| ---
|
| tags:
|
| - depth-estimation
|
| library_name: coreml
|
| license: apple-ascl
|
| base_model:
|
| - apple/DepthPro
|
| ---
|
|
|
| This repo contains [DepthPro.mlpackage](DepthPro.mlpackage)(1900 MB).
|
|
|
| # DepthPro CoreML Models
|
|
|
| DepthPro is a monocular depth estimation model. This means that it is trained to predict depth on a single image.
|
|
|
| [DepthPro paper](https://arxiv.org/pdf/2410.02073)
|
|
|
| [DepthPro original repo](https://huggingface.co/apple/DepthPro)
|
|
|
| # Model Inputs and Outputs
|
|
|
| ### Inputs
|
|
|
| - `image`: $1536 \times 1536$ 3 color image ($[1 \times 3 \times 1536 \times 1536]$ ImageType).
|
| - `originalWidth`: A scalar containing the original width of the image before resizing ($[1 \times 1 \times 1 \times 1]$ TensorType).
|
|
|
| ### Outputs
|
|
|
| - `depthMeters`: $1536 \times 1536$ 1 channel tensor containing depth in meters ($[1 \times 1 \times 1536 \times 1536]$ Tensor).
|
|
|
| # Download
|
|
|
| Install `huggingface-cli`
|
|
|
| ```bash
|
| brew install huggingface-cli
|
| ```
|
|
|
| To download:
|
|
|
| ```bash
|
| huggingface-cli download \
|
| --local-dir models --local-dir-use-symlinks False \
|
| coreml-projects/DepthPro-coreml \
|
| --include "DepthPro.mlpackage/*""
|
| ```
|
|
|
| To download everything, skip the `--include` argument.
|
|
|
| # Conversion Tutorial
|
|
|
| The [`huggingface/coreml-examples`](https://github.com/huggingface/coreml-examples/blob/main/tutorials/DepthPro/depth_pro_coreml_guide.ipynb) repository contains sample conversion code for `DepthPro.mlpackage` and other models.
|
|
|
| # Swift Integration
|
|
|
| The [`huggingface/coreml-examples`](https://github.com/huggingface/coreml-examples/blob/main/DepthProSample/README.md) repository contains sample Swift code for `DepthPro.mlpackage` and other models. See [the instructions there](https://github.com/huggingface/coreml-examples/tree/main/DepthProSample) to build the demo app, which shows how to use the model in your own Swift apps. |
