Depth Anything V2 Small for Core AI, nine input sizes

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+img-depth-anything-v2-small-float32.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,46 @@
+---
+license: apache-2.0
+base_model: depth-anything/Depth-Anything-V2-Small
+tags:
+  - depth-estimation
+  - monocular-depth
+  - depth-anything
+  - core-ai
+  - apple-silicon
+  - macos
+library_name: swift-depth-estimator
+---
+
+# img-depth-anything — Depth Anything V2 Small for Core AI (macOS 27)
+
+[Depth Anything V2](https://github.com/DepthAnything/Depth-Anything-V2) Small (Yang, Kang, Ming,
+Xu, Feng and Zhao, NeurIPS 2024; Apache 2.0) exported from the authors' own code and checkpoint
+(`depth_anything_v2_vits.pth`) to an Apple Core AI `.aimodel` for on-device monocular depth. Read
+by [swift-depth-estimator](https://github.com/arraypress/swift-depth-estimator) and the
+[`img depth`](https://github.com/arraypress/swift-img-cli) verb.
+
+## Files
+
+| Path | What |
+|---|---|
+| `img-depth-anything-v2-small-float32.aimodel/` | Nine entry points, one per input size the authors' `Resize` (shorter side 518, multiples of 14, `lower_bound`) produces for common aspect ratios: `h518w518`, `h518w686`, `h686w518`, `h518w784`, `h784w518`, `h518w924`, `h924w518`, `h518w826`, `h826w518`. Each takes an ImageNet-normalised RGB image `[1, 3, H, W]` and returns relative inverse depth `[1, H, W]` (larger is nearer). Float32, 102 MB — the weights are shared. |
+
+The host reproduces `infer_image`: OpenCV `INTER_CUBIC` on the image in 0…1, ImageNet mean and
+standard deviation, the network, then bilinear upsampling with `align_corners=True` back to the
+picture's own size. A picture whose aspect ratio maps to a size not in the list uses the nearest.
+
+## Fidelity
+
+Against the authors' PyTorch model on the CPU, on their demo images cropped to every exported
+ratio: prepared tensors above 100 dB PSNR (the cubic resampler is exact), network outputs
+111–127 dB, whole images end to end 113–130 dB.
+
+## Use
+
+```sh
+hf download arraypress/img-depth-anything --local-dir models
+img depth install models/img-depth-anything-v2-small-float32.aimodel
+img depth photo.jpg        # photo-depth.png, nearer is brighter
+```
+
+Requires macOS 27 (Core AI) on Apple silicon. Converted with coreai-torch 0.4.2 / torch 2.13.

img-depth-anything-v2-small-float32.aimodel/main.hash

@@ -0,0 +1 @@
+����F#E|����o�\�.�})|9Ai�r

img-depth-anything-v2-small-float32.aimodel/main.mlirb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aebc9f94623457c9b07ded1da6ffd5c1e962e12d096cb7d297c0e394169eb72
+size 101694147

img-depth-anything-v2-small-float32.aimodel/metadata.json

@@ -0,0 +1,8 @@
+{
+  "license" : "Apache-2.0",
+  "producer" : "coreai-core 1.0.0b2",
+  "creationDate" : "20260924T152434Z",
+  "assetVersion" : "2.0",
+  "author" : "Yang, Kang, Ming, Xu, Feng, Zhao — Depth Anything V2 (NeurIPS 2024), Small; Core AI export by DepthEstimator",
+  "description" : "Depth Anything V2 Small: entry points h518w518, h518w686, h686w518, h518w784, h784w518, h518w924, h924w518, h518w826, h826w518 take an ImageNet-normalised RGB image [1,3,H,W] and return relative inverse depth [1,H,W]. Preprocess and upsample in the host as the authors' infer_image does."
+}