Releases: HUST-NingKang-Lab/MGM
Releases · HUST-NingKang-Lab/MGM
Release Note – MGM v0.5.8
Fixes & Improvements
- Fixed dataset splitting issue (#2): Resolved a rounding error in dataset partitioning that caused random_split to fail when the sum of split sizes did not match the dataset length.
Upgrade Instructions
To update to the latest version, run:
pip install --upgrade microformer-mgm
If you encounter any issues, feel free to open a new issue on GitHub.
v0.5.7
Fixed bug in get_z and add genus name to reconstructed abundance table.
v0.5.6
Fixed no label provided in get_Z during reconstruct step.
v0.5.5
In this version, we fixed the library version and add accelerator library in requirements.txt to avoid conflict bug.
v0.5.1
In this release, we added new function in reconstruct mode.
v0.4.1
In this release, we fixed the bug that no tokenizer provided in generate function.
v0.4.0
In this release, you can train your generator with label file using pretrain mode and generate tensors following your prompt using generate mode