聊聊pytorch中Optimizer与optimizer.step()的用法

optim.SGD([
                    {'params': model.base.parameters()},
                    {'params': model.classifier.parameters(), 'lr': 1e-3}
                ], lr=1e-2, momentum=0.9)

optimizer.step()

for input, target in dataset:
        optimizer.zero_grad()
        output = model(input)
        loss = loss_fn(output, target)
        loss.backward()
        optimizer.step()         
optimizer.step(closure)

for input, target in dataset:
    def closure():
        optimizer.zero_grad()
        output = model(input)
        loss = loss_fn(output, target)
        loss.backward()
        return loss
    optimizer.step(closure)

optimizer_G = Adam(model_G.parameters(), lr=train_c.lr_G)   # lr 使用的是初始lr
optimizer_D = Adam(model_D.parameters(), lr=train_c.lr_D)

def step(self, closure=None):
            """PerfORMs a single optimization step.
            Arguments:
                closure (callable, optional): A closure that reevaluates the model
                    and returns the loss.
            """
            loss = None
            if closure is not None:
                loss = closure()
     
            for group in self.param_groups:
                weight_decay = group['weight_decay']
                momentum = group['momentum']
                dampening = group['dampening']
                nesterov = group['nesterov']
     
                for p in group['params']:
                    if p.grad is None:
                        continue
                    d_p = p.grad.data
                    if weight_decay != 0:
                        d_p.add_(weight_decay, p.data)
                    if momentum != 0:
                        param_state = self.state[p]
                        if 'momentum_buffer' not in param_state:
                            buf = param_state['momentum_buffer'] = d_p.clone()
                        else:
                            buf = param_state['momentum_buffer']
                            buf.mul_(momentum).add_(1 - dampening, d_p)
                        if nesterov:
                            d_p = d_p.add(momentum, buf)
                        else:
                            d_p = buf     
                    p.data.add_(-group['lr'], d_p)     
            return loss

total_loss.backward()
optimizer_G.step()