def WalkThroughAllOptimizers(option):
dataReader = DataReader(x_data_name, y_data_name)
XData,YData = dataReader.ReadData()
X = dataReader.NormalizeX()
Y = dataReader.ToOneHot()
n_input, n_output = dataReader.num_feature, dataReader.num_category
n_hidden = 8
eta, batch_size, max_epoch = option[1], 10, 10000
eps = 0.06
params = HyperParameters41(n_input, n_output, n_hidden,
eta, max_epoch, batch_size, eps,
LossFunctionName.CrossEntropy3,
InitialMethod.Xavier,
option[0])
loss_history = CLossHistory()
net = TwoLayerClassificationNet()
#ShowData(XData, YData)
net.train(dataReader, params, loss_history)
trace = loss_history.GetMinimalLossData()
print(trace.toString())
title = loss_history.ShowLossHistory(params)
print("wait for 10 seconds...")
wbs_min = WeightsBias30(params)
wbs_min.W1 = trace.dict_weights["W1"]
wbs_min.W2 = trace.dict_weights["W2"]
wbs_min.B1 = trace.dict_weights["B1"]
wbs_min.B2 = trace.dict_weights["B2"]
ShowAreaResult(X, wbs_min, net, title)
ShowData(X, YData)
dict_cache = net.ForwardCalculationBatch3(input, wb1, wb2)
Z[0,i,j] = dict_cache["Output"][0,0]
Z[1,i,j] = dict_cache["Output"][1,0]
Z[2,i,j] = dict_cache["Output"][2,0]
# end if
# end for
# end for
return X,Y,Z
if __name__ == '__main__':
dataReader = DataReader(x_data_name, y_data_name)
dataReader.ReadData()
X = dataReader.NormalizeX()
Y = dataReader.ToOneHot()
n_input, n_output = dataReader.num_feature, dataReader.num_category
n_hidden = 3
eta, batch_size, max_epoch = 0.1, 10, 10000
eps = 0.01
params = CParameters(n_input, n_hidden, n_output, eta, max_epoch, batch_size, eps, LossFunctionName.CrossEntropy3)
loss_history = CLossHistory()
net = TwoLayerClassificationNet()
#ShowData(XData, YData)
wb1, wb2 = net.train(dataReader, params, loss_history, net.ForwardCalculationBatch3)