算法艺术创作
algorithmic-art
通过代码和可调参数创作生成艺术与交互式视觉效果。
visualization-and-submission【设计与创意】Guide NAVSIM camera, BEV, and LiDAR visualization plus safe two-stage submission pickle preparation and local validation.
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
Use this route for NAVSIM scene plots, sensor overlays, GIFs, or a locally
validated warmup/challenge submission.pkl.
plot_bev_frame, camera grids, annotations, LiDAR
overlays, custom plots, or GIF renderingwarmup_two_stage or the authorized private
private_test_hard_two_stage challenge pathpython scripts/validate_submission_metadata.py --help, then python scripts/validate_submission_metadata.py path/to/submission.pkl.Scene, sensor blobs, calibration, and a map
API for map layers; API/help checks do not need local data.AgentInput. The selected agent must
have requires_scene=False; a privileged agent that needs Scene or
annotations must stop before generation.This route owns plotting and pickle preparation/validation. Route installation, data layout, sensor contracts, agent implementation, and EPDMS scoring to the corresponding NAVSIM skills; use the links in the references when composing a larger workflow.