---
license: mit
library_name: libreyolo
pipeline_tag: depth-estimation
tags:
  - depth-estimation
  - monocular-depth
  - gtr
  - pytorch
  - libreyolo
---

# LibreGTRl-depth

GTR-L monocular depth 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 depth:

```python
from libreyolo import LibreYOLO
model = LibreYOLO("LibreGTRl-depth.pt")
result = model.predict("image.jpg")[0]
inverse_depth = result.depth_map
```

The default input is a 640 by 640 stretch resize. This checkpoint supports the
`depth` task only.

## Output

`Results.depth_map` is relative inverse depth on the original image canvas:
higher values are closer. The network's native output is metric depth from a
log-depth head (`exp(clamp(logit, -4, 5))` metres); LibreYOLO returns its exact
reciprocal, so `1 / depth_map` recovers the metre estimate. That scale holds
only for cameras and scenes like the training data; treat it as relative
otherwise.

## 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/depth/gtrdepth_l.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 model was pretrained by its authors on a mixed metric-depth corpus (SUN
RGB-D, DIODE, Virtual KITTI 2, KITTI, Hypersim, TartanAir, ARKitScenes and
ImageNet pseudo-labels).

## 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

Strict loading and exact CPU parity with the pinned upstream graph (maximum
absolute difference 0.0 on the metre output at 640px, portable attention) were
checked for this artifact, along with CPU prediction and fixed-resolution
ONNX/TorchScript export. No independently reproduced benchmark accuracy or
latency numbers are claimed here.

## License

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