Project-MONAI / Project-MONAI/MONAI
refactor unet blocks to use the more recent layer api
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 8.7k
- Forks
- 1.6k
- Avg merge
- 5d 1h
- Merged PRs (30d)
- 20
Description
Is your feature request related to a problem? Please describe.
the previous implementations of get_*_layer
https://github.com/Project-MONAI/MONAI/blob/ff9ff55dd9198dabcc31eebe3109332ea708b356/monai/networks/blocks/dynunet_block.py#L133-L137
could now be replaced by Convolution
https://github.com/Project-MONAI/MONAI/blob/ff9ff55dd9198dabcc31eebe3109332ea708b356/monai/networks/blocks/convolutions.py#L24
this is however a breaking change, the existing versions should be kept and deprecated by renaming and with warnings in advance.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start in monai/networks/blocks/dynunet_block.py at the existing get_*_layer implementations and compare them with Convolution in monai/networks/blocks/convolutions.py. Determine the affected UNet blocks, preserve the existing versions under renamed deprecated entry points with warnings, and verify that the newer layer API replaces the current implementations without losing compatibility.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Refactor
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100