I am a beginner to PyTorch. When I am building a toy neural network for regression, I mistakenly set the requires_grad
of label y
to True
(since I do not have when computing loss), and this makes the network diverge where the loss grows larger than larger and finally becomes nan
.
Previously, when I tried to visualize the tensor with matplotlib
, I could not convert tensors to np.array()
when requires_grad=True
, I am wondering if this happens based on the similar reason.
The following is the code.
import torch
x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1)
y = x.pow(2) + 10 * torch.rand(x.size())
x.requires_grad = True
y.requires_grad = True
class Net(torch.nn.Module):
def __init__(self, n_feature, n_hidden, n_output):
super(Net, self).__init__()
self.hidden = torch.nn.Linear(n_feature, n_hidden)
self.predict = torch.nn.Linear(n_hidden, n_output)
def forward(self, x):
x = torch.relu(self.hidden(x))
x = self.predict(x)
return x
net = Net(1, 10, 1)
optimizer = torch.optim.SGD(net.parameters(), lr=0.5)
criterion = torch.nn.MSELoss()
for t in range(200):
y_pred = net(x)
loss= criterion(y_pred, y)
optimizer.zero_grad()
loss.backward()
print("Epoch {}: {}".format(t, loss))
optimizer.step()