损失不是在Pythorch中收敛，而是在十个方面

Question

Epoch: 1    Training Loss: 0.816370     Validation Loss: 0.696534
Validation loss decreased (inf --> 0.696534).  Saving model ...
Epoch: 2    Training Loss: 0.507756     Validation Loss: 0.594713
Validation loss decreased (0.696534 --> 0.594713).  Saving model ...
Epoch: 3    Training Loss: 0.216438     Validation Loss: 1.119294
Epoch: 4    Training Loss: 0.191799     Validation Loss: 0.801231
Epoch: 5    Training Loss: 0.111334     Validation Loss: 1.753786
Epoch: 6    Training Loss: 0.064309     Validation Loss: 1.348847
Epoch: 7    Training Loss: 0.058158     Validation Loss: 1.839139
Epoch: 8    Training Loss: 0.015489     Validation Loss: 1.370469
Epoch: 9    Training Loss: 0.082856     Validation Loss: 1.701200
Epoch: 10   Training Loss: 0.003859     Validation Loss: 2.657933
Epoch: 11   Training Loss: 0.018133     Validation Loss: 0.593986
Validation loss decreased (0.594713 --> 0.593986).  Saving model ...
Epoch: 12   Training Loss: 0.160197     Validation Loss: 1.499911
Epoch: 13   Training Loss: 0.012942     Validation Loss: 1.879732
Epoch: 14   Training Loss: 0.002037     Validation Loss: 2.399405
Epoch: 15   Training Loss: 0.035908     Validation Loss: 1.960887
Epoch: 16   Training Loss: 0.051137     Validation Loss: 2.226335
Epoch: 17   Training Loss: 0.003953     Validation Loss: 2.619108
Epoch: 18   Training Loss: 0.000381     Validation Loss: 2.746541
Epoch: 19   Training Loss: 0.094646     Validation Loss: 3.555713
Epoch: 20   Training Loss: 0.022620     Validation Loss: 2.833098
Epoch: 21   Training Loss: 0.004800     Validation Loss: 4.181845
Epoch: 22   Training Loss: 0.014128     Validation Loss: 1.933705
Epoch: 23   Training Loss: 0.026109     Validation Loss: 2.888344
Epoch: 24   Training Loss: 0.000768     Validation Loss: 3.029443
Epoch: 25   Training Loss: 0.000327     Validation Loss: 3.079959
Epoch: 26   Training Loss: 0.000121     Validation Loss: 3.578420
Epoch: 27   Training Loss: 0.148478     Validation Loss: 3.297387
Epoch: 28   Training Loss: 0.030328     Validation Loss: 2.218535
Epoch: 29   Training Loss: 0.001673     Validation Loss: 2.934132
Epoch: 30   Training Loss: 0.000253     Validation Loss: 3.215722

我的损失没有收敛。我正在研究马与人的数据集。在tensorflow中有一个official notebook，它就像一个符咒。当我试图用Pythorch复制同样的方法时，损失并没有收敛。你能看看吗？在

我正在使用criterion = nn.BCEWithLogitsLoss()和{}。虽然它似乎对训练损失有一定的影响，但验证损失看起来像是随机数，并没有形成任何模式。损失没有汇合的可能原因是什么？在

这是我的CNN架构：

^{pr2}$

This is the complete jupyter notebook。很抱歉不能创建一个最小的可复制的示例代码。在

Answer 1

我想问题出在dataloaders，这里我注意到，你没有把samplers传递给loaders这里：

# define samplers for obtaining training and validation batches
train_sampler = SubsetRandomSampler(train_idx)
valid_sampler = SubsetRandomSampler(valid_idx)

train_loader = torch.utils.data.DataLoader(
        train_dataset,
        batch_size=16,
        num_workers=0,
        shuffle=True
    )

test_loader = torch.utils.data.DataLoader(
        test_dataset,
        batch_size=16,
        num_workers=0,
        shuffle=True
    )

我从来没有使用过Samplers，所以我现在不知道如何正确地使用它们，但是我想您想这样做smth：

^{pr2}$

根据文件：

sampler (Sampler, optional) – defines the strategy to draw samples from the dataset. If specified, shuffle must be False.

如果你正在使用采样器，你应该关闭随机播放。在