def train(dataReader, max_epoch):
n_input = dataReader.num_feature
n_hidden = 2
n_output = 1
eta, batch_size = 0.1, 5
eps = 0.01
hp = HyperParameters20(n_input, n_hidden, n_output, eta, max_epoch, batch_size, eps, NetType.BinaryClassifier, InitialMethod.Xavier)
net = NeuralNet20(hp, "Arc_221_epoch")
#net.LoadResult()
net.train(dataReader, 5, True)
#net.ShowTrainingTrace()
ShowTransformation(net, dataReader, max_epoch)
ShowResult2D(net, dataReader, max_epoch)
# draw train data
X, Y = dataReader.XTrain, dataReader.YTrain
plt.plot(X[:, 0], Y[:, 0], '.', c='b')
# create and draw visualized validation data
TX = np.linspace(0, 1, 100).reshape(100, 1)
TY = net.inference(TX)
plt.plot(TX, TY, 'x', c='r')
plt.title(title)
plt.show()
#end def
if __name__ == '__main__':
dataReader = DataReader20(train_data_name, test_data_name)
dataReader.ReadData()
dataReader.GenerateValidationSet()
n_input, n_hidden, n_output = 1, 3, 1
eta, batch_size, max_epoch = 0.5, 10, 10000
eps = 0.001
hp = HyperParameters20(n_input, n_hidden, n_output, eta, max_epoch,
batch_size, eps, NetType.Fitting,
InitialMethod.Xavier)
net = NeuralNet20(hp, "complex_131")
net.train(dataReader, 50, True)
net.ShowTrainingTrace()
ShowResult(net, dataReader, hp.toString())
fig = plt.figure(figsize=(6,6))
p1,= plt.plot(TX,net.A1[:,0],'.',c='r')
p2,= plt.plot(TX,net.A1[:,1],'.',c='g')
p3,= plt.plot(TX,net.Z2[:,0],'x',c='blue')
plt.legend([p1,p2,p3], ["a1","a2","z"])
plt.show()
if __name__ == '__main__':
dataReader = DataReader20(train_data_name, test_data_name)
dataReader.ReadData()
dataReader.GenerateValidationSet()
n_input, n_hidden, n_output = 1, 2, 1
eta, batch_size, max_epoch = 0.05, 10, 5000
eps = 0.001
hp = HyperParameters20(n_input, n_hidden, n_output, eta, max_epoch, batch_size, eps, NetType.Fitting, InitialMethod.Xavier)
net = NeuralNet20(hp, "sin_121")
net.LoadResult()
print(net.wb1.W)
print(net.wb1.B)
print(net.wb2.W)
print(net.wb2.B)
#net.train(dataReader, 50, True)
#net.ShowTrainingTrace()
#ShowResult(net, dataReader, hp.toString())
ShowResult2D(net, hp.toString())
dataReader.NormalizeY(NetType.MultipleClassifier, base=1)
fig = plt.figure(figsize=(6, 6))
DrawThreeCategoryPoints(dataReader.XTrainRaw[:, 0],
dataReader.XTrainRaw[:, 1], dataReader.YTrain,
"Source Data")
plt.show()
dataReader.NormalizeX()
dataReader.Shuffle()
dataReader.GenerateValidationSet()
n_input = dataReader.num_feature
n_hidden = 3
n_output = dataReader.num_category
eta, batch_size, max_epoch = 0.1, 10, 5000
eps = 0.1
hp = HyperParameters20(n_input, n_hidden, n_output, eta, max_epoch,
batch_size, eps, NetType.MultipleClassifier,
InitialMethod.Xavier)
net = NeuralNet20(hp, "Bank_233")
net.train(dataReader, 100, True)
net.ShowTrainingTrace()
fig = plt.figure(figsize=(6, 6))
DrawThreeCategoryPoints(dataReader.XTrain[:, 0], dataReader.XTrain[:, 1],
dataReader.YTrain, hp.toString())
ShowClassificationResult25D(net, 50, hp.toString())
plt.show()
def Test(dataReader, net):
print("testing...")
X,Y = dataReader.GetTestSet()
A2 = net.inference(X)
print("A2=",A2)
diff = np.abs(A2-Y)
result = np.where(diff < 1e-2, True, False)
if result.sum() == dataReader.num_test:
return True
else:
return False
if __name__ == '__main__':
dataReader = XOR_DataReader()
dataReader.ReadData()
dataReader.GenerateValidationSet()
n_input = dataReader.num_feature
n_hidden = 2
n_output = 1
eta, batch_size, max_epoch = 0.1, 1, 10000
eps = 0.005
hp = HyperParameters20(n_input, n_hidden, n_output, eta, max_epoch, batch_size, eps, NetType.BinaryClassifier, InitialMethod.Xavier)
net = NeuralNet20(hp, "Xor_221")
net.train(dataReader, 100, True)
net.ShowTrainingTrace()
print(Test(dataReader, net))
def train(hp, folder):
net = NeuralNet20(hp, folder)
net.train(dataReader, 50, True)
trace = net.GetTrainingTrace()
return trace
# Copyright (c) Microsoft. All rights reserved.
# Licensed under the MIT license. See LICENSE file in the project root for full license information.
import numpy as np
from HelperClass2.NeuralNet20 import *
train_data_name = "../../Data/ch10.train.npz"
test_data_name = "../../Data/ch10.test.npz"
if __name__ == '__main__':
dataReader = DataReader20(train_data_name, test_data_name)
dataReader.ReadData()
dataReader.NormalizeX()
dataReader.Shuffle()
dataReader.GenerateValidationSet()
n_input = dataReader.num_feature
n_hidden = 2
n_output = 1
eta, batch_size, max_epoch = 0.1, 5, 10000
eps = 0.08
hp = HyperParameters20(n_input, n_hidden, n_output, eta, max_epoch,
batch_size, eps, NetType.BinaryClassifier,
InitialMethod.Xavier)
net = NeuralNet20(hp, "Arc_221")
net.train(dataReader, 5, True)
net.ShowTrainingTrace()