Thanks for your sharing of your augmentation code. I have a question about ''augment_channel_translation'' in ''spatial_transforms.py''.
What is the meaning of this augment method? Does it in order to prevent the impact of poor registration between different modality of one object?(different modality: like RGB and Depth in netural image; CT and MRI and PET in medical image. One modality is one channel)
Hi Eric,
exactly. It will misalign the 'color' channels (translation only) to simulate bad registration. I have not used it though, so I cannot say how well this works as an augmentation.
Best,
Fabian
Hi,
Thanks for your sharing of your augmentation code. I have a question about ''augment_channel_translation'' in ''spatial_transforms.py''.
What is the meaning of this augment method? Does it in order to prevent the impact of poor registration between different modality of one object?(different modality: like RGB and Depth in netural image; CT and MRI and PET in medical image. One modality is one channel)
Thanks.
Best,
Eric Kani