I cannot figure out why .grad is None while the weights have required_grad = True?
class LeNet(nn.Module):
def __init__(self):
super(LeNet, self).__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16*5*5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
out = F.relu(self.conv1(x))
out = F.max_pool2d(out, 2)
out = F.relu(self.conv2(out))
out = F.max_pool2d(out, 2)
out = out.view(out.size(0), -1)
out = F.relu(self.fc1(out))
out = F.relu(self.fc2(out))
out = self.fc3(out)
return out
def train_cnn(data, lr=0.01, epochs=100, momentum=0.9, weight_decay=0):
model = LeNet()
model.cuda()
criterion = torch.nn.CrossEntropyLoss()
model.train()
optimizer = torch.optim.SGD(model.parameters(), lr=lr, momentum=momentum, weight_decay=weight_decay)
for e in range(epochs):
for data in trainloader:
x, y = data
x = x.cuda()
y = y.cuda()
outputs = model(x)
loss = criterion(outputs, y)
optimizer.zero_grad()
loss.backward()
print(model.conv1.weight[0].requires_grad)
print(model.conv1.weight[0].grad)
exit()
The output of this is
True
None