litert-community / L2CS-Gaze360-LiteRT

huggingface.co
Total runs: 234
24-hour runs: 0
7-day runs: -10
30-day runs: 125
Model's Last Updated: September 08 2026
image-classification

Introduction of L2CS-Gaze360-LiteRT

Model Details of L2CS-Gaze360-LiteRT

L2CS-Net — LiteRT (on-device gaze estimation, fully-GPU)

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)

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 . Upstream: Ahmednull/L2CS-Net .

Runs of litert-community L2CS-Gaze360-LiteRT on huggingface.co

234
Total runs
0
24-hour runs
0
3-day runs
-10
7-day runs
125
30-day runs

More Information About L2CS-Gaze360-LiteRT huggingface.co Model

More L2CS-Gaze360-LiteRT license Visit here:

https://choosealicense.com/licenses/mit

L2CS-Gaze360-LiteRT huggingface.co

L2CS-Gaze360-LiteRT huggingface.co is an AI model on huggingface.co that provides L2CS-Gaze360-LiteRT's model effect (), which can be used instantly with this litert-community L2CS-Gaze360-LiteRT model. huggingface.co supports a free trial of the L2CS-Gaze360-LiteRT model, and also provides paid use of the L2CS-Gaze360-LiteRT. Support call L2CS-Gaze360-LiteRT model through api, including Node.js, Python, http.

litert-community L2CS-Gaze360-LiteRT online free

L2CS-Gaze360-LiteRT huggingface.co is an online trial and call api platform, which integrates L2CS-Gaze360-LiteRT's modeling effects, including api services, and provides a free online trial of L2CS-Gaze360-LiteRT, you can try L2CS-Gaze360-LiteRT online for free by clicking the link below.

litert-community L2CS-Gaze360-LiteRT online free url in huggingface.co:

https://huggingface.co/litert-community/L2CS-Gaze360-LiteRT

L2CS-Gaze360-LiteRT install

L2CS-Gaze360-LiteRT is an open source model from GitHub that offers a free installation service, and any user can find L2CS-Gaze360-LiteRT on GitHub to install. At the same time, huggingface.co provides the effect of L2CS-Gaze360-LiteRT install, users can directly use L2CS-Gaze360-LiteRT installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

L2CS-Gaze360-LiteRT install url in huggingface.co:

https://huggingface.co/litert-community/L2CS-Gaze360-LiteRT

Url of L2CS-Gaze360-LiteRT

Provider of L2CS-Gaze360-LiteRT huggingface.co

litert-community
ORGANIZATIONS

Other API from litert-community