[Python] why does not my code cause the error 'element 0 of tensors does not require grad and...

Given the code fragment below, I freeze the weights of the neural network using model.fc1.requires_grad_(False) and model.fc2.requires_grad_(False). If I use loss = criterion(outputs, y_batch) to calculate the loss, the training is fine. But when I use loss = compute_loss(model) to calculate the loss, I get the error RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn. Why does not loss = criterion(outputs, y_batch) cause the error?

def compute_loss(model):
for _, params in model.named_parameters():
loss = sum(params)
return loss

class SimpleNet(nn.Module):
def __init__(self, input_size, hidden_size, output_size):
super(SimpleNet, self).__init__()
self.fc1 = nn.Linear(input_size, hidden_size)
self.fc2 = nn.Linear(hidden_size, output_size)

def forward(self, x):
x = self.fc1(x)
x = self.fc2(x)
return x

model = SimpleNet(input_size, hidden_size, output_size)

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=learning_rate)

for epoch in range(num_epochs):
for batch_idx, (X_batch, y_batch) in enumerate(dataloader):
optimizer.zero_grad()
outputs = model(X_batch)
loss = criterion(outputs, y_batch)
# loss = compute_loss(model)

loss.backward()
optimizer.step()

if (batch_idx + 1) % 10 == 0:
model.fc1.requires_grad_(False)
model.fc2.requires_grad_(False)

print("Training complete!")

Continue reading...