| --- |
| license: bsd-3-clause |
| library_name: libreyolo |
| pipeline_tag: image-segmentation |
| datasets: |
| - detection-datasets/coco |
| tags: |
| - semantic-segmentation |
| - deeplabv3 |
| - torchvision |
| - pascal-voc |
| - libreyolo |
| --- |
| |
| # LibreDeepLabv3mv3-sem |
|
|
| DeepLabv3 semantic segmentation with dilated MobileNetV3-Large, output stride 16, repackaged for |
| LibreYOLO. It predicts background plus 20 Pascal VOC-named foreground classes |
| from a checkpoint trained on the matching COCO subset. This is DeepLabv3, not |
| DeepLabv3+; there is no decoder or CRF. |
|
|
| ```python |
| from libreyolo import LibreYOLO |
| |
| model = LibreYOLO("LibreDeepLabv3mv3-sem.pt") |
| result = model.predict("image.jpg") |
| mask = result.semantic_mask.data |
| ``` |
|
|
| ## Source |
|
|
| Derived from [pytorch/vision](https://github.com/pytorch/vision) at commit |
| [`336d36e8db990a905498c73933e35231876e28bc`](https://github.com/pytorch/vision/commit/336d36e8db990a905498c73933e35231876e28bc) |
| (torchvision v0.26.0). Copyright (c) Soumith Chintala 2016 and torchvision |
| contributors. The source implementation is BSD-3-Clause. |
|
|
| Official checkpoint: [deeplabv3_mobilenet_v3_large-fc3c493d.pth](https://download.pytorch.org/models/deeplabv3_mobilenet_v3_large-fc3c493d.pth) |
| Bytes: `44356159` |
| SHA-256: `fc3c493d68e89cc31ef488c803d5d7dd2f3190fb570598faa49fef69be8e5e70` |
| Published mIoU / pixel accuracy: 60.3 / 91.2. |
|
|
| The published metrics use torchvision's aspect-preserving evaluation preset. |
| LibreYOLO uses a fixed 520x520 stretch deployment contract, followed by |
| ImageNet normalization and restoration of the output mask to the source |
| canvas, so end-to-end metrics can differ. |
|
|
| ## Modifications and verification |
|
|
| Conversion removes only the training-time `aux_classifier.*` tensors and adds |
| LibreYOLO v1.0 checkpoint metadata. Every retained runtime tensor and state-dict |
| key is unchanged. The native 520x520 logits are bit-exact against the pinned |
| torchvision implementation before postprocessing (`max_abs_diff == 0.0`). |
|
|
| The fixed-shape deployment graph was also tested through LibreYOLO's unified |
| backend: |
|
|
| - ONNX Runtime CPU: 100% identical public mask pixels; maximum logit difference |
| `3.06e-5`. |
| - TorchScript: bit-exact logits and 100% identical public mask pixels. |
| - OpenVINO CPU: 99.9876% identical public mask pixels using |
| the runtime's default reduced-precision execution hint. |
| - TensorRT 10.16 FP32 on RTX 5070 Ti: 99.9851% identical public |
| mask pixels. |
|
|
| The converted file has `44325189` bytes and SHA-256 |
| `fb83a67bca845817d816d139af6fb6a4b9d809c0a813ebcfcb1e2a5fbd222682`. See `docs/provenance/deeplabv3.md` and |
| `weights/convert_deeplabv3_weights.py` in the |
| [LibreYOLO source repository](https://github.com/LibreYOLO/libreyolo). |
|
|
| ## License |
|
|
| The checkpoint publisher did not attach a separate per-object license file. |
| This mirror applies the releasing project's BSD-3-Clause license on an |
| **implied, not publisher-confirmed**, basis. Torchvision warns that pretrained |
| models may have licenses or terms derived from training data and that users |
| must determine whether they have permission for their use case. COCO |
| annotations are CC BY 4.0; source images retain their individual Flickr terms. |
| See [`LICENSE`](./LICENSE) and [`NOTICE`](./NOTICE). |
|
|
