Releases: PolarBean/DeepSlice
DeepSlice 1.2.3
DeepSlice 1.2
Allows DeepSlice to use tensorflow 2 and more recent versions of Python.
Thanks to @wjguan for fixing a major model loading bug!
DeepSlice 1.1.7
Full Changelog: 1.1.6...1.1.7
DeepSlice 1.1.6
DeepSlice 1.1.5
DeepSlice 1.1.4
DeepSlice 1.1.3
In this release we have added the ability to auto detect potential outlier sections and to manually specify heavily damaged sections. This allows DeepSlice to weight these sections less when calculating average angle and section number based position.
DeepSlice 1.1.2
Added the ability to choose to use a secondary model and fixes a bug with propagating angles when a section is outside of the atlas.
DeepSlice 1.1.1
Previous fix hurt performance on the rat model
DeepSlice 1.1.0
Switching to the use of the keras Functional API alongside manually specifying an input layer seems to have affected performance negatively. Here we reimplement the Sequential APi and improve an improvement in the performance of the Model.