Tier 2: demo videos, sample clip with expected output, smoke test, results.json, model-index, training data
97a0336 verified | IDM inverse dynamics models | |
| Copyright 2026 Reka AI | |
| The weights and code in this repository use the Apache License 2.0 (see LICENSE). | |
| RAFT-small optical flow weights: BSD-3-Clause, from torchvision | |
| (torchvision.models.optical_flow.raft_small). flow/inference.py downloads them at | |
| run time. They are not part of this repository and are not redistributed here. | |
| Videos in assets/ and examples/ (not Apache 2.0) | |
| Source: walking tours by POPtravel on Wikimedia Commons, CC BY 3.0 | |
| (https://creativecommons.org/licenses/by/3.0/). The videos in assets/ add the model overlay. | |
| The video in examples/ is a shortened, re-encoded excerpt. Changes were made. | |
| Bristol: https://commons.wikimedia.org/wiki/File:Walking_in_BRISTOL_-_UK_-_4K_60fps_(UHD).webm | |
| Ingolstadt: https://commons.wikimedia.org/wiki/File:Walking_in_INGOLSTADT_-_Germany_-_4K_60fps_(UHD).webm | |
| Bamberg: https://commons.wikimedia.org/wiki/File:Walking_in_BAMBERG_-_Germany_-_4K_60fps_(UHD).webm | |