Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -31,9 +31,13 @@ head (174 classes of *physical interactions* — put/lift/push/roll/cover/preten
|
|
| 31 |
| path | what |
|
| 32 |
|---|---|
|
| 33 |
| `macos/vjepa2_ssv2_fp16.aimodel` | fp16 bundle (macOS / JIT) |
|
| 34 |
-
| `
|
|
|
|
| 35 |
| `macos/metadata.json` | I/O + preprocessing spec |
|
| 36 |
|
|
|
|
|
|
|
|
|
|
| 37 |
## Preprocessing
|
| 38 |
|
| 39 |
Sample 16 frames uniformly from the clip, resize+center-crop to 256×256, scale to 0..1, normalize
|
|
|
|
| 31 |
| path | what |
|
| 32 |
|---|---|
|
| 33 |
| `macos/vjepa2_ssv2_fp16.aimodel` | fp16 bundle (macOS / JIT) |
|
| 34 |
+
| `ios/vjepa2_ssv2_fp16.h18p.aimodelc` | iOS AOT bundle (iPhone, A18 Pro+ GPU) |
|
| 35 |
+
| `macos/labels.json`, `ios/labels.json` | 174 SSv2 class names |
|
| 36 |
| `macos/metadata.json` | I/O + preprocessing spec |
|
| 37 |
|
| 38 |
+
**Live demo app**: [coreai-video](https://github.com/john-rocky/coreai-model-zoo/tree/main/apps/coreai-video)
|
| 39 |
+
— camera → live top-3 actions. iPhone 17 Pro: ~0.34 s per 16-frame clip.
|
| 40 |
+
|
| 41 |
## Preprocessing
|
| 42 |
|
| 43 |
Sample 16 frames uniformly from the clip, resize+center-crop to 256×256, scale to 0..1, normalize
|