Search results

  1. C

    Benchmarking the A311D / VIM3 NPU

    Could you provide detail results, including int8 result on mobilenet, because it is more meaningful than generic score.
  2. C

    Benchmarking the A311D / VIM3 NPU

    yep, just build using android A311D toolchain https://github.com/VeriSilicon/tflite-vx-delegate however, the building process was not straightfoward.
  3. C

    Benchmarking the A311D / VIM3 NPU

    I find out that vendor of NPU (VeriSilicon) created custom TFLite Delegate on their github repository. After running tflite benchmark I've got 6.5 msec on single thread MobileNet v2 on NPU delegate
Top