| | --- |
| | tags: |
| | - depth-estimation |
| | library_name: coreml |
| | license: apache-2.0 |
| | --- |
| | |
| | # Depth Anything Core ML Models |
| |
|
| | Depth Anything model was introduced in the paper [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://arxiv.org/abs/2401.10891) by Lihe Yang et al. and first released in [this repository](https://github.com/LiheYoung/Depth-Anything). |
| |
|
| | ## Model description |
| |
|
| | Depth Anything leverages the [DPT](https://huggingface.co/docs/transformers/model_doc/dpt) architecture with a [DINOv2](https://huggingface.co/docs/transformers/model_doc/dinov2) backbone. |
| |
|
| | The model is trained on ~62 million images, obtaining state-of-the-art results for both relative and absolute depth estimation. |
| |
|
| | <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/depth_anything_overview.jpg" |
| | alt="drawing" width="600"/> |
| |
|
| | <small> Depth Anything overview. Taken from the <a href="https://arxiv.org/abs/2401.10891">original paper</a>.</small> |
| |
|
| | ## Evaluation - Variants |
| |
|
| | | Variant | Parameters | Size (MB) | Weight precision | Act. precision | abs-rel error | abs-rel reference | |
| | | ------------------------------------------------------- | ---------: | --------: | ---------------- | -------------- | ------------: | ----------------: | |
| | | [small-original](https://huggingface.co/LiheYoung/depth-anything-small-hf) (PyTorch) | 24.8M | 99.2 | Float32 | Float32 | | | |
| | | [DepthAnythingSmallF32](DepthAnythingSmallF32.mlpackage) | 24.8M | 99.0 | Float32 | Float32 | 0.0073 | small-original | |
| | | [DepthAnythingSmallF16](DepthAnythingSmallF16.mlpackage) | 24.8M | 45.8 | Float16 | Float16 | 0.0077 | small-original | |
| |
|
| | ## Evaluation - Inference time |
| |
|
| | The following results use the small-float16 variant. |
| |
|
| | | Device | OS | Inference time (ms) | Dominant compute unit | |
| | | -------------------- | ---- | ------------------: | --------------------- | |
| | | iPhone 12 Pro Max | 18.0 | 31.10 | Neural Engine | |
| | | iPhone 15 Pro Max | 17.4 | 33.90 | Neural Engine | |
| | | MacBook Pro (M1 Max) | 15.0 | 32.80 | Neural Engine | |
| | | MacBook Pro (M3 Max) | 15.0 | 24.58 | Neural Engine | |
| |
|
| |
|
| | ## Download |
| |
|
| | Install `huggingface-cli` |
| |
|
| | ```bash |
| | brew install huggingface-cli |
| | ``` |
| |
|
| | To download one of the `.mlpackage` folders to the `models` directory: |
| |
|
| | ```bash |
| | huggingface-cli download \ |
| | --local-dir models --local-dir-use-symlinks False \ |
| | apple/coreml-depth-anything-small \ |
| | --include "DepthAnythingSmallF16.mlpackage/*" |
| | ``` |
| |
|
| | To download everything, skip the `--include` argument. |
| |
|
| | ## Integrate in Swift apps |
| |
|
| | The [`huggingface/coreml-examples`](https://github.com/huggingface/coreml-examples/blob/main/depth-anything-example/README.md) repository contains sample Swift code for `coreml-depth-anything-small` and other models. See [the instructions there](https://github.com/huggingface/coreml-examples/tree/main/depth-anything-example) to build the demo app, which shows how to use the model in your own Swift apps. |
| |
|
