ModelPrésentéExterne

BambiMot

Trained model checkpoints for the BAMBI Wildlife MOT project: detection and multi-object tracking of wildlife (Wild boar, Red deer, Roe deer) in aerial thermal imagery from the BAMBI dataset.

Sourcehuggingface.co/NavidGh/BambiMot/tree/7a9dcff64e41ac45025b6b67fe811f2add3750db

TypeOtherVersionRevision 7a9dcffCClasse

Source du modèle

Type: Other
Taille du fichier: 16,9–527 MB
Version: vRevision 7a9dcff
Mis à jour: 16 sept. 2026
Téléchargements: 0
Source: Hugging Face

Description de la source

BAMBI Wildlife MOT — trained weights

Trained model checkpoints for the BAMBI Wildlife MOT project: detection and multi-object tracking of wildlife (Wild boar, Red deer, Roe deer) in aerial thermal imagery from the BAMBI dataset.

Code, documentation, and reproduction instructions: https://github.com/Navid-alt/BAMBI_MOT

These weights are git-ignored in the source repo because of their size and are hosted here instead. File paths below mirror where each script writes/expects the checkpoint in the repo checkout.

Files

Detectors

Model	File	Place at (in repo checkout)
YOLO26-s (640)	`yolo26-s/runs/train_yolo26-s/weights/best.pt`	`detection_models/yolo26-s/runs/train_yolo26-s/weights/best.pt`
YOLO26-l (1024)	`yolo26-l/runs/train_yolo26-l_1024/weights/best.pt`	`detection_models/yolo26-l/runs/train_yolo26-l_1024/weights/best.pt`
YOLO26-l (default res)	`yolo26-l/runs/train_yolo26-l/weights/best.pt`	`detection_models/yolo26-l/runs/train_yolo26-l/weights/best.pt`
RF-DETR-l — EMA (recommended)	`rf-detr-l/output/checkpoint_best_ema.pth`	`detection_models/rf-detr-l/output/checkpoint_best_ema.pth`
RF-DETR-l — regular	`rf-detr-l/output/checkpoint_best_regular.pth`	`detection_models/rf-detr-l/output/checkpoint_best_regular.pth`

*/weights/last.pt (YOLO) and rf-detr-l/output/{checkpoint_39,last}.ckpt (full training state incl. optimizer, ~527 MB each) are included for full reproducibility but are not needed for inference.

Learned tracker (TrackAssociator, MOTRv2-style)

File	Notes
`transformer_tracking/output/associator_last.pth`	Final associator — use this for inference
`transformer_tracking/output/associator_epoch{0..9}.pth`	Per-epoch checkpoints

The associator runs on top of the frozen RF-DETR-l detector (checkpoint_best_ema.pth above).

Classes

0: Wild boar · 1: Red deer · 2: Roe deer

Usage

Download a file and drop it at the path listed above; the detection/tracking scripts pick it up automatically. Example:

from huggingface_hub import hf_hub_download

ckpt = hf_hub_download(
    repo_id="NavidGh/BambiMot",
    filename="rf-detr-l/output/checkpoint_best_ema.pth",
)

See the GitHub repo's detection_models/readme.md and transformer_tracking/README.md for training and evaluation commands.

Sources

1 source

Hugging FacePrincipalVersion 7a9dcff64e41ac45025b6b67fe811f2add3750db

huggingface.co/NavidGh/BambiMot/tree/7a9dcff64e41ac45025b6b67fe811f2add3750db

Vérifié 2 sept.

