v0.1.19

0.1.19 — 2023-01-04

Features

• Add pytorch lightning in-built auto_lr_finder option to SegmentationExperiment

v0.1.18

0.1.18 — 2023-01-03

Features

• Add Multi-scale-convolutional-attention (MSCA) module (SegNexT).
• Add TokenMixer & MetaFormer modules.

v0.1.17

0.1.17 — 2022-12-29

Features

• Add transformer modules
• Add exact, slice, and memory efficient (xformers) self attention computations
• Add transformers modules to Decoder modules
• Add common transformer mlp activation functions: star-relu, geglu, approximate-gelu.
• Add Linformer self-attention mechanism.
• Add support for model intialization from yaml-file in MultiTaskUnet.
• Add a new cross-attention long-skip module. Works with long_skip='cross-attn'

Refactor

• Added more verbose error messages for the abstract wrapper-modules in modules.base_modules
• Added more verbose error catching for xformers.ops.memory_efficient_attention.

v0.1.16

0.1.16 — 2022-12-14

Dependencies

• Bump old versions of numpy & scipy

v0.1.15

0.1.15 — 2022-12-13

Features

• Use the inferer class as input to segmentation benchmarker class

v0.1.14

0.1.14 — 2022-12-01

Performance

• Throw away some unnecessary parts of the cellpose post-proc pipeline that just brought overhead and did nothing.

Refactor

• Refactor the whole cellpose post-processing pipeline for readability.

• Refactored multiprocessing code to be reusable and moved it under utils.

Features

• Add exact euler integration (on CPU) for cellpose post-processing.

• added more pathos.Pool options for parallel processing. Added ThreadPool, ProcessPool & SerialPool

• add all the mapping methods for each Pool obj. I.e. amap, imap, uimap and map

v0.1.13

0.1.13 — 2022-11-25

Features

• Add option to return encoder features, and decoder features along the outputs in the forward pass of any model.

Fixes

• Turn the cellpose and stardist postproc dirs into modules.
  

v0.1.2

0.1.12 — 2022-11-03

Performance

• Reverse engineered the stardist post-processing pipeline to python. Accelerated it with Numba and optimized it even further. Now it runs almost 2x faster than the original C++ verion.

Fixes

• Fix bug with padding in SlidingWindowInferer
  

v0.1.11

0.1.11 — 2022-10-21

Removed

• unnecessary torchvision dependency

v0.1.10

0.1.10 — 2022-10-21

Removed

• torch-optimizer removed from the optional dependency list. Started to cause headache.