Project-MONAI / Project-MONAI/MONAI

PHL filtering with more than 16 channels

Open
#5,279 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Feature request
Dominant language
Python
Stars
8.7k
Forks
1.6k
Avg merge
5d 1h
Merged PRs (30d)
20

Description

Hello,

I am trying to play with the CRF block. Here is the current error message I got:

  File "/home/bastien/.virtualenvs/cbct-z52AAXGJ/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/bastien/.virtualenvs/cbct-z52AAXGJ/lib/python3.8/site-packages/monai/networks/blocks/crf.py", line 97, in forward
    bilateral_output = PHLFilter.apply(output_tensor, bilateral_features)
  File "/home/bastien/.virtualenvs/cbct-z52AAXGJ/lib/python3.8/site-packages/monai/networks/layers/filtering.py", line 93, in forward
    output_data = _C.phl_filter(input, scaled_features)
RuntimeError: PHL filtering not implemented for channel count > 16

Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.

Is there any plan to increase this?

Thank you!

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading monai/networks/blocks/crf.py around the PHLFilter call and monai/networks/layers/filtering.py where _C.phl_filter is invoked. Trace the implementation behind that binding and its channel-count limitation. Done means CRF PHL filtering accepts inputs with more than 16 channels and the existing behavior remains intact.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.