src/armnnTfLiteParser/TensorFlowLiteSupport.md

   1 # TensorFlow Lite operators that the Arm NN SDK supports
   2
   3 This reference guide provides a list of TensorFlow Lite operators the Arm NN SDK currently supports.
   4
   5 ## Fully supported
   6
   7 The Arm NN SDK TensorFlow Lite parser currently supports the following operators:
   8
   9 * ADD
  10
  11 * AVERAGE_POOL_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE
  12
  13 * BATCH_TO_SPACE
  14
  15 * CONCATENATION, Supported Fused Activation: RELU , RELU6 , TANH, NONE
  16
  17 * CONV_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE
  18
  19 * DEPTHWISE_CONV_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE
  20
  21 * FULLY_CONNECTED, Supported Fused Activation: RELU , RELU6 , TANH, NONE
  22
  23 * LOGISTIC
  24
  25 * MAX_POOL_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE
  26
  27 * MAXIMUM
  28
  29 * MEAN
  30
  31 * MINIMUM
  32
  33 * MUL
  34
  35 * PAD
  36
  37 * RELU
  38
  39 * RELU6
  40
  41 * RESHAPE
  42
  43 * RESIZE_BILINEAR
  44
  45 * SOFTMAX
  46
  47 * SPACE_TO_BATCH
  48
  49 * SPLIT
  50
  51 * SQUEEZE
  52
  53 * STRIDED_SLICE
  54
  55 * SUB
  56
  57 * TANH
  58
  59 * UNPACK
  60
  61 ## Custom Operator
  62
  63 * TFLite_Detection_PostProcess
  64
  65 ## Tested networks
  66
  67 Arm tested these operators with the following TensorFlow Lite neural network:
  68
  69 * [Quantized MobileNet](http://download.tensorflow.org/models/mobilenet_v1_2018_02_22/mobilenet_v1_1.0_224_quant.tgz)
  70
  71 * [Quantized SSD MobileNet](http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_quantized_300x300_coco14_sync_2018_07_18.tar.gz)
  72
  73 More machine learning operators will be supported in future releases.