第一次接触pytorch，本贴仅记录学习过程，侵删
在B站看完了视频的P5 05.用pytorch实现线性回归。
附上视频地址：《PyTorch深度学习实践》完结合集_05. 用pytorch实现线性回归
先记录一些笔记。
import torch.nn
# 1. Prepare dataset
x_data = torch.Tensor([[1.0], [2.0], [3.0]])
y_data = torch.Tensor([[2.0], [4.0], [6.0]])
# 2. Design model using Class
class LinearModel(torch.nn.Module):
def __init__(self):
super().__init__()
self.linear = torch.nn.Linear(1, 1)
# Class nn.Linear contain two member Tensors: weight and bias.
def forward(self, x):
y_pred = self.linear(x)
return y_pred
model = LinearModel() # Create a instance of class LinearModel
# 3. Construct Loss and Optimizer
criterion = torch.nn.MSELoss(size_average=False)
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
# 4. Training Cycle
for epoch in range(1000):
y_pred = model(x_data)
loss = criterion(y_pred, y_data)
print(epoch, loss)
optimizer.zero_grad()
# The grad computed by .backward() will be accumulated.
# So before backward, remember set the grad to ZERO!!!
loss.backward()
optimizer.step() # update
# Output weight and bias
print('w=', model.linear.weight.item())
print('b=', model.linear.bias.item())
# Test Model
x_test = torch.Tensor([[4.0]])
y_test = model(x_test)
print('y_pred=', y_test.data)
作业：
其中LBFGS会多次重新计算函数，这样就要使用一个闭包（closure）来支持多次计算model的操作。
import matplotlib.pyplot as plt
import torch.nn
# 1. Prepare dataset
x_data = torch.Tensor([[1.0], [2.0], [3.0]])
y_data = torch.Tensor([[2.0], [4.0], [6.0]])
# 2. Design model using Class
class LinearModel(torch.nn.Module):
def __init__(self):
super().__init__()
self.linear = torch.nn.Linear(1, 1)
def forward(self, x):
y_pred = self.linear(x)
return y_pred
model = LinearModel()
# 3. Construct Loss and Optimizer
criterion = torch.nn.MSELoss(size_average=False)
optimizer = torch.optim.LBFGS(model.parameters(), lr=0.01)
# 4. Training Cycle
loss_list = []
time = []
for epoch in range(1000):
def closure():
y_pred = model(x_data)
loss = criterion(y_pred, y_data)
print(epoch, loss)
loss_list.append(loss.item())
time.append(epoch)
optimizer.zero_grad()
loss.backward()
return loss
optimizer.step(closure)
# Output weight and bias
print('w=', model.linear.weight.item())
print('b=', model.linear.bias.item())
# Test Model
x_test = torch.Tensor([[4.0]])
y_test = model(x_test)
print('y_pred=', y_test.data)
plt.plot(time, loss_list)
plt.title('LBFGS')
plt.xlabel('epoch')
plt.ylabel('loss')
plt.show()
图：
其余的Optimizer代码不一定需要使用闭包：
import matplotlib.pyplot as plt
import torch.nn
# 1. Prepare dataset
x_data = torch.Tensor([[1.0], [2.0], [3.0]])
y_data = torch.Tensor([[2.0], [4.0], [6.0]])
# 2. Design model using Class
class LinearModel(torch.nn.Module):
def __init__(self):
super().__init__()
self.linear = torch.nn.Linear(1, 1)
def forward(self, x):
y_pred = self.linear(x)
return y_pred
model = LinearModel()
# 3. Construct Loss and Optimizer
criterion = torch.nn.MSELoss(size_average=False)
optimizer = torch.optim.Adagrad(model.parameters(), lr=0.01)
# optimizer = torch.optim.Adam(model.parameters(), lr=0.01)
# optimizer = torch.optim.Adamax(model.parameters(), lr=0.01)
# optimizer = torch.optim.ASGD(model.parameters(), lr=0.01)
# optimizer = torch.optim.RMSprop(model.parameters(), lr=0.01)
# optimizer = torch.optim.Rprop(model.parameters(), lr=0.01)
# optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
# 4. Training Cycle
loss_list = []
time = []
for epoch in range(1000):
y_pred = model(x_data)
loss = criterion(y_pred, y_data)
print(epoch, loss)
loss_list.append(loss.item())
time.append(epoch)
optimizer.zero_grad()
loss.backward()
optimizer.step()
# Output weight and bias
print('w=', model.linear.weight.item())
print('b=', model.linear.bias.item())
# Test Model
x_test = torch.Tensor([[4.0]])
y_test = model(x_test)
print('y_pred=', y_test.data)
plt.plot(time, loss_list)
plt.title('Adagrad')
plt.xlabel('epoch')
plt.ylabel('loss')
plt.show()
图：
