L2CS-Net gaze360 LiteRT fp16 (fully-GPU, Pixel 8a corr 0.9999, 3ms)

.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
+samples/sample.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,50 @@
+---
+license: mit
+library_name: LiteRT
+pipeline_tag: image-classification
+tags: [litert, tflite, on-device, android, gpu, gaze-estimation, l2cs, resnet, gaze360]
+base_model: Ahmednull/L2CS-Net
+---
+
+# L2CS-Net — LiteRT (on-device gaze estimation, fully-GPU)
+
+[L2CS-Net](https://github.com/Ahmednull/L2CS-Net) (Ahmednull) gaze estimation, converted to **LiteRT** and
+running **fully on the `CompiledModel` GPU** (ML Drift) on Android. Predicts where a centered face is looking
+(yaw/pitch). ResNet50 backbone trained on Gaze360.
+
+![L2CS-Net — face + gaze direction (on-device LiteRT GPU)](samples/sample.png)
+
+## On-device (Pixel 8a, Tensor G3 — verified)
+
+| | |
+|---|---|
+| nodes on GPU | **139 / 139** LITERT_CL (full residency) |
+| inference | **~3 ms** (448×448) |
+| size | 47.9 MB (fp16) |
+| accuracy | device-vs-PyTorch corr **0.9999**, gaze angle within ~0.1° |
+
+```
+face[1,3,448,448] (ImageNet-normalized) →[GPU: ResNet50]→ yaw[1,90], pitch[1,90] (softmax over angle bins)
+```
+
+The 90 bins span [-180,180]° (4° each); gaze angle = softmax expectation `Σ p_i·i · 4 − 180` (softmax baked in).
+
+## How it converts (litert-torch)
+
+Pure CNN (ResNet50 + 2 FC heads). Two numerically-exact ResNet fixes:
+1. **stem `MaxPool2d(3,s2,p1)` → zero-pad + valid max-pool** — PyTorch's max-pool pads with `-inf` → a `PADV2`
+   the Mali delegate won't delegate (compile fail); since the pool follows a ReLU, a 0-pad is exactly
+   equivalent → `PAD`, full GPU residency.
+2. **global `AdaptiveAvgPool2d(1)` → `mean(3).mean(2)`**.
+
+Result: banned ops NONE, all tensors ≤4D, tflite-vs-torch corr **1.0**, device-vs-torch corr **0.9999**.
+
+## Preprocessing & decode
+
+Center-crop to a (centered) face, resize 448×448, /255, ImageNet mean/std, NCHW. Decode: softmax expectation
+over the 90 bins → yaw/pitch degrees → gaze direction.
+
+## License
+
+[MIT](https://github.com/Ahmednull/L2CS-Net/blob/main/LICENSE). Upstream:
+[Ahmednull/L2CS-Net](https://github.com/Ahmednull/L2CS-Net).

gaze_fp16.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b16a8158ec0e252ee105e717177149655a60b71c8a1eccd97b873bf640c2a13d
+size 47868896