validation_batch_size等於訓練CNN中的train_batch_size？

Question

我想以最高的準確度保存模型，我需要在每個步驟中採取一批驗證數據進行驗證，以便在每一步訓練之後，訓練數據集將因時代而重複使用，但是如果train_batch_size等於validation_batch_size，驗證數據集也將被重用？因爲驗證數據集遠小於訓練數據集。我應該怎麼做？我的意思是重用驗證集沒有任何問題？或者我分別設置不同的尺寸。

MAX_EPOCH = 10 
for epoch in range(MAX_EPOCH): 
    # training 
    train_step = int(80000/TRAIN_BATCH_SIZE) 
    train_loss, train_acc = 0, 0 
    for step in range(epoch * train_step, (epoch + 1) * train_step): 
     x_train, y_train = sess.run([x_train_batch, y_train_batch]) 
     train_summary, _, err, ac = sess.run([merged, train_op, loss, acc], 
              feed_dict={x: x_train, y_: y_train, 
                 mode: learn.ModeKeys.TRAIN, 
                 global_step: step}) 
     train_loss += err 
     train_acc += ac 
     if (step + 1) % 100 == 0: 
      train_writer.add_summary(train_summary, step) 
    print("Epoch %d,train loss= %.2f,train accuracy=%.2f%%" % (
     epoch, (train_loss/train_step), (train_acc/train_step * 100.0))) 

    # validation 
    val_step = int(20000/VAL_BATCH_SIZE) 
    val_loss, val_acc = 0, 0 
    for step in range(epoch * val_step, (epoch + 1) * val_step): 
     x_val, y_val = sess.run([x_val_batch, y_val_batch]) 
     val_summary, err, ac = sess.run([merged, loss, acc], 
             feed_dict={x: x_val, y_: y_val, mode: learn.ModeKeys.EVAL, 
                global_step: step}) 
     val_loss += err 
     val_acc += ac 
     if (step + 1) % 100 == 0: 
      valid_writer.add_summary(val_summary, step) 
    print(
     "Epoch %d,validation loss= %.2f,validation accuracy=%.2f%%" % (
      epoch, (val_loss/val_step), (val_acc/val_step * 100.0))) 

Answer 1

在評估過程中可以使用不同的批量大小。

也就是說，每次評估模型時都應該使用相同的驗證集。否則，結果會增加/減少，因爲您評估的例子與先前的評估相比本質上更容易/更難。