千层面的实时数据扩充 [英] Realtime Data augmentation in Lasagne

问题描述

我需要对数据集进行实时扩充，以输入CNN，但是我很难找到合适的库.我尝试了caffe，但是DataTransform不支持许多实时增强功能，例如旋转等.因此，为了易于实施，我选择了Lasagne.但似乎它也不支持实时增强.我已经看到一些与Facial Keypoints detection有关的帖子，其中他正在使用nolearn.lasagne的Batchiterator.但是我不确定它是否实时.没有合适的教程.那么最后我应该如何通过nolearn或其他方式在Lasagne中进行实时增强?

I need to do realtime augmentation on my dataset for input to CNN, but i am having a really tough time finding suitable libraries for it. I have tried caffe but the DataTransform doesn't support many realtime augmentations like rotating etc. So for ease of implementation i settled with Lasagne. But it seems that it also doesn't support realtime augmentation. I have seen some posts related to Facial Keypoints detection where he's using Batchiterator of nolearn.lasagne. But i am not sure whether its realtime or not. There's no proper tutorial for it. So finally how should i do realtime augmentation in Lasagne either through nolearn or otherwise?

推荐答案

是的，

Yes, the Facial Keypoints Recognition tutorial that you mention does use real-time (on the fly) augmentation to flip the input images (and target coordinates) at random.

nolearn-utils 库包含大量示例进行几种类型的扩充的迭代器.例如. AffineTransformBatchIteratorMixin即时进行仿射仿射变换.

The nolearn-utils library has a ton of examples of iterators that do several types of augmentation. E.g. AffineTransformBatchIteratorMixin does random affine transforms on the fly.

这篇关于千层面的实时数据扩充的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！