为什么验证损失是常数？

原文标题 ：Why is the validation loss constant?

我正在尝试在我制作的自定义数据集上使用来自 Aladdin Persson 的 unet 模型。问题是“在训练期间，训练损失正在减少，而验证损失是恒定的。而且我只是无法弄清楚问题所在。我在训练集中有 368 张图片，在验证集中有 51 张图片。[橙色是验证损失，蓝色是训练][1]我还发布了我的训练代码以及我在验证集上检查准确性的部分。

这部分是train_fn。

for batch_idx, (data, targets) in enumerate(loop):
    #img = data.cpu().squeeze(0).permute(1,2,0).numpy()
    #plt.imshow(img)
    data = data.to(device=DEVICE)
    targets = targets.float().unsqueeze(1).to(device=DEVICE)
    
    # forward
    with torch.cuda.amp.autocast():
        predictions = model(data)
        loss = loss_fn(predictions, targets)
    # backward
    optimizer.zero_grad()
    scaler.scale(loss).backward()
    scaler.step(optimizer)
    scaler.update()
    
    running_loss += loss.item()

    # update tqdm loop
    loop.set_postfix(loss=loss.item())
    
train_loss = running_loss/len(loader)
train_losses.append(train_loss)

epochs.append(epoch)
scheduler.step()

还有训练部分

for epoch in range(1,NUM_EPOCHS):
    train_fn(train_loader, model, optimizer, loss_fn, scaler, epoch, scheduler)

    #save model
    checkpoint = {
        "state_dict": model.state_dict(),
        "optimizer":optimizer.state_dict(),
    }
    save_checkpoint(checkpoint)

    # check accuracy
    val_loss = check_accuracy(epoch, val_loader, model, loss_fn, device=DEVICE)
    val_losses.append(val_loss)
    # print some examples to a folder
    save_predictions_as_imgs(
        val_loader, model, folder="saved_images/", device=DEVICE
    )

    plt.plot(epochs, train_losses)
    plt.plot(epochs, val_losses)
    plt.xlabel('Epochs')
    plt.ylabel('Loss')
    plt.title('Loss function')
    plt.show()
    

和 check_accuracy

def check_accuracy(epoch ,loader, model, loss_fn, device="cuda"):
try:
    val_losses
except NameError:
    val_losses = []
num_correct = 0
num_pixels = 0
dice_score = 0
running_loss = 0
idx = 1
model.eval()

with torch.no_grad():
    for x, y in loader:
        # if idx <= 10:
        #     grid_data = make_grid(x)
        #     grid_mask = make_grid(y)
        #     f, axarr_val = plt.subplots(2,1)
        #     plt.title('Validation transform')
        #     axarr_val[0].imshow(grid_data.permute(1,2,0).numpy())
        #     axarr_val[1].imshow(grid_mask.permute(1,2,0).numpy())
        #     plt.savefig("transformacije/validation/fig" + str(epoch+1) + str(idx) + ".png")
        #     plt.close(f)
        #     idx = idx+1
        x = x.to(device)
        y = y.to(device).unsqueeze(1)
        preds = torch.sigmoid(model(x))
        preds = (preds > 0.5).float()
        num_correct += (preds == y).sum()
        num_pixels += torch.numel(preds)
        dice_score += (2 * (preds * y).sum()) / (
            (preds + y).sum() + 1e-8
        )
        loss = loss_fn(preds, y)
        running_loss += loss.item()
    val_loss = running_loss/len(loader)
print(
    f"Got {num_correct}/{num_pixels} with acc {num_correct/num_pixels*100:.2f}"
)
print(f"Dice score: {dice_score/len(loader)}")
print(f"Validation Loss: {val_loss}")
model.train()
return val_loss

如果您能提供帮助，我将不胜感激。谢谢。[1]：https://i.stack.imgur.com/tRh89.png