Skip to content

Latest commit

 

History

History
27 lines (14 loc) · 858 Bytes

TensorFlowLiteSupport.md

File metadata and controls

27 lines (14 loc) · 858 Bytes

TensorFlow Lite operators that the Arm NN SDK supports

This reference guide provides a list of TensorFlow Lite operators the Arm NN SDK currently supports.

The Arm NN SDK TensorFlow Lite parser currently only supports uint8.

Fully supported

The Arm NN SDK TensorFlow Lite parser currently supports the following operators:

  • AVERAGE_POOL_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE

  • CONV_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE

  • DEPTHWISE_CONV_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE

  • SOFTMAX

  • SQUEEZE

Tested networks

Arm tested these operators with the following TensorFlow Lite neural network:

More machine learning operators will be supported in future releases.