efficientnet-lite4-int8

TensorFlow EfficientNet-Lite

Task
image-classification
Version
1.0.0
Licence
Apache-2.0
Source
TensorFlow EfficientNet-Lite

1 results

  • TCL Smart TV ProNPU · nnapi:mtk-mdla_shim

    22 msWorks with tweaks

    Tweak: Load the model from a memory-mapped buffer, not a path on shared storage: SELinux blocks the NN HAL (mtk_hal_neuralnetworks) from reading FUSE files, and NNAPI then silently falls back to its CPU reference path (~9 s per image).

    invoke p50 22 ms; full request (decode, render, pack, invoke) ~72 ms

    version 1.0.0 · 2026-11-18

Open in the live table