You need to agree to share your contact information to access this model
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
These are trained DeepStarNoodles weights (StarSeg, Hydra, Noodle Tracer, temporal VAE). Access is gated so we know who has the locked recipe. DINOv3 backbone weights are not included; download those from Meta under the DINOv3 License.
Log in or Sign Up to review the conditions and access this model content.
DeepStarNoodles weights
Locked inference and retrain weights for DeepStarNoodles.
| File | Role | SHA-256 |
|---|---|---|
starseg/starseg_best.pt |
StarSeg detector (YOLOv8) | 0252e49d3b201f5fe557536d37648ff6ff8ac1ca2c303ec7b5c707f1973a9414 |
hydra/epoch_060.pt |
18-channel Hydra parent | b3423e9bab886777e04825945434b8d42609b3c3fde0cd270d2fe2668c411eec |
hydra/endpoint_mse_best.pt |
Released dense Hydra | dcf7140c9ef0129d8f66b33b05af6d0ebb064f84b41ce61e51e67061799e3f02 |
tracer/noodle_tracer_seed20260807_endpoint_mse_calibrated.pt |
Noodle Tracer | bb7f1b5da4f998006163b0bfbba005b417dfd6e8ab313d8e3869b7224fcc5c6c |
temporal_vae/dnt_progress_temporal_vae_60s_sleepy.pt |
Optional 60-second progress temporal VAE | 182de7d66d3b670c94e25d4f78070d7ffa5851acd76200cc7c059849b1abddc9 |
First-party weights are MIT, matching the GitHub code. StarSeg inference uses Ultralytics (AGPL-3.0). The DINOv3 ConvNeXt-Base backbone is not in this repo; get dinov3_convnext_base_pretrain_lvd1689m-801f2ba9.pth from Meta (SHA-256 801f2ba95801bdcc9a8b77e293d38b35b355dbc813ef609cd82e18c3a185e8da).
The temporal VAE is an inference-only export of the frozen DeepNoodleTracker
checkpoint at step 10,250. It expects one support-weighted 64×64 progress raster
per second and produces a 64-D posterior mean from a centered window spanning
−30 through +29 seconds. It was trained from Hydra checkpoint
3f691daa14a891a5f9ad163355d969f8922892c662d4d9b7864a54fd815eecee.
The currently released Hydra checkpoint has the same channel contract, but its
output distribution has not yet been scientifically revalidated with this VAE.
Use the released VAE as the default reproducible recipe or fine-tune a new model
through the configurable representation API.
Download into a DeepStarNoodles checkout
hf download weertman/deepstarnoodles --local-dir MODELS
Then place the Meta DINOv3 file at MODELS/dinov3/dinov3_convnext_base_pretrain_lvd1689m-801f2ba9.pth and run SCRIPTS/validate_artifacts.py. That check skips Ultralytics yolo26l-seg.pt unless you add it for StarSeg from-scratch training.