Instructions to use JerryYuu/BrickCraft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use JerryYuu/BrickCraft with ultralytics:
from huggingface_hub import hf_hub_download from ultralytics import YOLO # pick the weights file from this repo's "Files and versions" tab weights = hf_hub_download("JerryYuu/BrickCraft", "<weights>.pt") model = YOLO(weights) source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
|
Download README.md from JerryYuu/BrickCraft: direct link, hf CLI and curl.
- Browser
- Download file 2.12 kB
-
https://huggingface.co/JerryYuu/BrickCraft/resolve/main/README.md
- Command line
-
hf download hf://JerryYuu/BrickCraft/README.md
-
curl -L -o README.md https://huggingface.co/JerryYuu/BrickCraft/resolve/main/README.md
2.12 kB
| license: agpl-3.0 | |
| library_name: ultralytics | |
| pipeline_tag: image-segmentation | |
| tags: | |
| - brickcraft | |
| - yolov8 | |
| - instance-segmentation | |
| - robotics | |
| # BrickCraft model checkpoints | |
| Task-specific YOLOv8n-seg checkpoints used by the single-arm BrickCraft assembly pipeline. | |
| - [Project website](https://intelligent-control-lab.github.io/BrickCraft/) | |
| - [Paper](https://arxiv.org/abs/2605.07605) | |
| ## Included checkpoints | |
| | Path | Purpose | Class IDs | | |
| | --- | --- | --- | | |
| | `yolo/seg_structure.pt` | Segment the assembled brick structure for scene alignment | `0: object` | | |
| | `yolo/seg_brick_gripper.pt` | Segment the target brick and gripper | `0: brick`, `1: gripper` | | |
| See [the YOLO checkpoint notes](yolo/README.md) for loading instructions and provenance. The checkpoint metadata records Ultralytics version `8.4.8`; packaging did not include a compatibility test with other versions. | |
| ## Download | |
| ```bash | |
| hf download JerryYuu/BrickCraft --local-dir ./models/BrickCraft | |
| ``` | |
| From the BrickCraft code repository root, configure: | |
| ```json | |
| { | |
| "yolo_seg_structure_ckpt": "./models/BrickCraft/yolo/seg_structure.pt", | |
| "yolo_seg_brick_gripper_ckpt": "./models/BrickCraft/yolo/seg_brick_gripper.pt" | |
| } | |
| ``` | |
| For reproducibility, pin `--revision` to the model repository commit used in your experiment. | |
| ## Scope and verification | |
| This release contains the two YOLO checkpoints only. SAM-2 and Brick Diffusion policy checkpoints are not included. These files alone do not provide the complete robot execution stack. | |
| The checkpoint files are preserved without modification. Their ZIP archive integrity and SHA256 checksums were verified during packaging. Inference accuracy, CUDA execution, and physical robot operation were not tested during packaging. | |
| ## License | |
| The included YOLO checkpoints are based on Ultralytics YOLOv8 and are distributed under AGPL-3.0. See [LICENSE](yolo/LICENSE) and [Ultralytics licensing information](https://www.ultralytics.com/license). This statement concerns the files included in this model repository; additional models added in future releases must document their own applicable terms. | |