src/armnnTfParser/TensorFlowSupport.md

   1 #TensorFlow operators that the Arm NN SDK supports
   2
   3 This reference guide provides a list of TensorFlow operators the Arm NN SDK currently supports.
   4
   5 The Arm NN SDK TensorFlow parser currently only supports fp32 operators.
   6
   7 These are the TensorFlow operators that the Arm NN SDK currently supports:
   8
   9 **avg_pool**
  10
  11 See the TensorFlow [avg_pool documentation](https://www.tensorflow.org/api_docs/python/tf/nn/avg_pool) for more information.
  12
  13 **bias_add**
  14
  15  See the TensorFlow [bias_add documentation](https://www.tensorflow.org/api_docs/python/tf/nn/bias_add) for more information.
  16
  17 **conv2d**
  18
  19  See the TensorFlow [conv2d documentation](https://www.tensorflow.org/api_docs/python/tf/nn/conv2d) for more information.
  20
  21 **identity**
  22
  23 See the TensorFlow [identity documentation](https://www.tensorflow.org/api_docs/python/tf/identity) for more information.
  24
  25 **local_response_normalization**
  26
  27 See the TensorFlow [local_response_normalization documentation](https://www.tensorflow.org/api_docs/python/tf/nn/local_response_normalization)  for more information.
  28
  29 **max_pool**
  30
  31 See the TensorFlow [max_pool documentation](https://www.tensorflow.org/api_docs/python/tf/nn/max_pool) for more information.
  32
  33 **relu**
  34
  35  See the TensorFlow [relu documentation](https://www.tensorflow.org/api_docs/python/tf/nn/relu) for more information.
  36
  37 **relu6**
  38
  39  See the TensorFlow [relu6 documentation](https://www.tensorflow.org/api_docs/python/tf/nn/relu6) for more information.
  40
  41 **shape**
  42
  43  See the TensorFlow [shape documentation](https://www.tensorflow.org/api_docs/python/tf/shape) for more information.
  44
  45 **sigmoid**
  46
  47  See the TensorFlow [sigmoid documentation](https://www.tensorflow.org/api_docs/python/tf/sigmoid) for more information.
  48
  49 **softplus**
  50
  51 See the TensorFlow [softplus documentation](https://www.tensorflow.org/api_docs/python/tf/nn/softplus) for more information.
  52
  53 **squeeze**
  54
  55 See the TensorFlow [squeeze documentation](https://www.tensorflow.org/api_docs/python/tf/squeeze) for more information.
  56
  57 **tanh**
  58
  59 See the TensorFlow [tanh documentation](https://www.tensorflow.org/api_docs/python/tf/tanh) for more information.
  60
  61 The Arm NN SDK TensorFlow parser currently partially supports:
  62
  63 **add**
  64
  65 The parser does not support all forms of [broadcast composition](https://www.tensorflow.org/performance/xla/broadcasting), only broadcasting of scalars and 1D tensors. See the TensorFlow [add operator documentation](https://www.tensorflow.org/api_docs/python/tf/add) for more information.
  66
  67 **depthwise_conv2D_native**
  68
  69 The parser only supports a dilation rate of (1,1,1,1). See the TensorFlow [depthwise_conv2d_native documentation](https://www.tensorflow.org/api_docs/python/tf/nn/depthwise_conv2d_native) for more information.
  70
  71 **fused_batch_norm**
  72
  73 The parser does not support training outputs. See the TensorFlow [fused_batch_norm documentation](https://www.tensorflow.org/api_docs/python/tf/nn/fused_batch_norm) for more information.
  74
  75 **matmul**
  76
  77 The parser only supports constant weights in a fully connected layer. See the TensorFlow [matmul documentation](https://www.tensorflow.org/api_docs/python/tf/matmul) for more information.
  78
  79 **multiply**
  80
  81 The parser does not support all forms of [broadcast composition](https://www.tensorflow.org/performance/xla/broadcasting), only broadcasting of scalars and 1D tensors. See the TensorFlow [multiply documentation](https://www.tensorflow.org/api_docs/python/tf/multiply) for more information. No broadcasting supported on the NEON backend.
  82
  83 **placeholder**
  84
  85  The parser only supports the NHWC data format in the input layer. See the TensorFlow [placeholder documentation](https://www.tensorflow.org/api_docs/python/tf/placeholder) for more information.
  86
  87 **reshape**
  88
  89 The parser does not support reshaping to or from 4D. See the TensorFlow [reshape documentation](https://www.tensorflow.org/api_docs/python/tf/reshape) for more information.
  90
  91 **resize_images**
  92
  93 The parser only supports `ResizeMethod.BILINEAR`. See the TensorFlow [resize_images documentation](https://www.tensorflow.org/api_docs/python/tf/image/resize_images) for more information.
  94
  95 **softmax**
  96
  97 The parser only supports 2D inputs and does not support selecting the `softmax` dimension. See the TensorFlow [softmax documentation](https://www.tensorflow.org/api_docs/python/tf/nn/softmax) for more information.
  98
  99
 100
 101 Arm tests these operators with the following TensorFlow fp32 neural networks:
 102
 103 * Cifar10.
 104
 105 * Lenet.
 106
 107 * mobilenet_v1_1.0_224. The Arm NN SDK only supports the non*_quant version of the network. See the [MobileNet_v1 documentation](https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet_v1.md) for more information on _quant networks.
 108
 109 * inception_v3. The Arm NN SDK only supports the official inception_v3 transformed model using the GPU acceleration only, but NEON acceleration is not supported at the moment. See the TensorFlow documentation on [preparing models for mobile deployment](https://www.tensorflow.org/mobile/prepare_models) for more information on how to transform the inception_v3 network.
 110
 111 More machine learning operators will be supported in future releases.