Xilinx / Xilinx/finn

cycle-free graph violated: partition depends on itself

Open
#863 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.1k
Forks
308
Avg merge
3d 9h
Merged PRs (30d)
14

Description

Hi @fpjentzsch,
I ran into the same problem and I tried the same thing with ResNet-50 but it still failed.

In detail

I ran into a problem while executing model.transform(CreateDataflowPartition()).

image

I made some adjustments and tests (see https://github.com/Xilinx/finn/issues/860#issuecomment-1649853296 for details), but the error still occurred.

Then I looked at the answers in this issue, and I used the ResNet-50 process to re-tune my code, but I was still stuck.

Part of the onnx file when resnet-50 is not used, see https://github.com/Xilinx/finn/issues/860#issuecomment-1649853296

Part of the onnx file when using resnet-50, as follows.

image

image

I guessed that it was due to the concat operation, so I stopped using concat and split all the output, but still had the same problem.
image

I hope you can help me solve this problem.

Thanks again.

Originally posted by @Special-zhang in https://github.com/Xilinx/finn/discussions/431#discussioncomment-6546507

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 at the model.transform(CreateDataflowPartition()) call and compare the ONNX graph examples and adjustments linked from issue #860. Trace how the partitioning step detects dependencies, then reproduce the cycle with the reported ResNet-50 and non-ResNet graphs; done means identifying the cause and resolving or clearly documenting the self-dependency.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
compilers, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.