How to optimize multiple fully connected layers?

[bb417759235 (linbeibei)]

l want to finetune a net.I made the following settings.
Modified the last three layers of fc
net.fc6 = nn.Linear(8192, 4096)
net.fc7 = nn.Linear(4096, 4096)
net.fc8 = nn.Linear(4096, 74)
optimizer = optim.SGD([{‘params’: net.fc6},{‘params’: net.fc7},{‘params’: net.fc8}], lr=0.0003, momentum=0.9)

but
It was given an error
param_group[‘params’] = list(params)
TypeError: ‘Linear’ object is not iterable

How to optimize multiple fully connected layers?

[bb417759235 (linbeibei)]

I know

Giving multiple parameters in optimizer

How can i give multiple parameters to the optimizer? fc1 = nn.Linear(784, 500) fc2 = nn.Linear(500, 10) optimizer = torch.optim.SGD([fc1.parameters(), fc2.parameters()], lr=0.01) # This causes an error. In this case, for simplicity, i don’t want to use a class with nn.Module.