linear(25,2))
def model_tanh():
return Sequential(Linear(2,25),Tanh(),Linear(25,25),
Tanh(), Linear(25,25), Tanh(),Linear(25,2))
def opti(model):
return Optimizer.SGD(model.param(),lr = lr)
def opti_mom(model):
return Optimizer.SGD(model.param(), lr = lr, momentum = True, mu = mu)
CE = Criterion.CrossEntropy()
MSE = Criterion.MSE()
##############################################################################
# test Relu vs Tanh with crossentropy
##############################################################################
test(model_relu, model_tanh, opti, opti, CE, CE, "relu", "tanh",
repetitions = rep, message = "Relu vs Tanh with crossentropy",
plots = plots, show_plots = show_plots, title_plots = "CE",
save_result_csv = save_csv, filename = "../results/csv/CE.csv")
###############################################################################
# test Relu vs Tanh with crossentropy and momentum
###############################################################################
#create model
model = Sequential(Linear(2, 25), Relu(), Linear(25, 25), Relu(),
Linear(25, 25), Relu(), Linear(25, 2))
#create data_sets with one hot encoding for MSE
train_input, train_target = generate_disc_data(one_hot_labels=True)
test_input, test_target = generate_disc_data(one_hot_labels=True)
#normalize the data
mean, std = train_input.mean(), train_input.std()
train_input.sub_(mean).div_(std)
test_input.sub_(mean).div_(std)
#define loss
criterion = Criterion.MSE()
#define optimizer
optim = Optimizer.SGD(parameters=model.param(), lr=1e-1)
#train the model
loss, accuracy = train(model,
criterion,
optim,
train_input,
train_target,
nb_epochs=200,
verbose=True)
#compute statistics on test
output = model.forward(test_input)
