You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The SegResNet architecture has proven to be competitive to UNet for segmentation problems in 2D and 3D, which makes it popular for benchmarking (and it is a default architecture in Auto3DSeg).
Recently, I tried benchmarking it against UNet for a 1D "segmentation" problem, namely photometry basecalling in genomic sequencers. UNet architectures from MONAI actually can be used for 1D, and they offer many options for parametrization.
Unfortunately, SegResNet is restricted to 2D or 3D (see code). Would it be difficult to enable it for 1D? @myron
The text was updated successfully, but these errors were encountered:
The SegResNet architecture has proven to be competitive to UNet for segmentation problems in 2D and 3D, which makes it popular for benchmarking (and it is a default architecture in Auto3DSeg).
Recently, I tried benchmarking it against UNet for a 1D "segmentation" problem, namely photometry basecalling in genomic sequencers. UNet architectures from MONAI actually can be used for 1D, and they offer many options for parametrization.
Unfortunately, SegResNet is restricted to 2D or 3D (see code). Would it be difficult to enable it for 1D? @myron
The text was updated successfully, but these errors were encountered: