---
license: mit
library_name: libreyolo
pipeline_tag: object-detection
tags:
  - object-detection
  - oriented-object-detection
  - gtr
  - pytorch
  - libreyolo
  - dota
datasets:
  - DOTA
---

# LibreGTRx-obb

GTR-X oriented-box weights for DOTA v1.0, converted for LibreYOLO.

GTR support is being prepared for LibreYOLO v1.6.0. Earlier PyPI releases may
not include this model family.

## Usage

With a LibreYOLO version that includes GTR OBB:

```python
from libreyolo import LibreYOLO
model = LibreYOLO("LibreGTRx-obb.pt")
result = model.predict("aerial.jpg")
result.obb.xywhr  # (cx, cy, w, h, theta) in pixels, theta in [0, pi)
```

The input is a fixed 1024 by 1024 pixel square. Images are resized to fit and
padded at the bottom and right. Class ids follow the upstream DOTA v1.0 order:
plane, baseball-diamond, bridge, ground-track-field, small-vehicle,
large-vehicle, ship, tennis-court, basketball-court, storage-tank,
soccer-ball-field, roundabout, harbor, swimming-pool, helicopter. This
checkpoint is inference-only in LibreYOLO.

## Source

[Official GTR implementation](https://github.com/Intellindust-AI-Lab/GTR/tree/782e737efe2e6437ac537fbdcee089673d3376c1),
source revision `782e737efe2e6437ac537fbdcee089673d3376c1`.

[Published checkpoint](https://huggingface.co/Phoenix8125/GTR/blob/9fc62c8c2b2c976835d0f1c1ffc544dbc0f9e29f/obb/gtrobb_x_dota.pth),
weight repository revision `9fc62c8c2b2c976835d0f1c1ffc544dbc0f9e29f`.
Copyright (c) 2026 Intellindust-AI-Lab. The source code is MIT licensed and the
publisher's weight repository explicitly declares MIT. The publisher reports
81.3 AP50 on the DOTA-v1.0 test set; LibreYOLO has not reproduced it.

## Modifications

Selected the EMA state dict and added LibreYOLO schema v1.0 metadata.
Learned parameters and state-dict keys are unchanged. Training/optimizer state
was removed. Conversion uses `weights/convert_gtr_weights.py` in the
[LibreYOLO source repository](https://github.com/LibreYOLO/libreyolo).

## Validation

Checkpoint schema, exact tensor preservation and strict loading were checked
for this artifact. On CPU its logits and rotated boxes match the pinned
upstream graph exactly, and decoded boxes match upstream's post-processor.
DOTA benchmark accuracy and GPU latency were not independently reproduced.

## License

MIT. See [LICENSE](./LICENSE) and [NOTICE](./NOTICE).