|
Download README.md from LibreYOLO/LibreECx-obj2coco: direct link, hf CLI and curl.
- Browser
- Download file 2.78 kB
-
https://huggingface.co/LibreYOLO/LibreECx-obj2coco/resolve/main/README.md
- Command line
-
hf download hf://LibreYOLO/LibreECx-obj2coco/README.md
-
curl -L -o README.md https://huggingface.co/LibreYOLO/LibreECx-obj2coco/resolve/main/README.md
2.78 kB
| license: other | |
| license_name: edgecrafter-non-commercial | |
| license_link: LICENSE | |
| library_name: libreyolo | |
| pipeline_tag: object-detection | |
| datasets: | |
| - detection-datasets/coco | |
| tags: | |
| - edgecrafter | |
| - objects365 | |
| - non-commercial | |
| # LibreECx-obj2coco | |
| **NON-COMMERCIAL USE ONLY. Commercial use requires a separate license from | |
| INTELLINDUST. These weights are not covered by LibreYOLO's MIT license.** | |
| EdgeCrafter X for detect, pretrained on Objects365 and fine-tuned | |
| on COCO. This is an explicit opt-in variant; the COCO-only default is | |
| `LibreECx.pt`. This file is not the raw 365-class pretraining model. | |
| ```python | |
| from libreyolo import LibreYOLO | |
| model = LibreYOLO("LibreECx-obj2coco.pt") | |
| results = model.predict("image.jpg") | |
| ``` | |
| Requires a LibreYOLO version containing EC `obj2coco` filename support. | |
| Existing versions can load a downloaded local checkpoint path if they already | |
| support the corresponding EC task. | |
| ## Source | |
| Official asset: [ecdet_x_o3652coco.pth](https://github.com/capsule2077/edgecrafter/releases/download/edgecrafterv1_o365/ecdet_x_o3652coco.pth) | |
| - Release: `edgecrafterv1_o365` (August 14, 2026) | |
| - Source SHA-256: `be9c77cd4def8aadd0cc679944ba57412f363de2d44f7c6b900289e61316314c` | |
| - Converted SHA-256: `d9409110af0d22eb62caad6f2c5f5786b3b1b197eacc3d9c4112e8d926b3bf88` | |
| Copyright (c) 2026 INTELLINDUST INFORMATION TECHNOLOGY (SHENZHEN) CO., LTD. | |
| ## Modifications and validation | |
| Conversion selects the released EMA when present and adds LibreYOLO metadata. | |
| Learned tensors and state-dict keys are unchanged, verified tensor by tensor. | |
| Checkpoint schema, factory loading, complete parameter coverage, and a finite | |
| 640-pixel CPU forward pass were checked. COCO accuracy and export parity have | |
| not been independently re-evaluated for this mirror. | |
| Converter: [convert_ec_weights.py](https://github.com/LibreYOLO/libreyolo/blob/feat/ec-o365/weights/convert_ec_weights.py). | |
| ## License | |
| [EdgeCrafter License](https://github.com/Intellindust-AI-Lab/EdgeCrafter/blob/124cb0922ebe4af55c025af448312c2374210815/LICENSE.md); included verbatim in [LICENSE](./LICENSE). | |
| See [NOTICE](./NOTICE) for attribution and the license history. | |
| The release asset repository still carries Apache-2.0. The main project | |
| changed to non-commercial terms on August 20, 2026, after this August 14 release. | |
| LibreYOLO's maintainer chose the stricter EdgeCrafter terms for this optional | |
| mirror. This is a disclosed redistribution policy, not upstream clarification | |
| of the conflicting notices or a claim that earlier Apache grants were revoked. | |
| Objects365's [dataset terms](https://www.objects365.org/download.html) state | |
| academic-purpose availability, CC BY 4.0 annotations, and separate image | |
| restrictions. This repository redistributes model weights, not dataset images. | |