Closed sampepose closed 7 years ago
Hi Sam,
you're bound to lose information with a shift augmentation, there's no way around that. However, the FlowNet trained on crops, not whole images. If you crop out a smaller region from both images, you can safely apply this geometric stuff without losing information in the visible part (of course it gets a little harder because the allowed augmentations depend on each input's crop settings).
Best, Nikolaus
Hi there,
Thank you for your time with my previous questions. I attempted to rewrite the data augmentation code in TensorFlow.
Here are my original two images along with the corresponding flow:
I then augment only with an x,y translation. I'm using the same uniform_bernoulli / gaussian_bernoulli distribution options as in the models for FlowNetS.
This seems like a large amount of information lost from such a huge translation. Half of the flow field is gone. Is this size of augmentation normal? As an extreme, sometimes I end up with an empty, noisy image after all of the transformations.
Thanks for your help!
Sam