Upload README.md with huggingface_hub

README.md

@@ -7,7 +7,7 @@ tags:
 - on-device
 - image-segmentation
 ---
-# pidnet_s_cityscapes — ExecuTorch XNNPACK
+# pidnet_s_cityscapes — ExecuTorch
 
 - **Source**: XuJiacong/PIDNet + oenpu/PIDNet_S_enlight_friendly_onnx weights
 - **License**: MIT
@@ -18,14 +18,22 @@ tags:
 
 All variants take and return fp32 tensors — swap the `.pte` file, keep your app code.
 
-| precision | file | size (MB) | parity vs fp32 eager (worst corr) | Mac median (ms)* |
+| build | file | size (MB) | parity vs fp32 eager (worst corr) | Mac median (ms)* |
 |-----------|------|-----------|------------------------------------|------------------|
 | fp32 | `pidnet_s_cityscapes_xnnpack_fp32.pte` | 30.5 | 1.000000 | 27.6 |
+| Core ML (fp16, iOS) | `pidnet_s_cityscapes_coreml_all.pte` | 15.8 | 0.999998 | 6.1 |
+
+
+The Core ML build is the same graph lowered to Apple's Neural Engine instead of
+XNNPACK, which is CPU-only. On an iPhone 17 Pro, Depth-Anything-V2-Small runs
+500.8 ms through XNNPACK and 42.7 ms through Core ML, at half the file size. It
+computes in fp16 and is iOS-only; the XNNPACK files stay the portable option and
+are what runs on Android.
 
 \*Mac arm64, single process, median of 10 — a reference point for relative cost
 only, not a device number (torch eager fp32 on the same machine: 64.5 ms).
 
-### Precisions that did not earn a slot
+### Builds that did not earn a slot
 
 - **fp16 is not shipped**: it comes out at 100% of the fp32 file (30.5 MB vs 30.5 MB), so it buys nothing. XNNPACK serializes convolution weights as fp32 no matter what dtype the graph carries, so on a conv-heavy model fp16 saves no disk and only adds cast operations. Reach for int8 here, not fp16.
 - **int8 is not shipped**: measured in the units that matter for this model — fraction of pixels keeping their class: median 0.9802 over 10 real images, worst 0.8997.
@@ -43,5 +51,5 @@ XNNPACK delegate coverage (fp32): 96.3% (263/273 ops); ops left on the portable
 
 ## Conversion
 
-torch.export -> to_edge_transform_and_lower(XnnpackPartitioner) -> .pte
+torch.export -> to_edge_transform_and_lower(partitioner) -> .pte
 (conversion scripts: [executorch-models](https://github.com/john-rocky/executorch-models))