Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Instructions on train and inference. #4

Open
VikasRajashekar opened this issue Dec 2, 2021 · 3 comments
Open

Instructions on train and inference. #4

VikasRajashekar opened this issue Dec 2, 2021 · 3 comments

Comments

@VikasRajashekar
Copy link

First of all very nice work.

It would be very nice if you add minimum code/commands to train your model or do inference on it.
It will help the fellow community.

@Hatmm
Copy link
Owner

Hatmm commented Dec 2, 2021

You can try the following for training.

python $ROOT/train_net.py \
  --num-gpus 8 \
  --config-file PATH/configs/deform_detr.yaml

For inference add --eval-only

@VikasRajashekar
Copy link
Author

You can try the following for training.

python $ROOT/train_net.py \
  --num-gpus 8 \
  --config-file PATH/configs/deform_detr.yaml

For inference add --eval-only

Thanks is it possible to shared the trained model? and way to load it.

@Hatmm
Copy link
Owner

Hatmm commented Dec 2, 2021

Unfortunately, I do not currently own any trained model. To load weights specify the path in the config file, e.g., WEIGHTS.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants