• State
  • Locked Locked
  • Replies 1 reply
  • Subscribers 101 subscribers
  • Views 279 views
  • Users 0 members are here
Support feedback
Options
Options
Related

This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

EDGE-AI-STUDIO: edgeaioptimization mmyolo lite

Taha Soliman
Prodigy 20 points
Part Number: EDGE-AI-STUDIO

Tool/software:

Currently i'm facing a major issue integrating the optimization mentioned in

https://github.com/TexasInstruments/edgeai-tensorlab/issues/7

As i integrate it with mmyolo as requested i face this issue.

from torch.fx.graph import _parse_stack_trace

ImportError: cannot import name '_parse_stack_trace' from 'torch.fx.graph

when i try to run the model after integrating the optimization i run into this issue. which when i tracked require torch with version 2.2 at least. Nevertheless mmyolo 0.6 which is the latest version require an earlier version same with cuda.

Hope you can guide me the environment you are currently using cause i tried several updates but reached a dead end.

  • 0
    TI__Prodigy 260 points

    Hi,

    The mmyolo repository requires torch version less than 2.1, because it depends on a particular version of mmcv. 

    I would suggest trying it again with a fresh clone of the repository,

    then apply our patch, and follow the following steps:

    1.  cd mmyolo
    2.  pip install torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 --index-url https://download.pytorch.org/whl/cu118
    3.  ./setup.sh
    4.  mim install -v -e .
    5.  pip install albumentations==1.3.1
    6.  pip install numpy==1.26.4

     (python version is 3.10)