每個 epoch 之后的驗證准確率和損失是相同的

Question

我的驗證准確性在每個紀元之后都是相同的。 不確定我在這里做錯了什么？ 我在下面添加了我的 CNN.network 和我的培訓 function。 我初始化了 CNN 一次。 然而，訓練 function 工作得非常好，損失下降，每個時期的准確性增加。 我做了一個測試 function 與我的驗證 function 相同的結構，同樣的事情發生了。 我的火車/瓦爾分裂是 40000/10000。 我正在使用 cifar 10。

下面是我的代碼：

#Make train function (simple at first)
def train_network(model, optimizer, train_loader, num_epochs=10):

  total_epochs = notebook.tqdm(range(num_epochs))
  model.train()

  for epoch in total_epochs:
    train_acc = 0.0
    running_loss = 0.0

    for i, (x_train, y_train) in enumerate(train_loader):
      x_train, y_train = x_train.to(device), y_train.to(device)

      y_pred = model(x_train)
      loss = criterion(y_pred, y_train)
    
      loss.backward()
      optimizer.step()
      optimizer.zero_grad()

      running_loss += loss.item()
      train_acc += accuracy(y_pred, y_train)

    running_loss /= len(train_loader)
    train_acc /= len(train_loader)

    print('Evaluation Loss: %.3f | Evaluation Accuracy: %.3f'%(running_loss, train_acc))


@torch.no_grad()
def validate_network(model, optimizer, val_loader, num_epochs=10):
  model.eval()
  total_epochs = notebook.tqdm(range(num_epochs))


  for epoch in total_epochs:  
    accu = 0.0
    running_loss = 0.0

    for i, (x_val, y_val) in enumerate(val_loader):
      x_val, y_val = x_val.to(device), y_val.to(device)

      val_pred = model(x_val)
      loss = criterion(val_pred, y_val)

      running_loss += loss.item()
      accu += accuracy(val_pred, y_val)

    running_loss /= len(val_loader)
    accu /= len(val_loader)

    
    print('Val Loss: %.3f | Val Accuracy: %.3f'%(running_loss,accu))

OUTPUT：

Val Loss: 0.623 | Val Accuracy: 0.786
Val Loss: 0.623 | Val Accuracy: 0.786
Val Loss: 0.623 | Val Accuracy: 0.786
Val Loss: 0.623 | Val Accuracy: 0.786
Val Loss: 0.623 | Val Accuracy: 0.786
Val Loss: 0.623 | Val Accuracy: 0.786
Val Loss: 0.623 | Val Accuracy: 0.786
Val Loss: 0.623 | Val Accuracy: 0.786
Val Loss: 0.623 | Val Accuracy: 0.786
Val Loss: 0.623 | Val Accuracy: 0.786

所以我想我的問題是，如何在驗證時獲得代表 output 的准確性和每個時期的損失。

Answer 1

這里發生的是你為number_of_epochs運行一個循環，你只需要多次訪問 same.network 。 我建議您在每個 epoch 結束時的訓練期間調用驗證 function 來測試 epoch 對模型性能的改進。 這意味着訓練 function 應該類似於：

def train_network(model, optimizer, train_loader, val_loader, num_epochs=10):

  total_epochs = notebook.tqdm(range(num_epochs))
  model.train()

  for epoch in total_epochs:
    train_acc = 0.0
    running_loss = 0.0

    for i, (x_train, y_train) in enumerate(train_loader):
      x_train, y_train = x_train.to(device), y_train.to(device)

      y_pred = model(x_train)
      loss = criterion(y_pred, y_train)
    
      loss.backward()
      optimizer.step()
      optimizer.zero_grad()

      running_loss += loss.item()
      train_acc += accuracy(y_pred, y_train)

    running_loss /= len(train_loader)
    train_acc /= len(train_loader)

    print('Evaluation Loss: %.3f | Evaluation Accuracy: %.3f'%(running_loss, train_acc))
    validate_network(model, optimizer, val_loader, num_epochs=1)

請注意，我添加了驗證加載器作為輸入，並在每個紀元結束時調用驗證 function，將紀元的驗證數設置為 1。一個小的額外更改是從驗證 function 中刪除紀元循環。