请问为什么要在训练代码中使用测试集选择最好的模型呢？

[LIKP0]

您好！感谢您开源代码，这对我有很大帮助！

但是我对您train_brats.py中如下的代码有些疑惑：

for epoch_num in tqdm(range(max_epoch), ncols=70):
    time1 = time.time()
    for i_batch, (sampled_batch, sample_stats) in enumerate(trainloader):
        ........

   ## ================ Evaluate ================
    logging.info(f'Epoch {epoch_num} Evaluation:')
    # print()
    t1_MSE_all, t1_PSNR_all, t1_SSIM_all = [], [], []
    t2_MSE_all, t2_PSNR_all, t2_SSIM_all = [], [], []
  
    t1_MSE_krecon, t1_PSNR_krecon, t1_SSIM_krecon = [], [], []
    t2_MSE_krecon, t2_PSNR_krecon, t2_SSIM_krecon = [], [], []
  
    for (sampled_batch, sample_stats) in testloader:
      ........

请问为什么要在训练代码中使用测试集选择best model呢？可能我的理解有误，但是我同样没有在训练代码中发现验证集？

再次感谢您的精彩工作，谢谢。