Pytorch - 07. Multidimensional characteristics of input processing

import numpy as npimport torchxy = np.loadtxt('diabetes.csv.gz',delimiter=',',dtype=np.float32) # delimiter=',' : the delimiter is,x_data = torch.from_numpy(xy[:,:-1]) #All rows start from the first column, not the last columny_data = torch.from_numpy(xy[:,[-1]]) # All rows as long as the last column [] represents a matrix not a vectorclass Model(torch.nn.Module):def __init__(self):super(Model, self).__init__()self.linear1 = torch.nn.Linear(8,6)self.linear2 = torch.nn.Linear(6,4)self.linear3 = torch.nn.Linear(4,1)self.sigmoid = torch.nn.Sigmoid()def forward(self,x):x = self.sigmoid(self.linear1(x))x = self.sigmoid(self.linear2(x))x = self.sigmoid(self.linear3(x))return xmodel = Model()criterion = torch.nn.BCELoss(size_average=True)optimizer = torch.optim.SGD(model.parameters(),lr=0.1)for epoch in range (10000):y_pred = model(x_data)loss = criterion(y_pred,y_data)print('epoch=', epoch, " loss=", loss.item())optimizer.zero_grad()loss.backward()optimizer.step()#--------------------------------------------------------# Test Modelx_test = torch.Tensor([[-0.29,0.48,0.18,-0.29,0,0,-0.53,-0.03]])y_test = model(x_test)print('y_pred=',y_test.data.item())

Test a set of data:

Change the activation function to RELU:

import numpy as npimport torchxy = np.loadtxt('diabetes.csv.gz',delimiter=',',dtype=np.float32) # delimiter=',' : the delimiter is,x_data = torch.from_numpy(xy[:,:-1]) #All rows start from the first column, not the last columny_data = torch.from_numpy(xy[:,[-1]]) # All rows as long as the last column [] represents a matrix not a vectorclass Model(torch.nn.Module):def __init__(self):super(Model, self).__init__()self.linear1 = torch.nn.Linear(8,6)self.linear2 = torch.nn.Linear(6,4)self.linear3 = torch.nn.Linear(4,1)self.sigmoid = torch.nn.Sigmoid()self.activate = torch.nn.ReLU()def forward(self,x):x = self.activate(self.linear1(x))x = self.activate(self.linear2(x))x = self.sigmoid(self.linear3(x)) #RELU, the y value when x is less than 0 is 0, and ln0 may appear when calculating the lossreturn xmodel = Model()criterion = torch.nn.BCELoss(size_average=True)optimizer = torch.optim.SGD(model.parameters(),lr=0.1)for epoch in range (10000):y_pred = model(x_data)loss = criterion(y_pred,y_data)print('epoch=', epoch, " loss=", loss.item())optimizer.zero_grad()loss.backward()optimizer.step()#--------------------------------------------------------# Test Modelx_test = torch.Tensor([[-0.29,0.48,0.18,-0.29,0,0,-0.53,-0.03]])y_test = model(x_test)print('y_pred=',y_test.data.item())