Download files

Artefacts du modèle

21 artefacts

rf-detr-l/output/checkpoint_39.ckpt

ckpt · 527 MB · SHA-256 709603053c11…7029 · Hugging Face

Download file

rf-detr-l/output/checkpoint_best_ema.pth

pth · 132 MB · SHA-256 b280452e64e8…7ff8 · Hugging Face

Download file

rf-detr-l/output/checkpoint_best_regular.pth

pth · 132 MB · SHA-256 bee2c7b5a503…649b · Hugging Face

Download file

rf-detr-l/output/last.ckpt

ckpt · 527 MB · SHA-256 bc2d9ef4da7b…8fe2 · Hugging Face

Download file

transformer_tracking/output/associator_epoch0.pth

pth · 16,9 MB · SHA-256 62a7b6440227…d635 · Hugging Face

Download file

transformer_tracking/output/associator_epoch1.pth

pth · 16,9 MB · SHA-256 8915ee1b2dd1…f46b · Hugging Face

Download file

transformer_tracking/output/associator_epoch2.pth

pth · 16,9 MB · SHA-256 45c0bf70dfdf…192b · Hugging Face

Download file

transformer_tracking/output/associator_epoch3.pth

pth · 16,9 MB · SHA-256 ec78b01c129e…1896 · Hugging Face

Download file

transformer_tracking/output/associator_epoch4.pth

pth · 16,9 MB · SHA-256 c002c5034c2c…7fb6 · Hugging Face

Download file

transformer_tracking/output/associator_epoch5.pth

pth · 16,9 MB · SHA-256 85a231d58d0c…2f68 · Hugging Face

Download file

transformer_tracking/output/associator_epoch6.pth

pth · 16,9 MB · SHA-256 d2e6c07310e8…259f · Hugging Face

Download file

transformer_tracking/output/associator_epoch7.pth

pth · 16,9 MB · SHA-256 2efe9d6ce030…e114 · Hugging Face

Download file

transformer_tracking/output/associator_epoch8.pth

pth · 16,9 MB · SHA-256 eff1b97e5234…d580 · Hugging Face

Download file

transformer_tracking/output/associator_epoch9.pth

pth · 16,9 MB · SHA-256 ec8bed7de0eb…a76a · Hugging Face

Download file

transformer_tracking/output/associator_last.pth

pth · 16,9 MB · SHA-256 cdddbc9db35f…8823 · Hugging Face

Download file

yolo26-l/runs/train_yolo26-l_1024/weights/best.pt

pt · 50,6 MB · SHA-256 51c2bd0ad6a6…e838 · Hugging Face

Download file

yolo26-l/runs/train_yolo26-l_1024/weights/last.pt

pt · 50,6 MB · SHA-256 cb4bc983abe2…43ed · Hugging Face

Download file

yolo26-l/runs/train_yolo26-l/weights/best.pt

pt · 50,5 MB · SHA-256 2632a6321884…e818 · Hugging Face

Download file

yolo26-l/runs/train_yolo26-l/weights/last.pt

pt · 50,5 MB · SHA-256 ee78e6bc00bd…cf42 · Hugging Face

Download file

yolo26-s/runs/train_yolo26-s/weights/best.pt

pt · 19,4 MB · SHA-256 feb2a61b1d9e…9d5e · Hugging Face

Download file

yolo26-s/runs/train_yolo26-s/weights/last.pt

pt · 19,4 MB · SHA-256 0b9198c92646…c429 · Hugging Face

Download file

Extraits de sources

2 extraits

Readme2 sept.huggingface.co/NavidGh/BambiMot

--- license: cc-by-nc-4.0 tags: - object-detection - multi-object-tracking - thermal - wildlife - yolo - rf-detr library_name: pytorch --- # BAMBI Wildlife MOT — trained weights Trained model checkpoints for the **BAMBI Wildlife MOT** project: detection and multi-object tracking of wildlife (Wild boar, Red deer, Roe deer) in aerial **thermal** imagery from the [BAMBI dataset](https://www.bambi.eco/). Code, documentation, and reproduction instructions: **https://github.com/Navid-alt/BAMBI_MOT** These weights are git-ignored in the source repo because of their size and are hosted here instead. File paths below mirror where each script writes/expects the checkpoint in the repo checkout. ## Files ### Detectors | Model | File | Place at (in repo checkout) | |---|---|---| | YOLO26-s (640) | `yolo26-s/runs/train_yolo26-s/weights/best.pt` | `detection_models/yolo26-s/runs/train_yolo26-s/weights/best.pt` | | YOLO26-l (1024) | `yolo26-l/runs/train_yolo26-l_1024/weights/best.pt` | `detection_models/yolo26-l/runs/train_yolo26-l_1024/weights/best.pt` | | YOLO26-l (default res) | `yolo26-l/runs/train_yolo26-l/weights/best.pt` | `detection_models/yolo26-l/runs/train_yolo26-l/weights/best.pt` | | RF-DETR-l — EMA (recommended) | `rf-detr-l/output/checkpoint_best_ema.pth` | `detection_models/rf-detr-l/output/checkpoint_best_ema.pth` | | RF-DETR-l — regular | `rf-detr-l/output/checkpoint_best_regular.pth` | `detection_models/rf-detr-l/output/checkpoint_best_regular.pth` | `*/weights/last.pt` (YOLO) and `rf-detr-l/output/{checkpoint_39,last}.ckpt` (full training state incl. optimizer, ~527 MB each) are included for full reproducibility but are **not needed for inference**. ### Learned tracker (TrackAssociator, MOTRv2-style) | File | Notes | |---|---| | `transformer_tracking/output/associator_last.pth` | Final associator — use this for inference | | `transformer_tracking/output/associator_epoch{0..9}.pth` | Per-epoch checkpoints | The associator runs on top of the **frozen** RF-DETR-l detector (`checkpoint_best_ema.pth` above). ## Classes `0: Wild boar` · `1: Red deer` · `2: Roe deer` ## Usage Download a file and drop it at the path listed above; the detection/tracking scripts pick it up automatically. Example: ```python from huggingface_hub import hf_hub_download ckpt = hf_hub_download( repo_id="NavidGh/BambiMot", filename="rf-detr-l/output/checkpoin...

Note2 sept.huggingface.co/NavidGh/BambiMot

Source context: 0 downloads · 0 likes · Pipeline object-detection · Library pytorch · Repo NavidGh/BambiMot