import numpy as np
import matplotlib.pyplot as plt
import torch as t
import torch.nn as nn
import torch.optim as optim
from torch.autograd import Variable
#
x_train = np.array([[3.3], [4.4], [5.5], [6.71], [6.93], [4.168], [9.779], [6.182], [7.59] ,[2.167], [7.042], [10.791], [5.313], [7.997], [3.1]], dtype=np.float32 )
y_train = np.array([[1.7], [2.76], [2.09], [3.19], [1.694], [1.573], [3.366], [2.596], [2.53], [1.221], [2.827], [3.465], [1.65], [2.904], [1.3]], dtype=np.float32)
plt.scatter(x_train, y_train)# plot process
plt.show()
print(x_train.dtype)
x_train =t.tensor( t.from_numpy(x_train) )
y_train =t.tensor( t.from_numpy(y_train) )
class LinearRegression(nn.Module):
def _init_(self):
super(LinearRegression,self)._init_()
self.linear = nn.Linear(1,1)# input and output is i dimension
def forward(self, x):
out = self.Linear(x)
return out
if t.cuda.is_available():
model = LinearRegression().cuda()
else:
model = LinearRegression()
criterion = nn.MSELoss()
optimizer = optim.SGD(model.parameters(), lr=1e-3)
num_epochs = 1000
for epoch in range(num_epochs):
if t.cuda.is_available():
inputs = Variable(x_train, requires_grad=True).cuda()
target = Variable(y_train, requires_grad=True).cuda()
else:
inputs = Variable(x_train)
target = Variable(y_train)
out = model(inputs)# forward
loss = criterion(out, target)#compute loss
optimizer.zero_grad()# zero grad
loss.backward()#back propgation
optimizer.step()# update parameters
if(epoch+1 )%20 == 0:
print('Epoch[{}/{}]), loss:{:.6f}'
.format(epoch+1, num_epochs, loss.data[0]))
why always told me : optimizer got an empty parameter list
None
The definition of __init__
is wrong.
You should use two underscores at each side instead of one :
def __init__(self):
super(LinearRegression,self).__init__()
1 Like
realy??
iām a fresh man in python .thanks a lot
feel so stupid:grinning:
No worries! We all had to start at some point!
1 Like