Strong tiling artifacts
Closed this issue · 3 comments
When I run the network prediction, the result has strong tiling artifacts. I use quite big halo, but it doesn't help. I encountered this before when using U-Net that wasn't trained for long enough or didn't see enough ground truth, which is kind of the case when applying a pretrained network to different data. As a workaround, would be nice to have an option for smooth transition between tiles, like in the original U-Net publication, where within the halo the weight of the tile in the result falls linearly towards the edge of the tile.
Here is an example:
Furthermore, it propagates to the superpixels (here GASP run on the wrong channel, but still you can see clearly the squares)
Fixing #205 doesn't help, i.e. changing size of halo doesn't improve prediction, which indicates more serious problems. Thus #220 and wolny/pytorch-3dunet#113
Progress:
- Halo implementation is fixed, which already greatly improved the prediction (wolny/pytorch-3dunet#113 (comment))
- Intensity normalisation doesn't cause problem at least for ovules (training data) and mouse (another dataset).
- Batch norm fix hallucinations created by group norm in mouse embryo (I mean you need to train with batch norm again).