Test Time Augmentation

What is Test Time Augmentation (TTA)?
Similar to what Data Augmentation is doing to the training set, the purpose of Test Time Augmentation is to perform random modifications to the test images. Thus, instead of showing the regular, “clean” images, only once to the trained model, we will show it the augmented images several times. We will then average the predictions of each corresponding image and take that as our final guess.

与对训练集所做的数据增强类似，TTA的目的是对测试图像进行随机修改。
常规测试做法：向训练好的模型显示一次常规的“干净”图像并得到结果。
TTA做法：向训练好的模型输入多张不同增强的图像，然后将对每个相应图像的预测进行平均作为最终预测。

           Input
             |           # input batch of images 
        / / /|\ \ \      # apply augmentations (flips, rotation, scale, etc.)
       | | | | | | |     # pass augmented batches through model
       | | | | | | |     # reverse transformations for each batch of masks/labels
        \ \ \ / / /      # merge predictions (mean, max, gmean, etc.)
             |           # output batch of masks/labels
           Output

参考

https://github.com/xuebinqin/U-2-Net/issues/216
Test Time Augmentation (TTA) and how to perform it with Keras
TTA(Test-Time Augmentation) 之Pytorch