From 590f3f7e0a792ca12ba9e30f59acd6aeafdd48d4 Mon Sep 17 00:00:00 2001 From: James Ward Date: Wed, 2 Dec 2020 10:20:48 +0000 Subject: IVGCVSW-5598 ArmNN Doxygen doc needs update Signed-off-by: James Ward Change-Id: Iac19640fec7aabdfcbb88a0856d4fce3a15d3f27 --- docs/01_parsers.dox | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'docs/01_parsers.dox') diff --git a/docs/01_parsers.dox b/docs/01_parsers.dox index 1c52c4a53b..1af2503f88 100644 --- a/docs/01_parsers.dox +++ b/docs/01_parsers.dox @@ -44,6 +44,7 @@ This reference guide provides a list of Caffe layers the Arm NN SDK currently su - Yolov1_tiny. - Lenet. - MobileNetv1. +- SqueezeNet v1.0 and SqueezeNet v1.1 ## The Arm NN SDK supports the following machine learning layers for Caffe networks: @@ -157,6 +158,7 @@ The Arm NN SDK TensorFlow Lite parser currently supports the following operators - 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 +- DEQUANTIZE - DIV - EXP - FULLY_CONNECTED, Supported Fused Activation: RELU , RELU6 , TANH, NONE @@ -171,10 +173,12 @@ The Arm NN SDK TensorFlow Lite parser currently supports the following operators - NEG - PACK - PAD +- QUANTIZE - RELU - RELU6 - RESHAPE - RESIZE_BILINEAR +- RESIZE_NEAREST_NEIGHBOR - SLICE - SOFTMAX - SPACE_TO_BATCH @@ -199,6 +203,15 @@ Arm tested these operators with the following TensorFlow Lite neural network: - [Quantized SSD MobileNet](http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_quantized_300x300_coco14_sync_2018_07_18.tar.gz) - DeepSpeech v1 converted from [TensorFlow model](https://github.com/mozilla/DeepSpeech/releases/tag/v0.4.1) - DeepSpeaker +- [DeepLab v3+](https://www.tensorflow.org/lite/models/segmentation/overview) +- FSRCNN +- EfficientNet-lite +- RDN converted from [TensorFlow model](https://github.com/hengchuan/RDN-TensorFlow) +- Quantized RDN (CpuRef) +- [Quantized Inception v3](http://download.tensorflow.org/models/tflite_11_05_08/inception_v3_quant.tgz) +- [Quantized Inception v4](http://download.tensorflow.org/models/inception_v4_299_quant_20181026.tgz) (CpuRef) +- Quantized ResNet v2 50 (CpuRef) +- Quantized Yolo v3 (CpuRef) More machine learning operators will be supported in future releases.



@@ -251,6 +264,8 @@ The Arm NN SDK TensorFlow parser currently only supports fp32 operators. - See the TensorFlow [squeeze documentation](https://www.tensorflow.org/api_docs/python/tf/squeeze) for more information. - tanh - See the TensorFlow [tanh documentation](https://www.tensorflow.org/api_docs/python/tf/tanh) for more information. +- transpose + - See the TensorFlow [transpose documentation](https://www.tensorflow.org/api_docs/python/tf/transpose) for more information. ## Partially supported @@ -283,6 +298,8 @@ The Arm NN SDK TensorFlow parser currently only supports fp32 operators. - The parser does not support all forms of [broadcast composition](https://www.tensorflow.org/performance/xla/broadcasting), only broadcasting of 4D and 1D tensors. See the TensorFlow [minimum operator documentation](https://www.tensorflow.org/api_docs/python/tf/math/minimum) for more information. - multiply - 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. +- pack/stack + - See the TensorFlow [stack documentation](https://www.tensorflow.org/api_docs/python/tf/stack) for more information. - pad - Only supports tf.pad function with mode = 'CONSTANT' and constant_values = 0. See the TensorFlow [pad documentation](https://www.tensorflow.org/api_docs/python/tf/pad) for more information. - realdiv @@ -295,9 +312,12 @@ The Arm NN SDK TensorFlow parser currently only supports fp32 operators. - 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. - split - Arm NN supports split along the channel dimension for data formats NHWC and NCHW. +- strided_slice + - See the TensorFlow [strided_slice documentation](https://www.tensorflow.org/api_docs/python/tf/strided_slice) for more information. - subtract - The parser does not support all forms of broadcasting [broadcast composition](https://www.tensorflow.org/performance/xla/broadcasting), only broadcasting of scalars and 1D tensors. See the TensorFlow [subtract documentation](https://www.tensorflow.org/api_docs/python/tf/math/subtract) for more information. + ## Tested networks Arm tests these operators with the following TensorFlow fp32 neural networks: -- cgit v1.2.1