Pytorch保存模型用于测试和用于继续训练的区别详解

torch.save(model.state_dict, path)

state = { 'model': model.state_dict(), 'optimizer':optimizer.state_dict(), 'epoch': epoch }  
torch.save(state, path)

def adjust_learning_rate(optimizer, epoch):
  lr_t = lr
  lr_t = lr_t * (0.3 ** (epoch // 2))
  for param_group in optimizer.param_groups:
    param_group['lr'] = lr_t

model.load_state_dict(torch.load(path))

checkpoint = torch.load(path)
model.load_state_dict(checkpoint['model'])
optimizer.load_state_dict(checkpoint['optimizer'])
start_epoch = checkpoint['epoch']+1