This reference guide provides a list of TensorFlow Lite operators the Arm NN SDK currently supports.
The Arm NN SDK TensorFlow Lite parser currently supports the following operators:
ADD
AVERAGE_POOL_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE
BATCH_TO_SPACE
CONCATENATION, 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
FULLY_CONNECTED, Supported Fused Activation: RELU , RELU6 , TANH, NONE
LOGISTIC
L2_NORMALIZATION
MAX_POOL_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE
MAXIMUM
MEAN
MINIMUM
MUL
PACK
PAD
RELU
RELU6
RESHAPE
RESIZE_BILINEAR
SLICE
SOFTMAX
SPACE_TO_BATCH
SPLIT
SQUEEZE
STRIDED_SLICE
SUB
TANH
TRANSPOSE
TRANSPOSE_CONV
UNPACK
Arm tested these operators with the following TensorFlow Lite neural network:
DeepSpeech v1 converted from TensorFlow model
DeepSpeaker
More machine learning operators will be supported in future releases.