Commit History
-
Drop barrel, add held-out stop-sign distance, add the GPU runbook
Aryan Sethi +1: Claude Opus 5 (1M context)Barrel is out of the pipeline: schema carries three classes, the Argoverse 2 extractor no longer maps CONSTRUCTION_BARREL, and depth routing follows. AV2 barrels are still read to locate the road surface for the per-log camera-height fit -- they rest on the road and there are many of them -- but they never become labels. Distance is now verified on data the model never saw: 20 further Argoverse 2 logs, 2,431 frames, 6,332 objects, scored with the existing checkpoint rather than retraining. The pinhole estimator comes out far better there than on nuScenes -- 0.21 m median error under 10 m, 0.79 m overall at 5% off, 98% within 25% -- because AV2 calibration is derived per log and its camera has higher angular resolution, while the nuScenes figure was dominated by one scene with a road gradient. Stop-sign distance is measured for the first time: 21 detections, 9.22 m median, 18% off. Thin, and reported as such. The count is a data limit rather than a threshold one -- AV2 stop signs sit …5d449ff
-
Publish the dataset to the Hub and verify the round trip
Aryan Sethi +1: Claude Opus 5 (1M context)Aryan006/cone-distance-v1, private: 2.38 GB as three tar shards alongside the manifest, sixteen calibration files, the derived class priors and a generated card. Private deliberately -- nuScenes and Argoverse 2 carry non-commercial research licences that restrict redistributing derived imagery. Pulled it back down and checked it, since "uploaded" and "trains on Colab" are not the same claim: 8,446 train and 1,815 val images restored as real files rather than dangling links, every image paired with a label, data.yaml rewritten to an absolute path. Both hub tools now read HF_TOKEN from the environment. A token passed as --token is visible to anyone who can run ps. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>529f79d -
Phase 1: unified data pipeline, QA and training
Aryan Sethi +1: Claude Opus 5 (1M context)Extract cones, barriers, barrels and stop signs from nuScenes, Argoverse 2, COCO and BDD100K into one manifest carrying camera intrinsics and ground-truth distance, then train YOLO11n and YOLO11s on the derived YOLO export. The manifest is the artifact, not the .txt files: .txt cannot hold intrinsics or gt distance, and phase 2's geometric distance estimator needs both. 2D boxes are projected from the 3D cuboids rather than taken from a pre-made 2D annotation file, so boxes and distances come from one convention. merge.py asserts the cross-dataset geometry rather than leaving it to be eyeballed -- distance positive, distance and box-bottom row negatively correlated within a camera, median cone distance plausible. A coordinate convention mismatch otherwise produces a manifest that trains fine and makes the depth numbers nonsense a day later. Extraction and export run locally; only training moves to Colab, so the dataset is published to the Hugging Face Hub as tar shards with the mani…9274a8d