| --- |
| license: other |
| license_name: nuscenes-non-commercial |
| license_link: https://www.nuscenes.org/terms-of-use |
| library_name: libreyolo |
| pipeline_tag: object-detection |
| tags: |
| - fcos3d |
| - 3d-detection |
| - monocular |
| - nuscenes |
| - mmdetection3d |
| - non-commercial |
| - pytorch |
| --- |
| |
| # LibreFCOS3D |
|
|
| Byte-identical mirror of the official FCOS3D R101-DCN nuScenes checkpoint |
| (finetuned variant), for use with LibreYOLO's `LibreFCOS3D` inference adapter. |
|
|
| > ## ⚠️ NON-COMMERCIAL WEIGHTS, AND AN IMPLIED REDISTRIBUTION BASIS |
| > |
| > **These weights are not covered by LibreYOLO's MIT license.** Two separate |
| > restrictions apply, and both bind you, the downloader: |
| > |
| > 1. **Training data.** This checkpoint was trained solely on |
| > [nuScenes](https://www.nuscenes.org/nuscenes), whose |
| > [terms of use](https://www.nuscenes.org/terms-of-use) are |
| > **non-commercial**. Read them before use. |
| > 2. **No declared checkpoint license.** OpenMMLab publishes this file from its |
| > model zoo without any per-object license. The mmdetection3d repository |
| > states only that "this project is released under the Apache 2.0 license", |
| > which covers the *code*. LibreYOLO's maintainer approved this mirror by |
| > treating that project-level Apache-2.0 statement as the redistribution |
| > basis. **This is LibreYOLO's disclosed interpretation, not a |
| > clarification from the OpenMMLab authors.** |
| > |
| > The FCOS3D *architecture* and LibreYOLO's *code* are unrestricted, as is any |
| > model you train from scratch. Only these pretrained weights are limited. |
|
|
| ## Source |
|
|
| - Publisher: [open-mmlab/mmdetection3d](https://github.com/open-mmlab/mmdetection3d) |
| model zoo |
| - Original URL: |
| [`fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_finetune_20210717_095645-8d806dc2.pth`](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/fcos3d/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_finetune/fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_finetune_20210717_095645-8d806dc2.pth) |
| - SHA-256: `8d806dc2ecae85bc8eaba1f16dccdf03459317ca6aed7984cfda33c2a2bc33a8` |
| - Size: 220,360,589 bytes |
| - Published July 2021. |
|
|
| This is the **finetuned** variant (depth weight 1.0), not the 1x base model. |
| Published nuScenes val results: **32.1 mAP, 39.5 NDS**. |
|
|
| The LibreYOLO implementation that consumes it was adapted from |
| mmdetection3d at |
| [`fe25f7a`](https://github.com/open-mmlab/mmdetection3d/tree/fe25f7a51d36e3702f961e198894580d83c4387b) |
| and mmdetection at |
| [`cfd5d3a`](https://github.com/open-mmlab/mmdetection/tree/cfd5d3a985b0249de009b67d04f37263e11cdf3d), |
| both Apache-2.0. |
|
|
| ## Modifications |
|
|
| **None.** The checkpoint is mirrored byte-for-byte, retaining its original |
| filename, `state_dict`/`meta` structure and serialization. No tensor values or |
| metadata were changed. It is *not* converted to LibreYOLO's v1.0 checkpoint |
| schema — the adapter loads the unchanged official format directly. |
|
|
| ## Classes |
|
|
| The ten nuScenes detection classes, in the official order. LibreYOLO validates |
| the checkpoint's `meta.CLASSES` against that order and refuses a mismatch. |
|
|
| ## LibreYOLO usage |
|
|
| ```python |
| import numpy as np |
| from libreyolo import LibreFCOS3D |
| |
| model = LibreFCOS3D("fcos3d_r101_caffe_fpn_gn-head_dcn_2x8_1x_nus-mono3d_finetune_20210717_095645-8d806dc2.pth") |
| result = model.predict("image.jpg", intrinsics=np.load("intrinsics.npy")) |
| print(result.boxes3d.xyz) |
| ``` |
|
|
| FCOS3D is a sibling API, not part of the generic `LibreYOLO(...)` factory, |
| because prediction requires original-image pinhole camera intrinsics. Download |
| this file and pass its local path. Inference is CPU or CUDA; MPS is |
| unsupported (torchvision `deform_conv2d`). Training, validation, tracking and |
| export are not implemented. |
|
|
| ## Validation |
|
|
| LibreYOLO's native implementation was verified against the pinned upstream |
| Python implementation using this checkpoint: every `state_dict` key and shape |
| loads strictly, and final CPU detections match across six calibrated nuScenes |
| camera views at confidence thresholds 0.05, 0.15 and 0.30. This is adapter |
| parity, not an independent 3D accuracy benchmark; use the official nuScenes |
| evaluator for accuracy. |
|
|
| ## License |
|
|
| See [`LICENSE`](./LICENSE) for the upstream Apache-2.0 code license and the |
| checkpoint's separate terms, and [`NOTICE`](./NOTICE) for provenance and |
| mirroring details. |
|
|
