mlcommons / mlcommons/chakra

unable to decode Chakra output .json

Open
#137 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
196
Forks
84
PR merge metrics
No merged PRs in 30d

Description

Describe the Bug

The DataDeps for layer id =207, name = add_ shows DataDeps = 206. Layer 206 is cudnn_convolution layer the output tensor ids of layer 206 dont seem to match input tensor id of layer 206. Could you help in clarifying.

Steps to Reproduce

Steps to reproduce the behavior.
Please include the version information where the bug was observed.

Expected Behavior

A clear and concise description of what you expected to happen.

Screenshots

If applicable, add screenshots to help explain your problem.

Attaching chakra output .json file for reference.
resnet_inf_test.csv

chakra_output_json.json

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 inspecting the attached chakra_output_json.json and resnet_inf_test.csv, focusing on the dependency and tensor IDs for layers 206 and 207. Compare the reported output IDs of the cudnn_convolution layer with the input IDs of the add_ layer, then determine whether the mismatch comes from the decoder or the supplied data.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
tooling
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.