• State Resolved
  • Locked Locked
  • Replies 2 replies
  • Subscribers 99 subscribers
  • Views 806 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.

TDA4VMXEVM: Model training using jacinto-ai/pytorch-mmdetection

Prithvi Kambhampati
Prodigy 235 points

Part Number: TDA4VMXEVM

Hi,

I am trying to train a ssd-lite-regnet-fpn model with jacinto-ai/pytorch-mmdetection and I am running into errors. I have installed open-mmlab/mmdetection and am able to train and test models. When I try to follow instructions on jacinto-ai/pytorch-mmdetection, I get the following error:

(open-mmlab) pkambhampati@usrdlx836as001:~/KTM/pytorch-mmdetection$ CUDA_VISIBLE_DEVICES=6,7 ./run_detection_train.sh
Training with: ./configs/ssd/ssd-lite_regnet_fpn_bgr.py @ 2020-09-02_21-13-54
*****************************************
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
*****************************************
Traceback (most recent call last):
Traceback (most recent call last):
File "./xmmdet/tools/train.py", line 14, in <module>
File "./xmmdet/tools/train.py", line 14, in <module>
from xmmdet.apis import set_random_seed, train_detectorfrom xmmdet.apis import set_random_seed, train_detector

ModuleNotFoundError: ModuleNotFoundErrorNo module named 'xmmdet':
No module named 'xmmdet'
Traceback (most recent call last):
File "./scripts/train_detection_main.py", line 30, in <module>
distributed_launch.main()
File "/data/home/pkambhampati/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/distributed/launch.py", line 257, in main
cmd=cmd)
subprocess.CalledProcessError: Command '['/data/home/pkambhampati/anaconda3/envs/open-mmlab/bin/python', '-u', './xmmdet/tools/train.py', '--local_rank=1', '--launcher=pytorch', './configs/ssd/ssd-lite_regnet_fpn_bgr.py']' returned non-zero exit status 1.
Done.

Are there any further steps that I need to follow to perform the training? 

 

Regards,

Prithvi

  • 0
    TI__Genius 11386 points

    Hi,

    Most probably it is due to a problem with your PYTHONPATH

    In your bash prompt, please type:

    echo $PYTHONPATH

    It has to start with a : to be able to user a local folder as a module. (In this case xmmdet is that local folder to be used as the module).

    If it doesn't, you can put the following at the end of your .bashrc to do that

    export PYTHONPATH=:$PYTHONPATH

    Be sure to close your current terminal and start a new one so that this .bashrc change takes effect.

    Let us know if this solves your problem. 

  • 0 in reply to Manu Mathew
    Prodigy 235 points

    Hi Manu,

    Thank you for the quick response. This did solve my problem. I had previously changed the PYTHONPATH variable because open-mmlab/mmdetection was issuing an error because of conflict with pycocotools.

    Thanks,

    Prithvi