DepthPro2-H / README.md
lucasnewman's picture
Upload folder using huggingface_hub
e38ec16 verified
|
Raw History Blame Contribute Delete
1.54 kB
---
license: other
license_name: apple-amlr
license_link: LICENSE
base_model:
- apple/DepthPro2-H
- apple/DepthPro2-focal
library_name: mlx-vlm
pipeline_tag: depth-estimation
tags:
- mlx
- metric-depth
- monocular-depth
- video-depth
---
# DepthPro2-H
This MLX derivative of Apple's Depth Pro 2 estimates metric depth from photos,
video, and live RGB frames. It includes the shared focal-length estimator.
The conversion repacks the convolution kernels for MLX and preserves Apple's
float32 weights. It adds an MLX model configuration and bundles the focal
estimator with the depth model.
## Usage
```sh
pip install mlx-vlm
```
```python
from mlx_vlm import load
from mlx_vlm.models.depth_pro_2.generate import DepthPro2Predictor, read_image
model, processor = load("nativ-community/DepthPro2-H")
predictor = DepthPro2Predictor(model, processor)
result = predictor.infer(read_image("photo.jpg"))
depth_m = result["depth"]
focal_px = result["focallength_px"]
```
See the [model documentation](https://github.com/Neywa-Labs/mlx-vlm/blob/main/mlx_vlm/models/depth_pro_2/README.md)
for video and live streams.
## License
Apple Machine Learning Research Model is licensed under the Apple Machine
Learning Research Model License Agreement.
The weights and this MLX derivative are for non-commercial scientific research
and academic development. The full agreement is included in [LICENSE](LICENSE).
See the [original model family](https://huggingface.co/apple/DepthPro2) for
architecture, evaluation, and citation information.