Stuck on an issue?

Lightrun Answers was designed to reduce the constant googling that comes with debugging 3rd party libraries. It collects links to all the places you might be looking at while hunting down a tough bug.

And, if you’re still stuck at the end, we’re happy to hop on a call to see how we can help out.

Unable to find model file

See original GitHub issue

Hello, Thank you so much for sharing a very much useful repository.

I have followed the step by step instructions given, and have downloaded all the datasets as mentioned in the below image

Training: python main.py configs/resa/resa50_culane.py --gpus 0

After running the above command, i was able to see following window:

But i couldn’t find any model file such as culane_resnet50.pth , resa_r34_culane.pth !! As it mentioned in the example run case.

Alternatively, is it possible to share the pre-trained model file?

As I am a beginner, I greatly appreciate your understanding and kind response.

Regards, Ajay

Issue Analytics

State:
Created a year ago
Comments:5 (2 by maintainers)

Top GitHub Comments

1reaction

Turoadcommented, May 6, 2022

Sorry, no ROS support.

1reaction

Turoadcommented, May 6, 2022

Just rename it, i.e., 11.pth to resa50_culane.pth. The best.pth is trained using resnet50 backbone. You cannot use resnet34 to load the weight. Try this:

python tools/detect.py configs/resa/resa50_culane.py --img images\ --load_from /lanedet/work_dirs/CULane/20220504_091910_lr_3e-02_b_8/ckpt/best.pth --savedir ./vis