def LoadData(): dr = DataReader_2_0(train_file, test_file) dr.ReadData() dr.NormalizeX() dr.Shuffle() dr.GenerateValidationSet() return dr
def load_data(): dataReader = DataReader_2_0(train_data_name, test_data_name) dataReader.ReadData() dataReader.NormalizeX() dataReader.Shuffle() dataReader.GenerateValidationSet() return dataReader
def LoadData(): dr = DataReader_2_0(train_file, test_file) dr.ReadData() dr.NormalizeX() dr.NormalizeY(NetType.MultipleClassifier, base=1) dr.Shuffle() dr.GenerateValidationSet() return dr
def LoadData(): dr = DataReader_2_0(train_file, test_file) dr.ReadData() dr.NormalizeX() #dr.NormalizeY(YNormalizationMethod.BinaryClassifier) dr.Shuffle() dr.GenerateValidationSet() return dr
def load_data(): dataReader = DataReader_2_0(train_file, test_file) dataReader.ReadData() dataReader.GenerateValidationSet(k=10) x_train, y_train = dataReader.XTrain, dataReader.YTrain x_test, y_test = dataReader.XTest, dataReader.YTest x_val, y_val = dataReader.XDev, dataReader.YDev return x_train, y_train, x_test, y_test, x_val, y_val
def LoadImageData(): print("reading data...") dr = DataReader_2_0(train_data_name, test_data_name) dr.ReadData() dr.NormalizeX() dr.NormalizeY(NetType.MultipleClassifier, base=0) dr.Shuffle() dr.GenerateValidationSet(k=10) return dr
def load_data(): train_data_name = "../data/ch14.Income.train.npz" test_data_name = "../data/ch14.Income.test.npz" dataReader = DataReader_2_0(train_data_name, test_data_name) dataReader.ReadData() dataReader.NormalizeX() dataReader.Shuffle() dataReader.GenerateValidationSet() x_train, y_train = dataReader.XTrain, dataReader.YTrain x_test, y_test = dataReader.XTest, dataReader.YTest x_val, y_val = dataReader.XDev, dataReader.YDev return x_train, y_train, x_test, y_test, x_val, y_val
def load_data(): train_file = "../data/ch11.train.npz" test_file = "../data/ch11.test.npz" dataReader = DataReader_2_0(train_file, test_file) dataReader.ReadData() dataReader.NormalizeX() dataReader.NormalizeY(NetType.MultipleClassifier, base=1) dataReader.Shuffle() dataReader.GenerateValidationSet() x_train, y_train = dataReader.XTrain, dataReader.YTrain x_test, y_test = dataReader.XTest, dataReader.YTest x_val, y_val = dataReader.XDev, dataReader.YDev return x_train, y_train, x_test, y_test, x_val, y_val
def load_data(): dr = DataReader_2_0(train_file, test_file) dr.ReadData() dr.Shuffle() dr.GenerateValidationSet(k=0) return dr
def ShowResult2D(net, dr): ShowDataHelper(dr.XTrain[:, 0], dr.XTrain[:, 1], dr.YTrain[:, 0], "Classifier Result", "x1", "x2", False, False) count = 50 X, Y = Prepare3DData(net, count) Z = net.output.reshape(count, count) plt.contourf(X, Y, Z, cmap=plt.cm.Spectral, zorder=1) plt.show() #end def if __name__ == '__main__': dataReader = DataReader_2_0(train_data_name, test_data_name) dataReader.ReadData() dataReader.NormalizeX() dataReader.Shuffle() dataReader.GenerateValidationSet() num_input = 2 num_hidden = 2 num_output = 1 max_epoch = 10000 batch_size = 5 learning_rate = 0.1 params = HyperParameters_4_0(learning_rate, max_epoch,