4
def autotune(trial):

      cfg= { 'device' : "cuda" if torch.cuda.is_available() else "cpu",
         #   'train_batch_size' : 64,
         #   'test_batch_size' : 1000,
         #   'n_epochs' : 1,
         #   'seed' : 0,
         #   'log_interval' : 100,
         #   'save_model' : False,
         #   'dropout_rate' : trial.suggest_uniform('dropout_rate',0,1.0),
            'lr' : trial.suggest_loguniform('lr', 1e-3, 1e-2),
            'momentum' : trial.suggest_uniform('momentum', 0.4, 0.99),
            'optimizer': trial.suggest_categorical('optimizer',[torch.optim.Adam,torch.optim.SGD, torch.optim.RMSprop, torch.optim.$
            'activation': F.tanh}
      optimizer = cfg['optimizer'](model.parameters(), lr=cfg['lr'])
      #optimizer = torch.optim.Adam(model.parameters(),lr=0.001

正如您在上面看到的,我正在尝试运行 Optuna 试验来为我的 CNN 模型搜索最佳超参数。

# Train the model
# use small epoch for large dataset
# An epoch is 1 run through all the training data
# losses = [] # use this array for plotting losses
      for _ in range(epochs):
    # using data_loader 
         for i, (data, labels) in enumerate(trainloader):
        # Forward and get a prediction
        # x is the training data which is X_train
            if name.lower() == "rnn":
                model.hidden = (torch.zeros(1,1,model.hidden_sz),
                    torch.zeros(1,1,model.hidden_sz))

            y_pred = model.forward(data)

        # compute loss/error by comparing predicted out vs acutal labels
            loss = criterion(y_pred, labels)
        #losses.append(loss)

            if i%10==0:  # print out loss at every 10 epoch
                 print(f'epoch {i} and loss is: {loss}')

        #Backpropagation
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()

study = optuna.create_study(sampler=optuna.samplers.TPESampler(), direction='minimize',pruner=optuna.pruners.SuccessiveHalvingPrune$
study.optimize(autotune, n_trials=1)

但是,当我运行上面的代码来调整并找出我的最佳参数时,发生了跟随错误,即使我仍然得到 epoch 损失和值,试验似乎也失败了。请指教谢谢!

[W 2020-11-11 13:59:48,000] Trial 0 failed, because the returned value from the objective function cannot be cast to float. Returned value is: None
Traceback (most recent call last):
  File "autotune2", line 481, in <module>
    n_instances, n_features, scores = run_analysis()
  File "autotune2", line 350, in run_analysis
    print(study.best_params)
  File "/home/shar/anaconda3/lib/python3.7/site-packages/optuna/study.py", line 67, in best_params
    return self.best_trial.params
  File "/home/shar/anaconda3/lib/python3.7/site-packages/optuna/study.py", line 92, in best_trial
    return copy.deepcopy(self._storage.get_best_trial(self._study_id))
  File "/home/shar/anaconda3/lib/python3.7/site-packages/optuna/storages/_in_memory.py", line 287, in get_best_trial
    raise ValueError("No trials are completed yet.")
ValueError: No trials are completed yet.
4

1 回答 1

3

引发此异常是因为您研究的目标函数必须返回一个浮点数。

在您的情况下,问题出在这一行:

study.optimize(autotune, n_trials=1)

您之前定义的自动调整函数不返回值,不能用于优化。

怎么修?

对于超参数搜索,autotune 函数必须返回一些你在一些训练后可以获得的指标——比如损失或交叉熵。

快速修复您的代码可能是这样的:

def autotune():
  cfg= { 'device' : "cuda" if torch.cuda.is_available() else "cpu"
        ...etc...
       }

  best_loss = 1e100;  # or larger

  # Train the model
  for _ in range(epochs):
     for i, (data, labels) in enumerate(trainloader):
        ... (train the model) ...
        # compute loss/error by comparing predicted out vs actual labels
        loss = criterion(y_pred, labels)
        best_loss = min(loss,best_loss)

  return best_loss

在 Optuna 存储库中有一个很好的Pythorch 示例,它使用 pythoch 回调来检索准确性(但如果需要,可以轻松更改以使用 RMSE)。它还使用多个实验,并采用超参数的中值。

于 2020-11-24T09:02:32.380 回答