DepthPro Coreml Normalized Inverse Depth

--- tags: - depth-estimation library_name: coreml license: apple-ascl base_model: - apple/DepthPro --- This repo contains [DepthProNormalizedInverseDepth.mlpackage](DepthProNormalizedInverseDepth.mlpackage)(1290 MB). `Normaized Inverse Depth` means that the model will output values between $[0,1]$ where 1 is the closest pixel to the camera, and 0 is the furthest pixel from the camera. # 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). ### Outputs - `normalizedInverseDepth` 1536x1536 monochrome image ($[1 \times 1 \times 1536 \times 1536]$ ImageType). # 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-normalized-inverse-depth \ --include "DepthProNormalizedInverseDepth.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 `DepthProNormalizedInverseDepth.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 `DepthProNormalizedInverseDepth.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.