LibreDDRNets-sem

DDRNet-23-slim Cityscapes 19-class semantic segmentation weights, converted for LibreYOLO.

Cityscapes non-commercial notice. These weights were trained on Cityscapes, whose license restricts the dataset and its derivatives to non-commercial use. See Dataset terms.

Source

Derived from ydhongHIT/DDRNet at commit de0db317c5af4b0946231f475cf74ca4f51b8ac2. The source checkpoint is the official DDRNet-23-slim Cityscapes checkpoint linked from the upstream README (Google Drive, SHA-256 688dd42edbd623d21a6fe67c4b90ef8a5913d2824214a49bb60d94c61e6544b4), val mIoU 77.8 as reported upstream. Copyright (c) 2020 xingkong. Licensed under the MIT License.

Modifications

Converted with weights/convert_ddrnet_weights.py in the LibreYOLO source repository. Key rename only: the model. training-wrapper prefix is stripped and the loss.criterion.weight buffer is dropped. Learned parameters are unchanged, including the auxiliary head used for training. weights/parity_ddrnet.py checks the port against the official code with max_abs_diff == 0. The tensors are wrapped with LibreYOLO checkpoint metadata (model_family=ddrnet, size=s, task=semantic, nc=19, evaluation canvas 1024x2048).

Usage

pip install libreyolo
from libreyolo import LibreYOLO

model = LibreYOLO("LibreDDRNets-sem.pt")
result = model("street.jpg", save=True)

License

MIT License, on an implied basis. The upstream repository links these weights from its README and states no separate terms for them, so LibreYOLO hosts them under the repository's MIT license on that implied basis. This is LibreYOLO's disclosed interpretation, not a license confirmed by the publisher. See the LICENSE and NOTICE files in this repository.

Dataset terms

These weights were trained on Cityscapes. The Cityscapes license permits distributing abstract derivative models from which the dataset cannot be recovered, and restricts the dataset and its derivatives to non-commercial use. Check those terms before using these pretrained weights commercially. The dataset is not redistributed in this repository. Weights trained from the ImageNet backbones (LibreYOLO/LibreDDRNet{s,m,l}-imagenet) or from scratch on your own data carry no Cityscapes term; a fine-tune started from this checkpoint inherits it.

Downloads last month
31
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support