Total runs:
887.1K
Run Growth:
378.4K
Growth Rate:
43.78%
Sponsored by
Vmake Labs Video Enhancer
apple / coreml-depth-anything-v2-small
Model's Last Updated: June 25 2024
depth-estimation
Introduction of coreml-depth-anything-v2-small
Model Details of coreml-depth-anything-v2-small
Depth Anything V2 Core ML Models
Depth Anything V2 was introduced in the paper of the same name by Lihe Yang et al. It uses the same architecture as the original Depth Anything release, but uses synthetic data and a larger capacity teacher model to achieve much finer and robust depth predictions. The original Depth Anything model was introduced in the paper Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data by Lihe Yang et al., and was first released in this repository .
Model description
Depth Anything V2 leverages the DPT architecture with a DINOv2 backbone.
The model is trained on ~600K synthetic labeled images and ~62 million real unlabeled images, obtaining state-of-the-art results for both relative and absolute depth estimation.
Depth Anything overview. Taken from the original paper .
Evaluation - Variants
| Variant | Parameters | Size (MB) | Weight precision | Act. precision | abs-rel error | abs-rel reference |
|---|---|---|---|---|---|---|
| small-original (PyTorch) | 24.8M | 99.2 | Float32 | Float32 | ||
| DepthAnythingV2SmallF32 | 24.8M | 99.2 | Float32 | Float32 | 0.0072 | small-original |
| DepthAnythingV2SmallF16 | 24.8M | 49.8 | Float16 | Float16 | 0.0089 | small-original |
Evaluated on 512 landscape images from the COCO dataset with aspect ratio similar to 4:3. Images were streched to a fixed size of 518x396, and the groundtruth corresponds to the results from the PyTorch model running on CUDA with
float32
precision.
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
brew install huggingface-cli
To download one of the
.mlpackage
folders to the
models
directory:
huggingface-cli download \
--local-dir models --local-dir-use-symlinks False \
apple/coreml-depth-anything-v2-small \
--include "DepthAnythingV2SmallF16.mlpackage/*"
To download everything, skip the
--include
argument.
Integrate in Swift apps
The
huggingface/coreml-examples
repository contains sample Swift code for
DepthAnythingV2SmallF16.mlpackage
and other models. See
the instructions there
to build the demo app, which shows how to use the model in your own Swift apps.
Runs of apple coreml-depth-anything-v2-small on huggingface.co
43.0K
Total runs
1.2K
24-hour runs
3.9K
3-day runs
12.6K
7-day runs
38.3K
30-day runs
More Information About coreml-depth-anything-v2-small huggingface.co Model
Url of coreml-depth-anything-v2-small
coreml-depth-anything-v2-small huggingface.co Url
Provider of coreml-depth-anything-v2-small huggingface.co
Other API from apple
Updated:March 01 2025
Total runs:
173.0K
Run Growth:
150.5K
Growth Rate:
86.92%
Total runs:
136.9K
Run Growth:
123.3K
Growth Rate:
90.38%
Total runs:
32.0K
Run Growth:
3.5K
Growth Rate:
11.40%
Total runs:
25.3K
Run Growth:
14.5K
Growth Rate:
59.09%
Total runs:
22.9K
Run Growth:
-32.9K
Growth Rate:
-118.52%
Total runs:
21.9K
Run Growth:
-42.4K
Growth Rate:
-182.35%
Total runs:
13.7K
Run Growth:
-17.9K
Growth Rate:
-124.22%
Total runs:
7.7K
Run Growth:
-223.3K
Growth Rate:
-2581.45%
Total runs:
7.5K
Run Growth:
-1.5K
Growth Rate:
-20.11%
Total runs:
6.9K
Run Growth:
-1.1K
Growth Rate:
-16.96%
Total runs:
5.8K
Run Growth:
4.7K
Growth Rate:
81.46%
Total runs:
5.4K
Run Growth:
-1.3M
Growth Rate:
-6019.86%
Total runs:
3.3K
Run Growth:
436
Growth Rate:
13.85%
Total runs:
3.0K
Run Growth:
2.7K
Growth Rate:
90.83%
Total runs:
2.5K
Run Growth:
1.4K
Growth Rate:
57.92%
Total runs:
2.3K
Run Growth:
-685
Growth Rate:
-30.61%
Total runs:
1.5K
Run Growth:
1.2K
Growth Rate:
80.18%
Total runs:
1.5K
Run Growth:
1.2K
Growth Rate:
73.99%
Total runs:
1.5K
Run Growth:
932
Growth Rate:
63.53%
Total runs:
1.3K
Run Growth:
-218
Growth Rate:
-16.01%
Total runs:
1.3K
Run Growth:
-187
Growth Rate:
-11.87%
Total runs:
1.2K
Run Growth:
34
Growth Rate:
3.00%
Total runs:
1.1K
Run Growth:
-459
Growth Rate:
-40.76%
Total runs:
765
Run Growth:
-441
Growth Rate:
-58.18%
Total runs:
686
Run Growth:
151
Growth Rate:
23.63%
Total runs:
683
Run Growth:
-77
Growth Rate:
-11.56%
Total runs:
667
Run Growth:
-252
Growth Rate:
-38.77%
Total runs:
593
Run Growth:
-838
Growth Rate:
-141.32%
Total runs:
511
Run Growth:
5
Growth Rate:
1.01%
Total runs:
449
Run Growth:
297
Growth Rate:
66.59%
Total runs:
438
Run Growth:
234
Growth Rate:
53.42%
Total runs:
434
Run Growth:
11
Growth Rate:
2.56%
Total runs:
425
Run Growth:
-12
Growth Rate:
-2.86%
Total runs:
415
Run Growth:
6
Growth Rate:
1.51%
Total runs:
383
Run Growth:
-29
Growth Rate:
-7.34%
Total runs:
357
Run Growth:
74
Growth Rate:
20.61%
Total runs:
347
Run Growth:
-22
Growth Rate:
-6.34%
Total runs:
279
Run Growth:
145
Growth Rate:
51.97%
Total runs:
244
Run Growth:
-70
Growth Rate:
-29.29%
Total runs:
240
Run Growth:
-145
Growth Rate:
-62.50%
Total runs:
231
Run Growth:
-86
Growth Rate:
-35.54%
Total runs:
212
Run Growth:
-76
Growth Rate:
-35.02%
Total runs:
202
Run Growth:
173
Growth Rate:
86.07%
Total runs:
155
Run Growth:
-120
Growth Rate:
-79.47%
Total runs:
141
Run Growth:
-29
Growth Rate:
-20.14%
Total runs:
138
Run Growth:
66
Growth Rate:
47.83%
Total runs:
131
Run Growth:
-170
Growth Rate:
-121.43%
Total runs:
126
Run Growth:
40
Growth Rate:
31.75%
Total runs:
118
Run Growth:
-311
Growth Rate:
-252.85%
Total runs:
112
Run Growth:
-1
Growth Rate:
-0.89%
Total runs:
51
Run Growth:
-82
Growth Rate:
-122.39%
Total runs:
48
Run Growth:
-133
Growth Rate:
-282.98%
Total runs:
41
Run Growth:
-19
Growth Rate:
-47.50%
Total runs:
38
Run Growth:
-79
Growth Rate:
-207.89%