---
license: mit
library_name: libreyolo
pipeline_tag: object-detection
tags:
  - object-detection
  - gtr
  - pytorch
  - libreyolo
  - coco
datasets:
  - detection-datasets/coco
---

# LibreGTRx

GTR-X COCO detection weights 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:

```python
from libreyolo import LibreYOLO
model = LibreYOLO("LibreGTRx.pt")
results = model.predict("image.jpg")
```

The default input is 640 by 640 pixels. This checkpoint supports detection.

## 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/det/gtr_x_coco.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.

## 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, strict loading and CPU prediction
were checked for this artifact. CUDA parity, independent COCO accuracy and RF1
training validation are deferred to the LibreYOLO v1.6.0 release checks.
No independently reproduced accuracy or latency numbers are claimed here.

## License

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