search

aharley / simple_bev

A Simple Baseline for BEV Perception
MIT License
457 stars 70 forks source link

visualization problem #21

Closed ygjwd12345 closed 1 year ago

ygjwd12345 commented 1 year ago

Thanks for your wonderful work. I am trying to reproduce it, and the result looks great. So I want to further analyze the result. Could you share your visualization command?

aharley commented 1 year ago

It's here: https://github.com/aharley/simple_bev/blob/main/vis_nuscenes.py

ygjwd12345 commented 1 year ago

would you mind giving me a demo command?

aharley commented 1 year ago

what about python vis_nuscenes.py

ygjwd12345 commented 1 year ago

something like python eval_nuscenes.py \ --batch_size=16 \ --data_dir='../nuscenes' \ --log_dir='logs_eval_nuscenes_bevseg' \ --init_dir='checkpoints/8x5_5e-4_rgb12_22:43:46' \ --res_scale=2 \ --device_ids=[0,1,2,3]

aharley commented 1 year ago

I think if you adapt this slightly to the vis script, it will work... Can you try it and let me know a specific issue you can't fix?

ygjwd12345 commented 1 year ago

my problem. I will test first.

ygjwd12345 commented 1 year ago

Thank you so much. I have successfully visualized the model. the command like python vis_nuscenes.py --data_dir='/home/xx/data/datatset/nuscenes/trainval' --init_dir='checkpoints/16x5_3e-4s_rgb_mine_09:22:16'