| --- |
| license: other |
| library_name: pytorch |
| tags: |
| - occupancy-prediction |
| - semantic-occupancy |
| - embodied-ai |
| - occscannet |
| - adaocc |
| - radio |
| - depth-anything-v2 |
| --- |
| |
| # AdaOcc checkpoints |
|
|
| **AdaOcc: Adaptive 3D Occupancy Prediction for Embodied Tasks** |
|
|
| Project page / code / setup instructions: <https://github.com/wangjl-nb/AdaOcc> |
|
|
| This Hugging Face repository only hosts the public AdaOcc checkpoint assets. It does not include OccScanNet data, generated labels/depth maps, RADIO weights, or the Depth-Anything-V2 fine-tuned checkpoint. |
|
|
| ## Uploaded files |
|
|
| | file | description | target path in the AdaOcc repo | |
| | --- | --- | --- | |
| | `pretrain/fusion_pretrain_model.pth` | Slim fusion pretrain initializer for training AdaOcc from scratch. | `pretrain/fusion_pretrain_model.pth` | |
| | `checkpoints/adaocc_online_depth_occscannet_mini_epoch200.pth` | Trained AdaOcc online-depth OccScanNet-mini epoch-200 checkpoint for direct evaluation. | `checkpoints/adaocc_online_depth_occscannet_mini_epoch200.pth` | |
| | `configs/radio_occscannet_mini_training_snapshot.py` | Config snapshot from the released training run. | reference only | |
| | `logs/online_depth_occscannet_mini_epoch200.log` | Training/evaluation log for the released checkpoint. | reference only | |
| | `SHA256SUMS` | Checksums for hosted assets. | reference only | |
|
|
| The released evaluation checkpoint reports `mIoU=58.49` and `IoU=65.49` on OccScanNet-mini; see the uploaded log for the full validation line. |
|
|
| ## Download |
|
|
| Run from the AdaOcc GitHub repository root: |
|
|
| ```bash |
| hf download wjldragon/AdaOcc \ |
| pretrain/fusion_pretrain_model.pth \ |
| checkpoints/adaocc_online_depth_occscannet_mini_epoch200.pth \ |
| --local-dir . |
| ``` |
|
|
| Use `--local-dir .` so the checkpoint paths are restored exactly under `pretrain/` and `checkpoints/`. Do not use `--local-dir pretrain` or `--local-dir checkpoints`, which would create nested paths such as `pretrain/pretrain/...`. |
|
|
| ## Fusion pretrain note |
|
|
| `pretrain/fusion_pretrain_model.pth` is a slim OPUS-derived initializer. It keeps the sparse middle-encoder weights used by AdaOcc's public config (`pts_middle_encoder.*`) and removes unused branches. The extraction script is in the GitHub project at `scripts/extract_adaocc_fusion_pretrain.py`. |
|
|
| For data preparation, environment setup, training, evaluation, and upstream asset instructions, please use the GitHub project: <https://github.com/wangjl-nb/AdaOcc>. |
|
|
